no code implementations • ECCV 2020 • Guo-Sen Xie, Li Liu, Fan Zhu, Fang Zhao, Zheng Zhang, Yazhou Yao, Jie Qin, Ling Shao
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
no code implementations • ECCV 2020 • Jiaxin Chen, Jie Qin, Yuming Shen, Li Liu, Fan Zhu, Ling Shao
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
no code implementations • 6 Jun 2024 • Jiaxi Hu, Qingsong Wen, Sijie Ruan, Li Liu, Yuxuan Liang
In this paper, we begin by validating this theory through wavelet analysis and propose the Transformer-based TwinS model, which consists of three modules to address the non-stationary periodic distributions: Wavelet Convolution, Period-Aware Attention, and Channel-Temporal Mixed MLP.
no code implementations • 30 May 2024 • Weilin Lin, Li Liu, Shaokui Wei, Jianze Li, Hui Xiong
Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.
1 code implementation • 30 May 2024 • Chunhui Zhang, Li Liu, Guanjie Huang, Hao Wen, Xi Zhou, Yanfeng Wang
Most existing trackers are tailored for open-air environments, leading to performance degradation when applied to UOT due to domain gaps.
no code implementations • 27 May 2024 • Fengji Ma, Li Liu, Hei Victor Cheng
Simultaneously, fixed pre-trained image embeddings are used as cross-modal auxiliary supervision to maintain the similarity between the MHE-tuned and original text embeddings by the knowledge distillation, preserving semantic information between different classes.
4 code implementations • 23 May 2024 • Chunhui Zhang, Li Liu, Hao Wen, Xi Zhou, Yanfeng Wang
To leverage more modalities, some recent efforts have been made to learn a unified visual object tracking model for any modality.
no code implementations • 15 May 2024 • Weijie L, Wei Yang, Yuenan Hou, Li Liu, Yongxiang Liu, Xiang Li
Various target characteristics, scene background information, and sensor parameters across ATR datasets challenge the generalization of those methods.
no code implementations • 30 Apr 2024 • Wentao Lei, Li Liu, Jun Wang
Therefore, we propose a novel Gloss-prompted Diffusion-based CS Gesture generation framework (called GlossDiff).
no code implementations • 3 Apr 2024 • Shuxian Fan, Adam Visokay, Kentaro Hoffman, Stephen Salerno, Li Liu, Jeffrey T. Leek, Tyler H. McCormick
In this paper, we develop a method for valid inference using outcomes (in our case COD) predicted from free-form text using state-of-the-art NLP techniques.
1 code implementation • 29 Mar 2024 • Bo wang, Jian Li, Yang Yu, Li Liu, Zhenping Sun, Dewen Hu
Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE).
no code implementations • 22 Mar 2024 • Jinge Wang, Zien Cheng, Qiuming Yao, Li Liu, Dong Xu, Gangqing Hu
The year 2023 marked a significant surge in the exploration of applying large language model (LLM) chatbots, notably ChatGPT, across various disciplines.
no code implementations • 21 Mar 2024 • Lizhe Liu, Bohua Wang, Hongwei Xie, Daqi Liu, Li Liu, Zhiqiang Tian, Kuiyuan Yang, Bing Wang
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems.
1 code implementation • 18 Mar 2024 • YuXuan Li, Xiang Li, Yimain Dai, Qibin Hou, Li Liu, Yongxiang Liu, Ming-Ming Cheng, Jian Yang
While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios.
1 code implementation • 11 Mar 2024 • YuXuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang
To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
Ranked #1 on 2D Object Detection on SARDet-100K (using extra training data)
1 code implementation • 8 Mar 2024 • Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao
We find that concealing deformation perturbations in areas insensitive to human eyes can achieve a better trade-off between imperceptibility and adversarial strength, specifically in parts of the object surface that are complex and exhibit drastic curvature changes.
no code implementations • 7 Mar 2024 • Vanshika Vats, Marzia Binta Nizam, Minghao Liu, Ziyuan Wang, Richard Ho, Mohnish Sai Prasad, Vincent Titterton, Sai Venkat Malreddy, Riya Aggarwal, Yanwen Xu, Lei Ding, Jay Mehta, Nathan Grinnell, Li Liu, Sijia Zhong, Devanathan Nallur Gandamani, Xinyi Tang, Rohan Ghosalkar, Celeste Shen, Rachel Shen, Nafisa Hussain, Kesav Ravichandran, James Davis
In the rapidly evolving landscape of artificial intelligence (AI), the collaboration between human intelligence and AI systems, known as Human-AI (HAI) Teaming, has emerged as a cornerstone for advancing problem-solving and decision-making processes.
1 code implementation • 4 Mar 2024 • Huali Xu, Li Liu, Shuaifeng Zhi, Shaojing Fu, Zhuo Su, Ming-Ming Cheng, Yongxiang Liu
For this reason, this paper explores a Source-Free CDFSL (SF-CDFSL) problem, in which CDFSL is addressed through the use of existing pretrained models instead of training a model with source data, avoiding accessing source data.
1 code implementation • 1 Feb 2024 • Zhuo Su, Jiehua Zhang, Longguang Wang, Hua Zhang, Zhen Liu, Matti Pietikäinen, Li Liu
With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition.
no code implementations • 31 Jan 2024 • Lei Liu, Li Liu, Haizhou Li
Cued Speech (CS) is a pure visual coding method used by hearing-impaired people that combines lip reading with several specific hand shapes to make the spoken language visible.
1 code implementation • 30 Jan 2024 • Bowen Peng, Bo Peng, Jingyuan Xia, Tianpeng Liu, Yongxiang Liu, Li Liu
Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations.
no code implementations • 26 Jan 2024 • Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan, Mingli Zhu, Ruotong Wang, Li Liu, Chao Shen
We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning.
1 code implementation • 7 Jan 2024 • Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, Nicu Sebe
It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef).
Ranked #1 on Camouflaged Object Segmentation on COD
Camouflaged Object Segmentation Dichotomous Image Segmentation +3
no code implementations • 21 Dec 2023 • Peng Zhao, Jiehua Zhang, Bowen Peng, Longguang Wang, YingMei Wei, Yu Liu, Li Liu
2) BNNs consistently exhibit better adversarial robustness under black-box attacks.
1 code implementation • 14 Dec 2023 • Chubin Zhang, Juncheng Yan, Yi Wei, Jiaxin Li, Li Liu, Yansong Tang, Yueqi Duan, Jiwen Lu
As a fundamental task of vision-based perception, 3D occupancy prediction reconstructs 3D structures of surrounding environments.
no code implementations • 13 Dec 2023 • Baoyuan Wu, Shaokui Wei, Mingli Zhu, Meixi Zheng, Zihao Zhu, Mingda Zhang, Hongrui Chen, Danni Yuan, Li Liu, Qingshan Liu
Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some particular cases.
2 code implementations • 26 Nov 2023 • Weijie Li, Yang Wei, Tianpeng Liu, Yuenan Hou, YuXuan Li, Zhen Liu, Yongxiang Liu, Li Liu
Besides, we employ local masks and multi-scale features to accommodate the various small targets in remote sensing.
no code implementations • 25 Oct 2023 • Yuan Li, Li Liu, Penggang Chen, Youmin Zhang, Guoyin Wang
Graph data widely exists in real life, with large amounts of data and complex structures.
no code implementations • 8 Oct 2023 • Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu, Li Liu, Ming-Ming Cheng
Thus, we propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model.
no code implementations • 5 Oct 2023 • Jinting Wang, Li Liu, Jun Wang, Hei Victor Cheng
To overcome this challenge, we introduce the concept of residuals by integrating a statistical face prior to the diffusion process.
1 code implementation • 18 Sep 2023 • Bowen Yin, Xuying Zhang, Zhongyu Li, Li Liu, Ming-Ming Cheng, Qibin Hou
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks.
Ranked #1 on RGB-D Salient Object Detection on DES
1 code implementation • 18 Sep 2023 • Mingjie Pan, Jiaming Liu, Renrui Zhang, Peixiang Huang, Xiaoqi Li, Bing Wang, Hongwei Xie, Li Liu, Shanghang Zhang
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels.
1 code implementation • 12 Sep 2023 • Junjing Zheng, Xinyu Zhang, Yongxiang Liu, Weidong Jiang, Kai Huo, Li Liu
A standard convex SPCA-based model with PSD constraint for unsupervised feature selection is proposed.
no code implementations • 8 Sep 2023 • Li Liu, Da Chen, Minglei Shu, Laurent D. Cohen
These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them.
1 code implementation • 17 Aug 2023 • Li Liu, Lufei Gao, Wentao Lei, Fengji Ma, Xiaotian Lin, Jinting Wang
In summary, this survey paper provides a comprehensive understanding of deep multi-modal learning for various BL generations and recognitions for the first time.
no code implementations • 13 Aug 2023 • Jinghua Zhang, Li Liu, Olli Silvén, Matti Pietikäinen, Dewen Hu
In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL).
Class-Incremental Object Detection Few-Shot Class-Incremental Learning +4
no code implementations • 9 Aug 2023 • Shanshan Huang, Haoxuan Li, Qingsong Li, Chunyuan Zheng, Li Liu
Multimedia recommendation involves personalized ranking tasks, where multimedia content is usually represented using a generic encoder.
1 code implementation • 27 Jul 2023 • Lingdong Kong, Yaru Niu, Shaoyuan Xie, Hanjiang Hu, Lai Xing Ng, Benoit R. Cottereau, Ding Zhao, Liangjun Zhang, Hesheng Wang, Wei Tsang Ooi, Ruijie Zhu, Ziyang Song, Li Liu, Tianzhu Zhang, Jun Yu, Mohan Jing, Pengwei Li, Xiaohua Qi, Cheng Jin, Yingfeng Chen, Jie Hou, Jie Zhang, Zhen Kan, Qiang Ling, Liang Peng, Minglei Li, Di Xu, Changpeng Yang, Yuanqi Yao, Gang Wu, Jian Kuai, Xianming Liu, Junjun Jiang, Jiamian Huang, Baojun Li, Jiale Chen, Shuang Zhang, Sun Ao, Zhenyu Li, Runze Chen, Haiyong Luo, Fang Zhao, Jingze Yu
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
1 code implementation • 24 Jul 2023 • YiQing Wang, Zihan Li, Jieru Mei, Zihao Wei, Li Liu, Chen Wang, Shengtian Sang, Alan Yuille, Cihang Xie, Yuyin Zhou
To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis.
1 code implementation • 17 Jul 2023 • Liu Liu, Shuaifeng Zhi, Zhenhua Du, Li Liu, Xinyu Zhang, Kai Huo, Weidong Jiang
In this paper, we propose a hybrid point-wise Radar-Optical fusion approach for object detection in autonomous driving scenarios.
no code implementations • 11 Jul 2023 • Shuzhou Sun, Shuaifeng Zhi, Qing Liao, Janne Heikkilä, Li Liu
To remedy this, we propose Two-stage Causal Modeling (TsCM) for the SGG task, which takes the long-tailed distribution and semantic confusion as confounders to the Structural Causal Model (SCM) and then decouples the causal intervention into two stages.
no code implementations • 7 Jul 2023 • Chunhui Zhang, Xin Sun, Li Liu, Yiqian Yang, Qiong Liu, Xi Zhou, Yanfeng Wang
This approach achieves feature integration in a unified backbone, removing the need for carefully-designed fusion modules and resulting in a more effective and efficient VL tracking framework.
1 code implementation • 6 Jul 2023 • Yun Liu, Yu-Huan Wu, Shi-Chen Zhang, Li Liu, Min Wu, Ming-Ming Cheng
This dataset enables the training of sophisticated detectors for high-quality CTD.
no code implementations • 15 Jun 2023 • Mingjie Pan, Li Liu, Jiaming Liu, Peixiang Huang, Longlong Wang, Shanghang Zhang, Shaoqing Xu, Zhiyi Lai, Kuiyuan Yang
In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023.
Ranked #3 on Prediction Of Occupancy Grid Maps on Occ3D-nuScenes
1 code implementation • 15 Jun 2023 • Bo wang, Yifan Zhang, Jian Li, Yang Yu, Zhenping Sun, Li Liu, Dewen Hu
The occlusion problem remains a crucial challenge in optical flow estimation (OFE).
no code implementations • 6 Jun 2023 • Jianrong Wang, Yaxin Zhao, Li Liu, Tianyi Xu, Qi Li, Sen Li
Given an audio clip and a reference face image, the goal of the talking head generation is to generate a high-fidelity talking head video.
1 code implementation • 5 Jun 2023 • Lufei Gao, Shan Huang, Li Liu
Cued Speech (CS) is a multi-modal visual coding system combining lip reading with several hand cues at the phonetic level to make the spoken language visible to the hearing impaired.
1 code implementation • 4 Jun 2023 • Jianrong Wang, Yuchen Huo, Li Liu, Tianyi Xu, Qi Li, Sen Li
Audio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction.
no code implementations • 1 Jun 2023 • Ruotong Wang, Hongrui Chen, Zihao Zhu, Li Liu, Baoyuan Wu
Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbed \textit{backdoor attack}.
1 code implementation • 18 May 2023 • Yixiong Chen, Li Liu, Chris Ding
This paper introduces a novel explainable image quality evaluation approach called X-IQE, which leverages visual large language models (LLMs) to evaluate text-to-image generation methods by generating textual explanations.
no code implementations • 15 May 2023 • Penghui Wei, Hongjian Dou, Shaoguo Liu, Rongjun Tang, Li Liu, Liang Wang, Bo Zheng
We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms.
1 code implementation • 14 May 2023 • Chunhui Zhang, Li Liu, Yawen Cui, Guanjie Huang, Weilin Lin, Yiqian Yang, Yuehong Hu
As the first to comprehensively review the progress of segmenting anything task for vision and beyond based on the foundation model of SAM, this work focuses on its applications to various tasks and data types by discussing its historical development, recent progress, and profound impact on broad applications.
no code implementations • 28 Apr 2023 • Yuchen Sun, Tianpeng Liu, Panhe Hu, Qing Liao, Shaojing Fu, Nenghai Yu, Deke Guo, Yongxiang Liu, Li Liu
Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields.
1 code implementation • 24 Apr 2023 • Jinghua Zhang, Li Liu, Kai Gao, Dewen Hu
In forward-compatible learning, we propose an innovative virtual class synthesis strategy and a Center-Triplet (CT) loss to enhance discriminative feature learning.
1 code implementation • 13 Apr 2023 • Zhuo Su, Jiehua Zhang, Tianpeng Liu, Zhen Liu, Shuanghui Zhang, Matti Pietikäinen, Li Liu
This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution.
1 code implementation • 7 Apr 2023 • Weijie Li, Wei Yang, Wenpeng Zhang, Tianpeng Liu, Yongxiang Liu, Li Liu
However, robustly recognizing vehicle targets is a challenging task in SAR due to the large intraclass variations and small interclass variations.
1 code implementation • CVPR 2023 • Xinyi Ying, Li Liu, Yingqian Wang, Ruojing Li, Nuo Chen, Zaiping Lin, Weidong Sheng, Shilin Zhou
Interestingly, during the training phase supervised by point labels, we discover that CNNs first learn to segment a cluster of pixels near the targets, and then gradually converge to predict groundtruth point labels.
no code implementations • 4 Apr 2023 • Bowen Peng, Jianyue Xie, Bo Peng, Li Liu
The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning.
2 code implementations • 3 Apr 2023 • Weijie Li, Wei Yang, Li Liu, Wenpeng Zhang, Yongxiang Liu
Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR.
no code implementations • 23 Mar 2023 • Yande Li, Mingjie Wang, Minglun Gong, Yonggang Lu, Li Liu
The ever-increasing demands for intuitive interactions in Virtual Reality has triggered a boom in the realm of Facial Expression Recognition (FER).
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 15 Mar 2023 • Zhuo Su, Matti Pietikäinen, Li Liu
LBP is a successful hand-crafted feature descriptor in computer vision.
no code implementations • 15 Mar 2023 • Huali Xu, Shuaifeng Zhi, Shuzhou Sun, Vishal M. Patel, Li Liu
Deep learning has been highly successful in computer vision with large amounts of labeled data, but struggles with limited labeled training data.
no code implementations • 3 Mar 2023 • Wentao Lei, Lei Liu, Li Liu
Experiments on two medical image datasets (i. e., ISIC 2018 challenge and ChestX-ray14) show that our method outperforms state-of-the-art SSL methods.
1 code implementation • 19 Feb 2023 • Baoyuan Wu, Zihao Zhu, Li Liu, Qingshan Liu, Zhaofeng He, Siwei Lyu
Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans.
1 code implementation • 12 Feb 2023 • Yawen Cui, Zitong Yu, Rizhao Cai, Xun Wang, Alex C. Kot, Li Liu
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.
1 code implementation • 24 Jan 2023 • Yawen Cui, Wanxia Deng, Haoyu Chen, Li Liu
Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all encountered classes previously.
no code implementations • 5 Jan 2023 • Ang Li, Jiayi Han, Yongjian Zhao, Keyu Li, Li Liu
While the US is not a standard paradigm for spinal surgery, the scarcity of intra-operative clinical US data is an insurmountable bottleneck in training a neural network.
no code implementations • 3 Jan 2023 • Janne Mustaniemi, Juho Kannala, Esa Rahtu, Li Liu, Janne Heikkilä
Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems.
1 code implementation • ICCV 2023 • Yaopei Zeng, Lei Liu, Li Liu, Li Shen, Shaoguo Liu, Baoyuan Wu
In particular, a proxy is derived from the accumulated gradients uploaded by the clients after local training, and is shared by all clients as the class prior for re-balance training.
1 code implementation • 29 Dec 2022 • Li Liu, Penggang Chen, Xin Li, William K. Cheung, Youmin Zhang, Qun Liu, Guoyin Wang
Aligning users across networks using graph representation learning has been found effective where the alignment is accomplished in a low-dimensional embedding space.
1 code implementation • 28 Dec 2022 • Peixiang Huang, Li Liu, Renrui Zhang, Song Zhang, Xinli Xu, Baichao Wang, Guoyi Liu
In this paper, we propose the learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors for both dense depth and BEV features, termed as TiG-BEV.
no code implementations • 23 Dec 2022 • Yongling Xu, Yang Du, Jing Zou, Tianying Zhou, Lushan Xiao, Li Liu, Pengcheng
In this paper, we propose a deep model called Attention-based Multiple Dimensions EEG Transformer (AMDET), which can exploit the complementarity among the spectral-spatial-temporal features of EEG data by employing the multi-dimensional global attention mechanism.
1 code implementation • 8 Dec 2022 • Yixiong Chen, Chunhui Zhang, Chris H. Q. Ding, Li Liu
In this work, we pre-train DNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications.
no code implementations • 2 Dec 2022 • Lei Liu, Li Liu
To our knowledge, this is the first work on ACSR for Mandarin Chinese.
no code implementations • 1 Dec 2022 • Yixiong Chen, Jingxian Li, Chris Ding, Li Liu
Deep transfer learning (DTL) has formed a long-term quest toward enabling deep neural networks (DNNs) to reuse historical experiences as efficiently as humans.
no code implementations • 25 Nov 2022 • Taoyong Cui, Jianze Li, Yuhan Dong, Li Liu
In the first stage, we propose a novel algorithm called polar decomposition-based orthogonal initialization (PDOI) to find a good initialization for the orthogonal optimization.
no code implementations • 7 Nov 2022 • Andrey Ignatov, Radu Timofte, Cheng-Ming Chiang, Hsien-Kai Kuo, Yu-Syuan Xu, Man-Yu Lee, Allen Lu, Chia-Ming Cheng, Chih-Cheng Chen, Jia-Ying Yong, Hong-Han Shuai, Wen-Huang Cheng, Zhuang Jia, Tianyu Xu, Yijian Zhang, Long Bao, Heng Sun, Diankai Zhang, Si Gao, Shaoli Liu, Biao Wu, Xiaofeng Zhang, Chengjian Zheng, Kaidi Lu, Ning Wang, Xiao Sun, HaoDong Wu, Xuncheng Liu, Weizhan Zhang, Caixia Yan, Haipeng Du, Qinghua Zheng, Qi Wang, Wangdu Chen, Ran Duan, Mengdi Sun, Dan Zhu, Guannan Chen, Hojin Cho, Steve Kim, Shijie Yue, Chenghua Li, Zhengyang Zhuge, Wei Chen, Wenxu Wang, Yufeng Zhou, Xiaochen Cai, Hengxing Cai, Kele Xu, Li Liu, Zehua Cheng, Wenyi Lian, Wenjing Lian
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
no code implementations • 4 Nov 2022 • Jiehua Zhang, Xueyang Zhang, Zhuo Su, Zitong Yu, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu
For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.
no code implementations • 28 Oct 2022 • Xuefeng Yang, Li Liu, Wenju Zhou, Jing Shi, Yinggang Zhang, Xin Hu, Huiyu Zhou
Moreover, the privacy of the system is analyzed to ensure the security of the real data.
1 code implementation • 10 Oct 2022 • Chunhui Zhang, Yixiong Chen, Li Liu, Qiong Liu, Xi Zhou
This work proposes a hierarchical contrastive learning (HiCo) method to improve the transferability for the US video model pretraining.
no code implementations • 3 Oct 2022 • Yu Zhang, Li Liu, Chen Diao, Ning Cai
Computer model has been extensively adopted to overcome the time limitation of language evolution by transforming language theory into physical modeling mechanism, which helps to explore the general laws of the evolution.
1 code implementation • 13 Sep 2022 • Zhuo Su, Max Welling, Matti Pietikäinen, Li Liu
Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance.
1 code implementation • 11 Sep 2022 • Bowen Peng, Bo Peng, Jie zhou, Jianyue Xie, Li Liu
Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers).
1 code implementation • ACM Transactions on Multimedia Computing, Communications and Applications 2022 • Ruoyu Chen, Jingzhi Li, Hua Zhang, Changchong Sheng, Li Liu, Xiaochun Cao
Different from existing models, in this paper, we propose a new interpretation method that explains the image similarity models by salience maps and attribute words.
no code implementations • 6 Sep 2022 • Zichao Li, Li Liu, Zeyu Wang, Yuyin Zhou, Cihang Xie
Adversarial training (AT) with samples generated by Fast Gradient Sign Method (FGSM), also known as FGSM-AT, is a computationally simple method to train robust networks.
no code implementations • 17 Aug 2022 • Huali Xu, Shuaifeng Zhi, Li Liu
The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxiliary dataset, despite the differences between the domains of the two datasets.
no code implementations • 10 Aug 2022 • Li Liu, Xiangeng Fang, Di Wang, Weijing Tang, Kevin He
Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis.
2 code implementations • 5 Aug 2022 • Runkai Zheng, Rongjun Tang, Jianze Li, Li Liu
Pruning these channels was then shown to be effective in mitigating the backdoor behaviors.
no code implementations • 3 Aug 2022 • Yuli Sun, Lin Lei, Dongdong Guan, Gangyao Kuang, Li Liu
In this first part, we analyze the HCD with GSP from the vertex domain.
no code implementations • 3 Aug 2022 • Yuli Sun, Lin Lei, Dongdong Guan, Gangyao Kuang, Li Liu
Then, we propose a regression model for the HCD, which decomposes the source signal into the regressed signal and changed signal, and requires the regressed signal have the same spectral property as the target signal on the same graph.
no code implementations • 26 Jul 2022 • Ye Wang, Jingbo Liao, Hong Yu, Guoyin Wang, Xiaoxia Zhang, Li Liu
Particularly, the model integrates the macro-level guided-category knowledge and micro-level open-domain dialogue data for the training, leveraging the priori knowledge into the latent space, which enables the model to disentangle the latent variables within the mesoscopic scale.
no code implementations • 20 Jul 2022 • Yawen Cui, Zitong Yu, Wei Peng, Li Liu
Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding the overfitting and catastrophic forgetting simultaneously.
no code implementations • 16 Jul 2022 • Wei Wu, Junlin He, Yu Qiao, Guoheng Fu, Li Liu, Jin Yu
The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i. e., feature vectors) and structured (i. e., related attributes) constraints.
1 code implementation • 3 Jun 2022 • Yixiong Chen, Li Liu, Jingxian Li, Hua Jiang, Chris Ding, Zongwei Zhou
In this work, we propose a meta-learning-based LR tuner, named MetaLR, to make different layers automatically co-adapt to downstream tasks based on their transferabilities across domains.
no code implementations • 30 May 2022 • Jiehua Zhang, Zhuo Su, Li Liu
Face recognition is one of the most active tasks in computer vision and has been widely used in the real world.
no code implementations • 22 May 2022 • Changchong Sheng, Gangyao Kuang, Liang Bai, Chenping Hou, Yulan Guo, Xin Xu, Matti Pietikäinen, Li Liu
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment.
no code implementations • 2 Apr 2022 • Jianrong Wang, Jinyu Liu, Longxuan Zhao, Shanyu Wang, Ruiguo Yu, Li Liu
Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals.
no code implementations • 1 Apr 2022 • Jianrong Wang, Zixuan Wang, Xiaosheng Hu, XueWei Li, Qiang Fang, Li Liu
Experimental results show that the speech synthesized by our model is comparable to the personalized speech synthesized by training a large amount of audio data in previous works.
1 code implementation • 8 Feb 2022 • Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang
Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.
1 code implementation • 19 Jan 2022 • Chunhui Zhang, Guanjie Huang, Li Liu, Shan Huang, Yinan Yang, Xiang Wan, Shiming Ge, DaCheng Tao
In this work, we propose WebUAV-3M, the largest public UAV tracking benchmark to date, to facilitate both the development and evaluation of deep UAV trackers.
no code implementations • 18 Jan 2022 • Yan Zhao, Lingjun Zhao, Zhong Liu, Dewen Hu, Gangyao Kuang, Li Liu
Aircraft detection in Synthetic Aperture Radar (SAR) imagery is a challenging task in SAR Automatic Target Recognition (SAR ATR) areas due to aircraft's extremely discrete appearance, obvious intraclass variation, small size and serious background's interference.
1 code implementation • 11 Jan 2022 • Jinyu Lu, Guoqiang Liu, Bing Sun, Chao Li, Li Liu
In CRYPTO 2019, Gohr made a pioneering attempt and successfully applied deep learning to the differential cryptanalysis against NSA block cipher SPECK32/64, achieving higher accuracy than the pure differential distinguishers.
1 code implementation • CVPR 2022 • Kunhong Li, Longguang Wang, Li Liu, Qing Ran, Kai Xu, Yulan Guo
Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.
Ranked #1 on Camera Localization on Aachen Day-Night benchmark
1 code implementation • 4 Jan 2022 • Xinyi Ying, Yingqian Wang, Longguang Wang, Weidong Sheng, Li Liu, Zaiping Lin, Shilin Zhou
Specifically, motivated by the local motion prior in the spatio-temporal dimension, we propose a local spatio-temporal attention module to perform implicit frame alignment and incorporate the local spatio-temporal information to enhance the local features (especially for small targets).
1 code implementation • CVPR 2022 • Longguang Wang, Xiaoyu Dong, Yingqian Wang, Li Liu, Wei An, Yulan Guo
Since a linear quantizer (i. e., round(*) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use pre-defined functions (e. g., exponential function) with learnable parameters to build the quantizer for joint optimization.
1 code implementation • CVPR 2022 • Siwei Wang, Xinwang Liu, Li Liu, Wenxuan Tu, Xinzhong Zhu, Jiyuan Liu, Sihang Zhou, En Zhu
Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations.
1 code implementation • 23 Nov 2021 • Junke Wang, Xitong Yang, Hengduo Li, Li Liu, Zuxuan Wu, Yu-Gang Jiang
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost.
1 code implementation • 22 Nov 2021 • Zihan Yan, Li Liu, Xin Li, William K. Cheung, Youmin Zhang, Qun Liu, Guoyin Wang
Social network alignment aims at aligning person identities across social networks.
no code implementations • 3 Nov 2021 • Keyu Li, Yangxin Xu, Jian Wang, Dong Ni, Li Liu, Max Q. -H. Meng
Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers.
no code implementations • 25 Oct 2021 • Yu Zhang, Chen Zhang, Renxin Yang, Jing Lyu, Li Liu, Xu Cai
The MMC-HVDC connected offshore wind farms (OWFs) could suffer short circuit fault (SCF), whereas their transient stability is not well analysed.
no code implementations • 20 Oct 2021 • Hengyang Wang, Xianghao Zhan, Li Liu, Asif Ullah, Huiyan Li, Han Gao, You Wang, Guang Li
The results show that DRCA improved the classification accuracy on six subjects (p < 0. 05), compared with the baseline models trained only with the source domain data;, while CPSC did not guarantee the accuracy improvement.
no code implementations • 8 Oct 2021 • Jiehua Zhang, Zhuo Su, Yanghe Feng, Xin Lu, Matti Pietikäinen, Li Liu
The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.
no code implementations • 16 Sep 2021 • Junfeng Hu, Yuxuan Liang, Zhencheng Fan, Li Liu, Yifang Yin, Roger Zimmermann
Specifically, we introduce a joint spatiotemporal graph attention network to learn the relations across space and time for short-term patterns.
no code implementations • 3 Sep 2021 • Navid Ahmadinejad, Li Liu
It then computes two weighted sums of Jaccard indices measuring the reconciliation from classes to clusters and vice versa.
2 code implementations • ICCV 2021 • Zhuo Su, Wenzhe Liu, Zitong Yu, Dewen Hu, Qing Liao, Qi Tian, Matti Pietikäinen, Li Liu
A faster version of PiDiNet with less than 0. 1M parameters can still achieve comparable performance among state of the arts with 200 FPS.
Ranked #2 on Edge Detection on BRIND
no code implementations • 2 Aug 2021 • Li Liu, Xianghao Zhan, Xikai Yang, Xiaoqing Guan, Rumeng Wu, Zhan Wang, Zhiyuan Luo, You Wang, Guang Li
As an effective framework to quantify the prediction reliability, conformal prediction (CP) was developed with the CPKNN (CP with kNN).
1 code implementation • 8 Jul 2021 • Lei Liu, Li Liu
Specifically, we demonstrate that long-tailed recognition suffers from both sample number and category similarity.
no code implementations • 7 Jun 2021 • Hao Guo, Jiuyang Tang, Weixin Zeng, Xiang Zhao, Li Liu
To mitigate this problem, a viable approach is to integrate complementary knowledge from other MMKGs.
1 code implementation • CVPR 2020 • Yichao Yan, Jie Qin1, Jiaxin Chen, Li Liu, Fan Zhu, Ying Tai, Ling Shao
In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i. e., part-based features) across different temporal ranges.
Ranked #6 on Person Re-Identification on iLIDS-VID
1 code implementation • 29 Apr 2021 • Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
1 code implementation • 14 Apr 2021 • Li Liu, Xianghao Zhan, Ziheng Duan, Yi Wu, Rumeng Wu, Xiaoqing Guan, Zhan Wang, You Wang, Guang Li
In this study, we classified different origins of three categories of herbal medicines with different feature extraction methods: manual feature extraction, mathematical transformation, deep learning algorithms.
1 code implementation • CVPR 2021 • Yichao Yan, Jinpeng Li, Jie Qin, Song Bai, Shengcai Liao, Li Liu, Fan Zhu, Ling Shao
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).
Ranked #10 on Person Search on CUHK-SYSU
no code implementations • 1 Mar 2021 • Keyu Li, Jian Wang, Yangxin Xu, Hao Qin, Dongsheng Liu, Li Liu, Max Q. -H. Meng
Furthermore, we propose a confidence-based approach to encode the optimization of image quality in the learning process.
no code implementations • 5 Feb 2021 • Li Liu, Xianghao Zhan, Rumeng Wu, Xiaoqing Guan, Zhan Wang, Wei zhang, Mert Pilanci, You Wang, Zhiyuan Luo, Guang Li
Furthermore, this study provides a systematic analysis of different augmentation strategies.
no code implementations • 27 Jan 2021 • Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
no code implementations • 26 Jan 2021 • Delu Zeng, Minyu Liao, Mohammad Tavakolian, Yulan Guo, Bolei Zhou, Dewen Hu, Matti Pietikäinen, Li Liu
Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision.
1 code implementation • 4 Jan 2021 • Li Liu, Mengge He, Guanghui Xu, Mingkui Tan, Qi Wu
Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice.
Ranked #3 on KG-to-Text Generation on AGENDA
2 code implementations • ICCV 2021 • Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang
Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.
Ranked #21 on Knowledge Distillation on ImageNet
no code implementations • ICCV 2021 • Jiyuan Liu, Xinwang Liu, Yuexiang Yang, Li Liu, Siqi Wang, Weixuan Liang, Jiangyong Shi
In this way, the generated partition can guide multi-view matrix factorization to produce more purposive coefficient matrix which, as a feedback, improves the quality of partition.
1 code implementation • ICCV 2021 • Xinwang Liu, Sihang Zhou, Li Liu, Chang Tang, Siwei Wang, Jiyuan Liu, Yi Zhang
After that, we theoretically show that the objective of SimpleMKKM is a special case of this local kernel alignment criterion with normalizing each base kernel matrix.
no code implementations • 1 Jan 2021 • Benyi Hu, Chi Zhang, Yuehu Liu, Le Wang, Li Liu
Long-tailed visual class recognition poses significant challenges to traditional machine learning and emerging deep networks due to its inherent class imbalance.
no code implementations • 24 Dec 2020 • Li Liu, Wenju Zhou, Minrui Fei, Zhile Yang, Hongyong Yang, Huiyu Zhou
This paper investigates an issue of distributed fusion estimation under network-induced complexity and stochastic parameter uncertainties.
1 code implementation • 25 Nov 2020 • Yixiong Chen, Chunhui Zhang, Li Liu, Cheng Feng, Changfeng Dong, Yongfang Luo, Xiang Wan
To alleviate this problem, an US dataset named US-4 is constructed for direct pretraining on the same domain.
no code implementations • 22 Nov 2020 • Runkai Zheng, Zhijia Yu, Yinqi Zhang, Chris Ding, Hei Victor Cheng, Li Liu
A major challenge in Fine-Grained Visual Classification (FGVC) is distinguishing various categories with high inter-class similarity by learning the feature that differentiate the details.
Ranked #12 on Fine-Grained Image Classification on FGVC Aircraft
no code implementations • 12 Nov 2020 • Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi
Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes.
no code implementations • 5 Nov 2020 • Shen Gao, Xiuying Chen, Li Liu, Dongyan Zhao, Rui Yan
Hence, in this paper, we propose to recommend an appropriate sticker to user based on multi-turn dialog context and sticker using history of user.
no code implementations • 2 Nov 2020 • Lufei Gao, Ruisong Zhou, Changfeng Dong, Cheng Feng, Zhen Li, Xiang Wan, Li Liu
With the development of radiomics, noninvasive diagnosis like ultrasound (US) imaging plays a very important role in automatic liver fibrosis diagnosis (ALFD).
no code implementations • 26 Oct 2020 • Gang Wang, Qunxi Dong, Jianfeng Wu, Yi Su, Kewei Chen, Qingtang Su, Xiaofeng Zhang, Jinguang Hao, Tao Yao, Li Liu, Caiming Zhang, Richard J Caselli, Eric M Reiman, Yalin Wang
With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.
1 code implementation • 19 Oct 2020 • Zhuo Su, Linpu Fang, Deke Guo, Dewen Hu, Matti Pietikäinen, Li Liu
Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated computation and substantially reduced memory footprint that appeal to the development of resource constrained devices.
no code implementations • 16 Oct 2020 • Wei Chen, Weiping Wang, Li Liu, Michael S. Lew
The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.
1 code implementation • 13 Oct 2020 • Jianrong Wang, Tong Wu, Shanyu Wang, Mei Yu, Qiang Fang, Ju Zhang, Li Liu
To this end, in this work, we present a novel end-to-end 3D lip motion Network (3LMNet) by utilizing the sentence-level 3D lip motion (S3DLM) to recognize speakers in both the text-independent and text-dependent contexts.
no code implementations • 28 Sep 2020 • Bingjie Yan, Yize Zhou, Boyi Liu, Jun Wang, Yuhan Zhang, Li Liu, Xiaolan Nie, Zhiwei Fan, Zhixuan Liang
However, there is a lack of a sufficiently reasonable contribution measurement mechanism to distribute the reward for each agent.
1 code implementation • CVPR 2021 • Lei Huang, Yi Zhou, Li Liu, Fan Zhu, Ling Shao
Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.
no code implementations • 27 Sep 2020 • Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
no code implementations • 9 Sep 2020 • Lei Liu, Wentao Lei, Yongfang Luo, Cheng Feng, Xiang Wan, Li Liu
Ultrasound (US) is a non-invasive yet effective medical diagnostic imaging technique for the COVID-19 global pandemic.
no code implementations • 21 Aug 2020 • Hao Luo, Li Liu
A key challenge of oversampling in imbalanced classification is that the generation of new minority samples often neglects the usage of majority classes, resulting in most new minority sampling spreading the whole minority space.
1 code implementation • 13 Jul 2020 • Cong Chen, Shouyang Dong, Ye Tian, Kunlin Cao, Li Liu, Yuanhao Guo
(1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student.
1 code implementation • ECCV 2020 • Linpu Fang, Xingyan Liu, Li Liu, Hang Xu, Wenxiong Kang
The key ideas are two-fold: a) explicitly modeling the dependencies among joints and the relations between the pixels and the joints for better local feature representation learning; b) unifying the dense pixel-wise offset predictions and direct joint regression for end-to-end training.
no code implementations • 9 Jul 2020 • Jianrong Wang, Xiaosheng Hu, Li Liu, Wei Liu, Mei Yu, Tianyi Xu
Given a speaker's speech, it is interesting to see if it is possible to generate this speaker's face.
1 code implementation • ECCV 2020 • Zhuo Su, Linpu Fang, Wenxiong Kang, Dewen Hu, Matti Pietikäinen, Li Liu
In this paper, we propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly.
3 code implementations • 20 Jun 2020 • Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao
This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales.
Ranked #69 on Semantic Segmentation on ADE20K val
no code implementations • 17 Jun 2020 • Jianrong Wang, Ge Zhang, Zhen-Yu Wu, XueWei Li, Li Liu
Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects.
1 code implementation • CVPR 2022 • Yan Feng, Baoyuan Wu, Yanbo Fan, Li Liu, Zhifeng Li, Shutao Xia
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown.
2 code implementations • 10 Apr 2020 • Ionut Cosmin Duta, Li Liu, Fan Zhu, Ling Shao
We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths.
1 code implementation • CVPR 2020 • Lei Huang, Li Liu, Fan Zhu, Diwen Wan, Zehuan Yuan, Bo Li, Ling Shao
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.
1 code implementation • CVPR 2020 • Lei Huang, Lei Zhao, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
Our work originates from the observation that while various whitening transformations equivalently improve the conditioning, they show significantly different behaviors in discriminative scenarios and training Generative Adversarial Networks (GANs).
1 code implementation • 10 Mar 2020 • Shen Gao, Xiuying Chen, Chang Liu, Li Liu, Dongyan Zhao, Rui Yan
Stickers with vivid and engaging expressions are becoming increasingly popular in online messaging apps, and some works are dedicated to automatically select sticker response by matching text labels of stickers with previous utterances.
no code implementations • 8 Mar 2020 • Li Liu, Da Chen, Ming-Lei Shu, Baosheng Li, Huazhong Shu, Michel Paques, Laurent D. Cohen
Tubular structure tracking is a crucial task in the fields of computer vision and medical image analysis.
2 code implementations • CVPR 2020 • Yuming Shen, Jie Qin, Jiaxin Chen, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao
One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.
no code implementations • ECCV 2020 • Lei Huang, Jie Qin, Li Liu, Fan Zhu, Ling Shao
To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.
2 code implementations • 6 Jan 2020 • Longguang Wang, Yulan Guo, Li Liu, Zaiping Lin, Xinpu Deng, Wei An
The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames.
Ranked #6 on Video Super-Resolution on MSU Super-Resolution for Video Compression (BSQ-rate over ERQA metric)
3 code implementations • 27 Dec 2019 • Yulan Guo, Hanyun Wang, Qingyong Hu, Hao liu, Li Liu, Mohammed Bennamoun
To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
no code implementations • NeurIPS 2019 • Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong liu, Yu Li, Ling Shao
DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.
no code implementations • 18 Nov 2019 • Yunyi Li, Li Liu, Yu Zhao, Xiefeng Cheng, Guan Gui
The popular L_2-norm and M-estimator are employed for standard image CS and robust CS problem to fit the data respectively.
1 code implementation • 6 Nov 2019 • Junfeng Hu, Zhencheng Fan, Jun Liao, Li Liu
The primary goal of skeletal motion prediction is to generate future motion by observing a sequence of 3D skeletons.
no code implementations • 16 Sep 2019 • Huan Xiong, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao
Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and machine learning.
1 code implementation • 26 Aug 2019 • Yuming Shen, Jie Qin, Jiaxin Chen, Li Liu, Fan Zhu
Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries.
2 code implementations • ICCV 2019 • Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, Ling Shao
Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner.
no code implementations • 22 Jul 2019 • Chengyu Guo, Jingyun Liang, Geng Zhan, Zhong Liu, Matti Pietikäinen, Li Liu
It is computationally efficient and only marginally increases the cost of computing LBPTOP, yet is extremely effective for ME recognition.
1 code implementation • 17 Jun 2019 • Yingkun Hou, Jun Xu, Mingxia Liu, Guanghai Liu, Li Liu, Fan Zhu, Ling Shao
This is motivated by the fact that finding closely similar pixels is more feasible than similar patches in natural images, which can be used to enhance image denoising performance.
1 code implementation • 17 Jun 2019 • Jun Xu, Yuan Huang, Ming-Ming Cheng, Li Liu, Fan Zhu, Zhou Xu, Ling Shao
A simple but useful observation on our NAC is: as long as the noise is weak, it is feasible to learn a self-supervised network only with the corrupted image, approximating the optimal parameters of a supervised network learned with pairs of noisy and clean images.
1 code implementation • 16 Jun 2019 • Jun Xu, Yingkun Hou, Dongwei Ren, Li Liu, Fan Zhu, Mengyang Yu, Haoqian Wang, Ling Shao
A novel Structure and Texture Aware Retinex (STAR) model is further proposed for illumination and reflectance decomposition of a single image.
no code implementations • 27 May 2019 • Yazhou Yao, Zeren Sun, Fumin Shen, Li Liu, Li-Min Wang, Fan Zhu, Lizhong Ding, Gangshan Wu, Ling Shao
To address this issue, we present an adaptive multi-model framework that resolves polysemy by visual disambiguation.
5 code implementations • CVPR 2019 • Lei Huang, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
With the support of SND, we provide natural explanations to several phenomena from the perspective of optimization, e. g., why group-wise whitening of DBN generally outperforms full-whitening and why the accuracy of BN degenerates with reduced batch sizes.
Ranked #8 on Robust Object Detection on DWD
no code implementations • 5 Dec 2018 • Ying Shen, Yang Deng, Kaiqi Yuan, Li Liu, Yong liu
Experiments show that our selected features have achieved a precision rate of 86. 77%, a recall rate of 89. 03% and an F1 score of 87. 89%.
no code implementations • 16 Nov 2018 • Mincong Luo, Xinfu He, Li Liu
In this paper, we propose a generative adversarial model based on prior knowledge and attention mechanism to achieve the generation of irradiated material images (data-to-image model), and a prediction model for corresponding industrial performance (image-to-data model).
no code implementations • ECCV 2018 • Zheng Zhang, Li Liu, Jie Qin, Fan Zhu, Fumin Shen, Yong Xu, Ling Shao, Heng Tao Shen
How to economically cluster large-scale multi-view images is a long-standing problem in computer vision.
no code implementations • 6 Sep 2018 • Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, Matti Pietikäinen
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.
1 code implementation • ECCV 2018 • Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Jie Qin, Ling Shao, Heng Tao Shen
Despite the remarkable success of Convolutional Neural Networks (CNNs) on generalized visual tasks, high computational and memory costs restrict their comprehensive applications on consumer electronics (e. g., portable or smart wearable devices).
1 code implementation • ECCV 2018 • Jingyi Zhang, Fumin Shen, Li Liu, Fan Zhu, Mengyang Yu, Ling Shao, Heng Tao Shen, Luc van Gool
The generative model learns a mapping that the distributions of sketches can be indistinguishable from the distribution of natural images using an adversarial loss, and simultaneously learns an inverse mapping based on the cycle consistency loss in order to enhance the indistinguishability.
no code implementations • ECCV 2018 • Guosheng Hu, Li Liu, Yang Yuan, Zehao Yu, Yang Hua, Zhihong Zhang, Fumin Shen, Ling Shao, Timothy Hospedales, Neil Robertson, Yongxin Yang
To advance subtle expression recognition, we contribute a Large-scale Subtle Emotions and Mental States in the Wild database (LSEMSW).
no code implementations • 15 Aug 2018 • MinZhong Luo, Li Liu
First, the formula is abstractly expressed as a multiway tree model, and then each step of the formula derivation transformation is abstracted as a mapping of multiway trees.
no code implementations • 5 Aug 2018 • Jiaojiao Zhao, Li Liu, Cees G. M. Snoek, Jungong Han, Ling Shao
While many image colorization algorithms have recently shown the capability of producing plausible color versions from gray-scale photographs, they still suffer from the problems of context confusion and edge color bleeding.
no code implementations • 30 Jun 2018 • Li Liu, Jiasong Wu, Dengwang Li, Lotfi Senhadji, Huazhong Shu
Results: The error rates for different fractional orders of FrScatNet are examined and show that the classification accuracy is significantly improved in fractional scattering domain.
no code implementations • 2 Jun 2018 • Yi-Chao Wu, Fei Yin, Xu-Yao Zhang, Li Liu, Cheng-Lin Liu
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications.
1 code implementation • 15 May 2018 • Delu Zeng, Yixuan He, Li Liu, Zhihong Chen, Jiabin Huang, Jie Chen, John Paisley
In this paper, we propose an end-to-end generic salient object segmentation model called Metric Expression Network (MEnet) to deal with saliency detection with the tolerance of distortion.
1 code implementation • CVPR 2018 • Yuming Shen, Li Liu, Fumin Shen, Ling Shao
As an important part of ZSIH, we formulate a generative hashing scheme in reconstructing semantic knowledge representations for zero-shot retrieval.
no code implementations • 13 Feb 2018 • Li Liu, Jie Chen, Guoying Zhao, Paul Fieguth, Xilin Chen, Matti Pietikäinen
Because extreme scale variations are not necessarily present in most standard texture databases, to support the proposed extreme-scale aspects of texture understanding we are developing a new dataset, the Extreme Scale Variation Textures (ESVaT), to test the performance of our framework.
no code implementations • 31 Jan 2018 • Li Liu, Jie Chen, Paul Fieguth, Guoying Zhao, Rama Chellappa, Matti Pietikainen
Texture is a fundamental characteristic of many types of images, and texture representation is one of the essential and challenging problems in computer vision and pattern recognition which has attracted extensive research attention.
1 code implementation • 31 Aug 2017 • Yunxuan Zhang, Li Liu, Cheng Li, Chen Change Loy
We introduce a novel approach for annotating large quantity of in-the-wild facial images with high-quality posterior age distribution as labels.
Ranked #7 on Age Estimation on MORPH Album2 (using extra training data)
no code implementations • 22 Aug 2017 • Yazhou Yao, Jian Zhang, Fumin Shen, Li Liu, Fan Zhu, Dongxiang Zhang, Heng-Tao Shen
To eliminate manual annotation, in this work, we propose a novel image dataset construction framework by employing multiple textual queries.
no code implementations • ICCV 2017 • Yuming Shen, Li Liu, Ling Shao, Jingkuan Song
Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching.
no code implementations • CVPR 2017 • Jie Qin, Li Liu, Ling Shao, Fumin Shen, Bingbing Ni, Jiaxin Chen, Yunhong Wang
Our ZSECOC equips the conventional ECOC with the additional capability of ZSAR, by addressing the domain shift problem.
Ranked #4 on Zero-Shot Action Recognition on Olympics
no code implementations • CVPR 2017 • Jie Qin, Li Liu, Ling Shao, Bingbing Ni, Chen Chen, Fumin Shen, Yunhong Wang
Extensive experiments on four realistic action datasets in terms of three tasks (i. e., partial action retrieval, recognition and prediction) clearly show the superiority of PRBC over the state-of-the-art methods, along with significantly reduced memory load and computational costs during the online test.
no code implementations • CVPR 2017 • Jiaxin Chen, Yunhong Wang, Jie Qin, Li Liu, Ling Shao
Numerous methods have been proposed for person re-identification, most of which however neglect the matching efficiency.
no code implementations • CVPR 2017 • Li Liu, Ling Shao, Fumin Shen, Mengyang Yu
Learning to hash has been recognized to accomplish highly efficient storage and retrieval for large-scale visual data.
no code implementations • CVPR 2017 • Yang Long, Li Liu, Ling Shao, Fumin Shen, Guiguang Ding, Jungong Han
Using the proposed Unseen Visual Data Synthesis (UVDS) algorithm, semantic attributes are effectively utilised as an intermediate clue to synthesise unseen visual features at the training stage.
1 code implementation • CVPR 2017 • Li Liu, Fumin Shen, Yuming Shen, Xianglong Liu, Ling Shao
Free-hand sketch-based image retrieval (SBIR) is a specific cross-view retrieval task, in which queries are abstract and ambiguous sketches while the retrieval database is formed with natural images.
no code implementations • 4 Jan 2017 • Li Liu, Yongzhong Yang, Lakshmi Narasimhan Govindarajan, Shu Wang, Bin Hu, Li Cheng, David S. Rosenblum
We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations.
no code implementations • 15 Jul 2016 • Yi Zhou, Li Liu, Ling Shao, Matt Mellor
Vehicle detection and annotation for streaming video data with complex scenes is an interesting but challenging task for urban traffic surveillance.