no code implementations • ECCV 2020 • Ke Han, Yan Huang, Zerui Chen, Liang Wang, Tieniu Tan
In this paper, we propose a novel Prediction, Recovery and Identification (PRI) model for LR re-id, which adaptively recovers missing details by predicting a preferable scale factor based on the image content.
no code implementations • ECCV 2020 • Zerui Chen, Yan Huang, Hongyuan Yu, Bin Xue, Ke Han, Yiru Guo, Liang Wang
With roughly the same computational complexity as previous models, our approach achieves state-of-the-art results on both the single-person and multi-person 3D pose estimation benchmarks.
no code implementations • COLING 2022 • Liang Wang, Peifeng Li, Sheng Xu
Most previous work on temporal relation extraction only focused on extracting the temporal relations among events or suffered from the issue of different expressions of events, timexes and Document Creation Time (DCT).
Ranked #1 on Temporal Relation Classification on TB-Dense
no code implementations • 7 Jun 2024 • Huanhuan Ma, Jinghao Zhang, Qiang Liu, Shu Wu, Liang Wang
By employing latent variables for phrase-level predictions, the final prediction of the image-caption pair can be aggregated using logical rules.
no code implementations • 3 Jun 2024 • Jiayao Tan, Fan Lyu, Chenggong Ni, Tingliang Feng, Fuyuan Hu, Zhang Zhang, Shaochuang Zhao, Liang Wang
Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data.
2 code implementations • 23 May 2024 • Ziqi Shi, Fan Lyu, Ye Liu, Fanhua Shang, Fuyuan Hu, Wei Feng, Zhang Zhang, Liang Wang
Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source data.
no code implementations • 15 May 2024 • Fan Lyu, Daofeng Liu, Linglan Zhao, Zhang Zhang, Fanhua Shang, Fuyuan Hu, Wei Feng, Liang Wang
Moreover, the continual doman drift in sequential learning tasks may entail the gradual displacement of the decision boundaries in the learned feature space, rendering the learned knowledge susceptible to forgetting.
1 code implementation • 6 May 2024 • Yunfeng Li, Bo wang, Ye Li, Zhiwen Yu, Liang Wang
The former does not fully exploit the potential of using only RGB and TIR information of the template or search region for channel and spatial feature fusion, and the latter lacks direct interaction between the template and search area, which limits the model's ability to fully exploit the original semantic information of both modalities.
Ranked #3 on Rgb-T Tracking on RGBT210
no code implementations • 6 May 2024 • Wenhao Zhu, Guojie Song, Liang Wang, Shaoguo Liu
Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power.
no code implementations • 24 Apr 2024 • Xiang Tao, Qiang Liu, Shu Wu, Liang Wang
The model learns semantic evolvement information of events by capturing local semantic changes and global semantic evolvement information through specific graph autoencoder and reconstruction strategies.
no code implementations • 19 Apr 2024 • Liang Wang, Luis Carvalho
Model evaluation is of crucial importance in modern statistics application.
1 code implementation • 18 Apr 2024 • Dawei Zhu, Liang Wang, Nan Yang, YiFan Song, Wenhao Wu, Furu Wei, Sujian Li
This paper explores context window extension of existing embedding models, pushing the limit to 32k without requiring additional training.
no code implementations • 30 Mar 2024 • Parag Pravin Dakle, Alolika Gon, Sihan Zha, Liang Wang, SaiKrishna Rallabandi, Preethi Raghavan
For the impact type classification task, our XLM-RoBERTa model fine-tuned using a custom fine-tuning strategy ranked first for the English language.
no code implementations • 26 Mar 2024 • Xiang Tao, Mingqing Zhang, Qiang Liu, Shu Wu, Liang Wang
This method models the propagation of news in the form of a propagation graph, and builds propagation graph test-time adaptation framework, enhancing the model's adaptability and robustness when facing OOD problems.
no code implementations • 25 Mar 2024 • Xiangxin Zhou, Dongyu Xue, Ruizhe Chen, Zaixiang Zheng, Liang Wang, Quanquan Gu
Antibody design, a crucial task with significant implications across various disciplines such as therapeutics and biology, presents considerable challenges due to its intricate nature.
1 code implementation • 22 Mar 2024 • Yifan Zhang, Weiqi Chen, Zhaoyang Zhu, Dalin Qin, Liang Sun, Xue Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
For the state-of-the-art (SOTA) model, the MSE is reduced by $33. 3\%$.
no code implementations • 12 Mar 2024 • Han Huang, Haitian Zhong, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan
We conducted experiments of different editing methods on five LVLMs, and thoroughly analyze how these methods impact the models.
no code implementations • 8 Mar 2024 • Zewen Chen, Haina Qin, Juan Wang, Chunfeng Yuan, Bing Li, Weiming Hu, Liang Wang
On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements.
1 code implementation • 8 Mar 2024 • Yi-Fan Zhang, Weichen Yu, Qingsong Wen, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs.
no code implementations • 7 Mar 2024 • Xiangxin Zhou, Xiwei Cheng, Yuwei Yang, Yu Bao, Liang Wang, Quanquan Gu
DecompOpt presents a new generation paradigm which combines optimization with conditional diffusion models to achieve desired properties while adhering to the molecular grammar.
no code implementations • 7 Mar 2024 • Yi Xiao, Xiangxin Zhou, Qiang Liu, Liang Wang
In this paper, we present the first systematic survey on multimodal frameworks for molecules research.
no code implementations • 7 Mar 2024 • Xiangxin Zhou, Liang Wang, Yichi Zhou
Nevertheless, when applying policy gradients to SDEs, since the policy gradient is estimated on a finite set of trajectories, it can be ill-defined, and the policy behavior in data-scarce regions may be uncontrolled.
no code implementations • 29 Feb 2024 • Jiajun Zhang, ZHIXUN LI, Qiang Liu, Shu Wu, Liang Wang
With the rapid development of social media, the wide dissemination of fake news on social media is increasingly threatening both individuals and society.
1 code implementation • 27 Feb 2024 • Parker Glenn, Parag Pravin Dakle, Liang Wang, Preethi Raghavan
Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final result.
1 code implementation • 26 Feb 2024 • Jiaqi Guan, Xiangxin Zhou, Yuwei Yang, Yu Bao, Jian Peng, Jianzhu Ma, Qiang Liu, Liang Wang, Quanquan Gu
Designing 3D ligands within a target binding site is a fundamental task in drug discovery.
no code implementations • 22 Feb 2024 • Yuwei Xia, Ding Wang, Qiang Liu, Liang Wang, Shu Wu, XiaoYu Zhang
Temporal Knowledge Graph (TKG) forecasting aims to predict future facts based on given histories.
1 code implementation • 20 Feb 2024 • Haisong Gong, Qiang Liu, Shu Wu, Liang Wang
In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods.
Ranked #6 on Text-based de novo Molecule Generation on ChEBI-20
Language Modelling Text-based de novo Molecule Generation +1
1 code implementation • 20 Feb 2024 • Haisong Gong, Weizhi Xu, Shu Wu, Qiang Liu, Liang Wang
To address this, we propose a novel word-level Heterogeneous-graph-based model for Fact Checking over unstructured and structured information, namely HeterFC.
1 code implementation • 18 Feb 2024 • Junfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang, Shu Wu, Liang Wang, Tieniu Tan
In this work, we adopt the intuition that the LVLM tends to respond logically consistently for existent objects but inconsistently for hallucinated objects.
no code implementations • 18 Feb 2024 • Jinghao Zhang, YuTing Liu, Qiang Liu, Shu Wu, Guibing Guo, Liang Wang
Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS).
no code implementations • 16 Feb 2024 • Chin-Chia Michael Yeh, Yujie Fan, Xin Dai, Vivian Lai, Prince Osei Aboagye, Junpeng Wang, Huiyuan Chen, Yan Zheng, Zhongfang Zhuang, Liang Wang, Wei zhang
All-Multi-Layer Perceptron (all-MLP) mixer models have been shown to be effective for time series forecasting problems.
2 code implementations • 15 Feb 2024 • Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, Douwe Kiela
Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss.
no code implementations • 13 Feb 2024 • Fan Lyu, Kaile Du, Yuyang Li, Hanyu Zhao, Zhang Zhang, Guangcan Liu, Liang Wang
At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model.
1 code implementation • 11 Feb 2024 • Xiang Tao, Qiang Liu, Shu Wu, Liang Wang
Based on our theoretical analysis, we further identify the limitations of the GraphMAE from the perspectives of alignment and uniformity, which have been considered as two key properties of high-quality representations in GCL.
1 code implementation • 8 Feb 2024 • Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei
This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023.
no code implementations • 6 Feb 2024 • Qiang Liu, Xiang Tao, Junfei Wu, Shu Wu, Liang Wang
In this work, we investigate to use Large Language Models (LLMs) for rumor detection on social media.
no code implementations • 28 Jan 2024 • Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Dehua Zheng, Weixuan Wang, Wenjin Yang, Siqin Li, Xianliang Wang, Wenhui Chen, Jing Dai, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu
We expect that agents should learn to enhance the extent to which humans achieve these goals while maintaining agents' original abilities (e. g., winning games).
no code implementations • 25 Jan 2024 • Zeyu Xi, Ge Shi, Xuefen Li, Junchi Yan, Zun Li, Lifang Wu, Zilin Liu, Liang Wang
We develop a knowledge guided entity-aware video captioning network (KEANet) based on a candidate player list in encoder-decoder form for basketball live text broadcast.
no code implementations • 16 Jan 2024 • Audrey Der, Chin-Chia Michael Yeh, Yan Zheng, Junpeng Wang, Zhongfang Zhuang, Liang Wang, Wei zhang, Eamonn J. Keogh
In this work we introduce a domain agnostic counterfactual explanation technique to produce explanations for time series anomalies.
no code implementations • 2 Jan 2024 • Fan Lyu, Wei Feng, Yuepan Li, Qing Sun, Fanhua Shang, Liang Wan, Liang Wang
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.
no code implementations • 2 Jan 2024 • Prince Aboagye, Yan Zheng, Junpeng Wang, Uday Singh Saini, Xin Dai, Michael Yeh, Yujie Fan, Zhongfang Zhuang, Shubham Jain, Liang Wang, Wei zhang
The emergence of pre-trained models has significantly impacted Natural Language Processing (NLP) and Computer Vision to relational datasets.
1 code implementation • 31 Dec 2023 • Liang Wang, Dawei Dai, Shiyu Fu, Guoyin Wang
In specific scenarios, face sketch can be used to identify a person.
2 code implementations • 31 Dec 2023 • Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei
In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
1 code implementation • 20 Dec 2023 • Yi-Fan Zhang, Zhang Zhang, Liang Wang, Tieniu Tan, Rong Jin
In an effort to address these issues, we delve into the realm of zero-shot machine-generated text detection.
no code implementations • 14 Dec 2023 • Zhuoyifan Zhang, Lu Zhang, Liang Wang, Haoming Wu
The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions.
no code implementations • 28 Nov 2023 • Yifan Zhang, Xue Wang, Tian Zhou, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
We demonstrate the effectiveness of \abbr through comprehensive experiments on multiple OOD detection benchmarks, extensive empirical studies show that \abbr significantly improves the performance of OOD detection over state-of-the-art methods.
no code implementations • 7 Nov 2023 • Yao Zhang, Zhiwen Yu, Jun Zhang, Liang Wang, Tom H. Luan, Bin Guo, Chau Yuen
Nevertheless, existing MARL algorithms ignore effective information aggregation which is fundamental for improving the learning capacity of decentralized agents.
no code implementations • 5 Nov 2023 • Chin-Chia Michael Yeh, Yan Zheng, Menghai Pan, Huiyuan Chen, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang, Jeff M. Phillips, Eamonn Keogh
In this work, we propose a sketch for discord mining among multi-dimensional time series.
no code implementations • 5 Nov 2023 • Chin-Chia Michael Yeh, Huiyuan Chen, Xin Dai, Yan Zheng, Yujie Fan, Vivian Lai, Junpeng Wang, Audrey Der, Zhongfang Zhuang, Liang Wang, Wei zhang
To facilitate this investigation, we introduce a CTSR benchmark dataset that comprises time series data from a variety of domains, such as motion, power demand, and traffic.
no code implementations • 5 Nov 2023 • Audrey Der, Chin-Chia Michael Yeh, Yan Zheng, Junpeng Wang, Huiyuan Chen, Zhongfang Zhuang, Liang Wang, Wei zhang, Eamonn Keogh
As a result, unmodified data mining tools can obtain near-identical performance on the synthesized time series as on the original time series.
no code implementations • 5 Nov 2023 • Chin-Chia Michael Yeh, Huiyuan Chen, Yujie Fan, Xin Dai, Yan Zheng, Vivian Lai, Junpeng Wang, Zhongfang Zhuang, Liang Wang, Wei zhang, Eamonn Keogh
The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph.
no code implementations • 2 Nov 2023 • Yiran Li, Junpeng Wang, Prince Aboagye, Michael Yeh, Yan Zheng, Liang Wang, Wei zhang, Kwan-Liu Ma
On the one hand, by visually examining the captions automatically generated from language-image models for an image dataset, we gain deeper insights into the semantic underpinnings of the visual contents, unearthing data biases that may be entrenched within the dataset.
1 code implementation • NeurIPS 2023 • Zhanke Zhou, Jiangchao Yao, Jiaxu Liu, Xiawei Guo, Quanming Yao, Li He, Liang Wang, Bo Zheng, Bo Han
To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse.
no code implementations • 23 Oct 2023 • Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei
Modern search engines are built on a stack of different components, including query understanding, retrieval, multi-stage ranking, and question answering, among others.
1 code implementation • 20 Oct 2023 • Dongyu Zhang, Liang Wang, Xin Dai, Shubham Jain, Junpeng Wang, Yujie Fan, Chin-Chia Michael Yeh, Yan Zheng, Zhongfang Zhuang, Wei zhang
FATA-Trans is field- and time-aware for sequential tabular data.
1 code implementation • 15 Oct 2023 • Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Qiang Liu, Shu Wu, Liang Wang
Each instance is accompanied by a veracity label and an explanation that outlines the reasoning path supporting the veracity classification.
1 code implementation • 12 Oct 2023 • Xueguang Ma, Liang Wang, Nan Yang, Furu Wei, Jimmy Lin
Our findings demonstrate that the effectiveness of large language models indeed surpasses that of smaller models.
1 code implementation • 6 Oct 2023 • Han Huang, Yan Huang, Liang Wang
In this paper, we propose VI-Diff, a diffusion model that effectively addresses the task of Visible-Infrared person image translation.
no code implementations • 5 Oct 2023 • Chin-Chia Michael Yeh, Xin Dai, Huiyuan Chen, Yan Zheng, Yujie Fan, Audrey Der, Vivian Lai, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang
A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapted to various downstream tasks.
no code implementations • 5 Oct 2023 • Chin-Chia Michael Yeh, Huiyuan Chen, Xin Dai, Yan Zheng, Junpeng Wang, Vivian Lai, Yujie Fan, Audrey Der, Zhongfang Zhuang, Liang Wang, Wei zhang, Jeff M. Phillips
A Content-based Time Series Retrieval (CTSR) system is an information retrieval system for users to interact with time series emerged from multiple domains, such as finance, healthcare, and manufacturing.
no code implementations • 5 Oct 2023 • Chin-Chia Michael Yeh, Xin Dai, Yan Zheng, Junpeng Wang, Huiyuan Chen, Yujie Fan, Audrey Der, Zhongfang Zhuang, Liang Wang, Wei zhang
In this paper, we investigate the application of MTL to the time series classification (TSC) problem.
1 code implementation • NeurIPS 2023 • Yi-Fan Zhang, Qingsong Wen, Xue Wang, Weiqi Chen, Liang Sun, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data.
1 code implementation • 19 Sep 2023 • Dawei Zhu, Nan Yang, Liang Wang, YiFan Song, Wenhao Wu, Furu Wei, Sujian Li
To decouple train length from target length for efficient context window extension, we propose Positional Skip-wisE (PoSE) training that smartly simulates long inputs using a fixed context window.
1 code implementation • 18 Sep 2023 • Ming-Zhe Li, Zhen Jia, Zhang Zhang, Zhanyu Ma, Liang Wang
In order to solve this dilemma, we propose a multi-semantic fusion (MSF) model for improving the performance of GZSSAR, where two kinds of class-level textual descriptions (i. e., action descriptions and motion descriptions), are collected as auxiliary semantic information to enhance the learning efficacy of generalizable skeleton features.
Action Recognition Generalized Zero Shot skeletal action recognition +1
no code implementations • 14 Sep 2023 • Xiangzhu Meng, Wei Wei, Qiang Liu, Shu Wu, Liang Wang
Motivated by the related medical findings on functional connectivites, TiBGL proposes template-induced brain graph learning to extract template brain graphs for all groups.
no code implementations • 14 Sep 2023 • Xiangzhu Meng, Qiang Liu, Shu Wu, Liang Wang
In recent years, functional magnetic resonance imaging (fMRI) has been widely utilized to diagnose neurological disease, by exploiting the region of interest (RoI) nodes as well as their connectivities in human brain.
1 code implementation • 31 Aug 2023 • Andong Lu, Zhang Zhang, Yan Huang, Yifan Zhang, Chenglong Li, Jin Tang, Liang Wang
The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features.
1 code implementation • 31 Aug 2023 • Milad Ramezani, Liang Wang, Joshua Knights, Zhibin Li, Pauline Pounds, Peyman Moghadam
This paper proposes a pose-graph attentional graph neural network, called P-GAT, which compares (key)nodes between sequential and non-sequential sub-graphs for place recognition tasks as opposed to a common frame-to-frame retrieval problem formulation currently implemented in SOTA place recognition methods.
no code implementations • 22 Aug 2023 • Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Tianzhu Zhang, Liang Wang
Gait recognition is to seek correct matches for query individuals by their unique walking patterns.
no code implementations • 21 Aug 2023 • Lei Han, Chunyu Tu, Zhiwen Yu, Zhiyong Yu, Weihua Shan, Liang Wang, Bin Guo
In this paper, we explicitly address the route planning for a group of agents, including UAVs, workers, and cars, with the goal of maximizing the task completion rate.
no code implementations • 17 Aug 2023 • Liang Wang, Nan Zhang, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Guokuan Li, Kaiyu Hu, Guilin Jiang, Jing Xiao
In this paper, we introduce EdgeMA, a practical and efficient video analytics system designed to adapt models to shifts in real-world video streams over time, addressing the data drift problem.
2 code implementations • 17 Aug 2023 • Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
To address this issue, instead of considering these two problems independently, we adopt an alternating optimization algorithm, which can estimate the degradation and restore the SR image in a single model.
no code implementations • 3 Aug 2023 • Liang Wang, Xiaogang Wang
In engineering applications, line, circle, arc, and point are collectively referred to as primitives, and they play a crucial role in path planning, simulation analysis, and manufacturing.
no code implementations • 2 Aug 2023 • Yan Zheng, Junpeng Wang, Chin-Chia Michael Yeh, Yujie Fan, Huiyuan Chen, Liang Wang, Wei zhang
The tool helps users discover nuance features of data entities, perform feature denoising/injecting in embedding training, and generate embeddings for unseen entities.
2 code implementations • 14 Jul 2023 • Liang Wang, Nan Yang, Furu Wei
Our framework initially trains a reward model based on LLM feedback to evaluate the quality of candidate examples, followed by knowledge distillation to train a bi-encoder based dense retriever.
2 code implementations • 27 Jun 2023 • Yongqi Li, Nan Yang, Liang Wang, Furu Wei, Wenjie Li
However, only learning to generate is insufficient for generative retrieval.
no code implementations • 27 Jun 2023 • Liang Wang, Kai Lu, Nan Zhang, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Guokuan Li, Jing Xiao
This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes.
no code implementations • 25 Jun 2023 • Jinghao Zhang, Qiang Liu, Shu Wu, Liang Wang
Even worse, the strong statistical correlation might mislead models to learn the spurious preference towards inconsequential modalities.
1 code implementation • 15 Jun 2023 • Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang
Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words.
no code implementations • 12 Jun 2023 • Haozhe Wang, Chao Du, Panyan Fang, Li He, Liang Wang, Bo Zheng
In this regard, we explore the problem of constrained bidding in adversarial bidding environments, which assumes no knowledge about the adversarial factors.
1 code implementation • 6 Jun 2023 • Jianing Zhu, Xiawei Guo, Jiangchao Yao, Chao Du, Li He, Shuo Yuan, Tongliang Liu, Liang Wang, Bo Han
In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information.
no code implementations • 2 Jun 2023 • Xin Dai, Yujie Fan, Zhongfang Zhuang, Shubham Jain, Chin-Chia Michael Yeh, Junpeng Wang, Liang Wang, Yan Zheng, Prince Osei Aboagye, Wei zhang
Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories.
1 code implementation • 26 May 2023 • Yongqi Li, Nan Yang, Liang Wang, Furu Wei, Wenjie Li
Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target.
no code implementations • 23 May 2023 • Wenhao Zhu, Tianyu Wen, Guojie Song, Liang Wang, Bo Zheng
Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed.
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.
no code implementations • 4 May 2023 • Wenhao Zhu, Tianyu Wen, Guojie Song, Xiaojun Ma, Liang Wang
Graph Transformer is gaining increasing attention in the field of machine learning and has demonstrated state-of-the-art performance on benchmarks for graph representation learning.
1 code implementation • 25 Apr 2023 • Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is 50% higher than advanced TTA methods.
no code implementations • 25 Apr 2023 • Qiang Liu, Junfei Wu, Shu Wu, Liang Wang
Then, DAL reversely optimizes news-aspect and evidence-aspect debiasing discriminators to mitigate the impact of news and evidence content biases.
no code implementations • 23 Apr 2023 • Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Weixuan Wang, Siqin Li, Xianliang Wang, Xianhan Zeng, Rundong Wang, Jiawei Wang, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu
MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.
1 code implementation • CVPR 2023 • Jingqiu Zhou, Linjiang Huang, Liang Wang, Si Liu, Hongsheng Li
Besides, the generated pseudo-labels can be fluctuating and inaccurate at the early stage of training.
Pseudo Label Weakly-supervised Temporal Action Localization +1
no code implementations • 12 Apr 2023 • Qiang Liu, Zhaocheng Liu, Zhenxi Zhu, Shu Wu, Liang Wang
However, none of existing multi-interest recommendation models consider the Out-Of-Distribution (OOD) generalization problem, in which interest distribution may change.
2 code implementations • 10 Apr 2023 • Nan Yang, Tao Ge, Liang Wang, Binxing Jiao, Daxin Jiang, Linjun Yang, Rangan Majumder, Furu Wei
We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references.
1 code implementation • 6 Apr 2023 • Dong An, Hanqing Wang, Wenguan Wang, Zun Wang, Yan Huang, Keji He, Liang Wang
To develop a robust VLN-CE agent, we propose a new navigation framework, ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments.
1 code implementation • CVPR 2023 • Wentao Chen, Chenyang Si, Zhang Zhang, Liang Wang, Zilei Wang, Tieniu Tan
Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively.
no code implementations • 24 Mar 2023 • Yiran Li, Junpeng Wang, Xin Dai, Liang Wang, Chin-Chia Michael Yeh, Yan Zheng, Wei zhang, Kwan-Liu Ma
Multi-head self-attentions are then applied to the sequence to learn the attention between patches.
1 code implementation • CVPR 2023 • Zhengxiong Luo, Dayou Chen, Yingya Zhang, Yan Huang, Liang Wang, Yujun Shen, Deli Zhao, Jingren Zhou, Tieniu Tan
A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data distribution.
Ranked #7 on Video Generation on UCF-101
no code implementations • 14 Mar 2023 • Liang Wang, Nan Yang, Furu Wei
This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems.
no code implementations • 10 Mar 2023 • Xuanhua Yang, Jianxin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng
Multi-task learning (MTL) has been widely applied in online advertising and recommender systems.
1 code implementation • Asian Conference on Computer Vision 2023 • Ke Han, Shaogang Gong, Yan Huang, Liang Wang, Tieniu Tan
However, existing Re-ID methods usually generate 3D body shapes without considering identity modeling, which severely weakens the discriminability of 3D human shapes.
no code implementations • 28 Feb 2023 • Xianglong Lang, Zhuming Wang, Zun Li, Meng Tian, Ge Shi, Lifang Wu, Liang Wang
Specifically, the framework consists of a Visual Representation Module to extract individual appearance features, a Knowledge Augmented Semantic Relation Module explore semantic representations of individual actions, and a Knowledge-Semantic-Visual Interaction Module aims to integrate visual and semantic information by the knowledge.
no code implementations • 24 Feb 2023 • Liang Wang, Zhuangkun Wei, Weisi Guo
This paper presents a Federated multi-agent Deep reinforcement learning-assisted Distributed Key generation scheme (FD2K), which fully exploits the common features of physical dynamics to establish secret key between legitimate users.
1 code implementation • 11 Feb 2023 • Dawei Dai, Yutang Li, Liang Wang, Shiyu Fu, Shuyin Xia, Guoyin Wang
In this study, we proposed a new task named sketch less face image retrieval (SLFIR), in which the retrieval was carried out at each stroke and aim to retrieve the target face photo using a partial sketch with as few strokes as possible (see Fig. 1).
no code implementations • 6 Feb 2023 • Shanlei Mu, Penghui Wei, Wayne Xin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng
In this paper, we propose a Hybrid Contrastive Constrained approach (HC^2) for multi-scenario ad ranking.
no code implementations • 6 Feb 2023 • Penghui Wei, Yongqiang Chen, Shaoguo Liu, Liang Wang, Bo Zheng
In a whole delivery period, advertisers usually desire a certain impression count for the ads, and they also expect that the delivery performance is as good as possible (e. g., obtaining high click-through rate).
1 code implementation • The Eleventh International Conference on Learning Representations (ICLR 2023) 2023 • Yifan Zhang, Xue Wang, Jian Liang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data.
Ranked #6 on Domain Adaptation on Office-Home
no code implementations • 26 Jan 2023 • Ya Wang, Liang Wang, Huawei Fan, Jun Ma, Hui Cao, Xingang Wang
It is revealed that the contents of the cluster are determined by the network symmetry and the breathing activities are due to the interplay between the neural network and the astrocyte.
no code implementations • 12 Jan 2023 • Xiaogang Wang, Yuhang Cheng, Liang Wang, Jiangbo Lu, Kai Xu, GuoQiang Xiao
Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions.
no code implementations • CVPR 2023 • Ke Han, Shaogang Gong, Yan Huang, Liang Wang, Tieniu Tan
Specifically, to formulate meaningful clothing variations in the feature space, our method first estimates a clothing-change normal distribution with intra-ID cross-clothing variances.
no code implementations • 17 Dec 2022 • Zhen Jia, Zhang Zhang, Liang Wang, Tieniu Tan
Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value.
no code implementations • 9 Dec 2022 • Audrey Der, Chin-Chia Michael Yeh, Renjie Wu, Junpeng Wang, Yan Zheng, Zhongfang Zhuang, Liang Wang, Wei zhang, Eamonn Keogh
PRCIS is a distance measure for long time series, which exploits recent progress in our ability to summarize time series with dictionaries.
1 code implementation • ICCV 2023 • Dong An, Yuankai Qi, Yangguang Li, Yan Huang, Liang Wang, Tieniu Tan, Jing Shao
Concretely, we build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map.
Ranked #2 on Visual Navigation on R2R
1 code implementation • 7 Dec 2022 • Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei
This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks.
Ranked #11 on Only Connect Walls Dataset Task 1 (Grouping) on OCW (using extra training data)
no code implementations • AMTA 2022 • Prince O Aboagye, Yan Zheng, Michael Yeh, Junpeng Wang, Zhongfang Zhuang, Huiyuan Chen, Liang Wang, Wei zhang, Jeff Phillips
Optimal Transport (OT) provides a useful geometric framework to estimate the permutation matrix under unsupervised cross-lingual word embedding (CLWE) models that pose the alignment task as a Wasserstein-Procrustes problem.
no code implementations • 1 Dec 2022 • Qiyue Yin, Tongtong Yu, Shengqi Shen, Jun Yang, Meijing Zhao, Kaiqi Huang, Bin Liang, Liang Wang
With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems.
1 code implementation • 22 Nov 2022 • Linjiang Huang, Kaixin Lu, Guanglu Song, Liang Wang, Si Liu, Yu Liu, Hongsheng Li
In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors.
no code implementations • 21 Nov 2022 • Zixuan Xu, Penghui Wei, Shaoguo Liu, Weimin Zhang, Liang Wang, Bo Zheng
Conventional graph neural network based methods usually deal with each domain separately, or train a shared model to serve all domains.
no code implementations • 2 Nov 2022 • Yilan Qin, Jiayu Ma, Mingle Jiang, Chuanfei Dong, Haiyang Fu, Liang Wang, Wenjie Cheng, YaQiu Jin
The multi-moment fluid model is trained with a small fraction of sparsely sampled data from kinetic simulations of Landau damping, using the physics-informed neural network (PINN) and the gradient-enhanced physics-informed neural network (gPINN).
no code implementations • 13 Oct 2022 • Weichen Yu, Hongyuan Yu, Yan Huang, Chunshui Cao, Liang Wang
Gait recognition aims to identify individuals by recognizing their walking patterns.
no code implementations • 13 Oct 2022 • Weichen Yu, Hongyuan Yu, Yan Huang, Liang Wang
The proposed method can be generalized to different gait recognition networks and achieves significant improvements.
1 code implementation • 12 Oct 2022 • Hongyuan Yu, Ting Li, Weichen Yu, Jianguo Li, Yan Huang, Liang Wang, Alex Liu
In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure.
1 code implementation • 11 Oct 2022 • Junfei Wu, Weizhi Xu, Qiang Liu, Shu Wu, Liang Wang
Comprehensive experiments have demonstrated the superiority of GETRAL over the state-of-the-arts and validated the efficacy of semantic mining with graph structure and contrastive learning.
no code implementations • 22 Sep 2022 • Kun Hu, Shaohui Mei, Wei Wang, Kaylena A. Ehgoetz Martens, Liang Wang, Simon J. G. Lewis, David D. Feng, Zhiyong Wang
The proposed scheme also sheds light on improving subject-level clinical studies from other scenarios as it can be integrated with many existing deep architectures.
1 code implementation • 18 Sep 2022 • Hua Wei, Jingxiao Chen, Xiyang Ji, Hongyang Qin, Minwen Deng, Siqin Li, Liang Wang, Weinan Zhang, Yong Yu, Lin Liu, Lanxiao Huang, Deheng Ye, Qiang Fu, Wei Yang
Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement learning.
no code implementations • 10 Sep 2022 • Wenjie Cheng, Haiyang Fu, Liang Wang, Chuanfei Dong, YaQiu Jin, Mingle Jiang, Jiayu Ma, Yilan Qin, Kexin Liu
The data-driven fluid modeling of PDEs for complex physical systems may be applied to improve fluid closure and reduce the computational cost of multi-scale modeling of global systems.
no code implementations • 9 Sep 2022 • Reza Arablouei, Liang Wang, Caitlin Phillips, Lachlan Currie, Jordan Yates, Greg Bishop-hurley
The evaluation results using two real-world animal behavior classification datasets show that the classification accuracy of the student GRU-MLP models improves appreciably through KD, approaching that of the teacher ResNet model.
no code implementations • 29 Aug 2022 • Zihan Lin, Xuanhua Yang, Xiaoyu Peng, Wayne Xin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng
For this purpose, we build a relatedness prediction network, so that it can predict the contrast strength for inter-task representations of an instance.
1 code implementation • 18 Aug 2022 • Yi-Fan Zhang, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, DaCheng Tao, Xing Xie
Our bound motivates two strategies to reduce the gap: the first one is ensembling multiple classifiers to enrich the hypothesis space, then we propose effective gap estimation methods for guiding the selection of a better hypothesis for the target.
no code implementations • 11 Aug 2022 • Chin-Chia Michael Yeh, Mengting Gu, Yan Zheng, Huiyuan Chen, Javid Ebrahimi, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang
Graph neural networks (GNNs) are deep learning models designed specifically for graph data, and they typically rely on node features as the input to the first layer.
1 code implementation • 8 Aug 2022 • Zehan Li, Nan Yang, Liang Wang, Furu Wei
In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions.
1 code implementation • 16 Jul 2022 • Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan
Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.
1 code implementation • 7 Jul 2022 • Gang Xu, Yu-chen Yang, Liang Wang, Xian-Tong Zhen, Jun Xu
Joint Super-Resolution and Inverse Tone-Mapping (joint SR-ITM) aims to increase the resolution and dynamic range of low-resolution and standard dynamic range images.
1 code implementation • 6 Jul 2022 • Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei
It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.
1 code implementation • 28 Jun 2022 • Chuanfu Shen, Shiqi Yu, Jilong Wang, George Q. Huang, Liang Wang
We provide a comprehensive survey on recent literature using deep learning and a discussion on the privacy and security of gait biometrics.
no code implementations • 27 Jun 2022 • Xuanhua Yang, Xiaoyu Peng, Penghui Wei, Shaoguo Liu, Liang Wang, Bo Zheng
Click-through rate (CTR) prediction is a fundamental technique in recommendation and advertising systems.
1 code implementation • 23 Jun 2022 • Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao
Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller.
2 code implementations • 14 Jun 2022 • ShangHua Gao, Zhong-Yu Li, Qi Han, Ming-Ming Cheng, Liang Wang
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further.
Ranked #2 on Instance Segmentation on COCO 2017 val (AP metric)
1 code implementation • 10 Jun 2022 • Haozhe Wang, Chao Du, Panyan Fang, Shuo Yuan, Xuming He, Liang Wang, Bo Zheng
Real-Time Bidding (RTB) is an important mechanism in modern online advertising systems.
no code implementations • 1 Jun 2022 • Qiang Liu, Yingtao Luo, Shu Wu, Zhen Zhang, Xiangnan Yue, Hong Jin, Liang Wang
Accordingly, we for the first time propose to model the biased credit scoring data with Multi-Task Learning (MTL).
no code implementations • 30 May 2022 • Penghui Wei, Shaoguo Liu, Xuanhua Yang, Liang Wang, Bo Zheng
Current bundle generation studies focus on generating a combination of items to improve user experience.
no code implementations • NAACL (ACL) 2022 • Penghui Wei, Xuanhua Yang, Shaoguo Liu, Liang Wang, Bo Zheng
This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR).
no code implementations • 15 May 2022 • Penghui Wei, Weimin Zhang, Ruijie Hou, Jinquan Liu, Shaoguo Liu, Liang Wang, Bo Zheng
Calibration techniques aim to post-process model predictions to posterior probabilities.
no code implementations • 29 Mar 2022 • Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang, Lechao Cheng, Junwei Han
Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis.
no code implementations • 28 Mar 2022 • Zhirong Xu, Shiyang Wen, Junshan Wang, Guojun Liu, Liang Wang, Zhi Yang, Lei Ding, Yan Zhang, Di Zhang, Jian Xu, Bo Zheng
Moreover, to deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework for the task of graph based advertisement retrieval.
no code implementations • 26 Mar 2022 • Richard Mortier, Hamed Haddadi, Sandra Servia, Liang Wang
A contrasting approach, distributed data analytics, where code and models for training and inference are distributed to the places where data is collected, has been boosted by two recent, ongoing developments: increased processing power and memory capacity available in user devices at the edge of the network, such as smartphones and home assistants; and increased sensitivity to the highly intrusive nature of many of these devices and services and the attendant demands for improved privacy.
1 code implementation • 20 Mar 2022 • Yuezihan Jiang, Yu Cheng, Hanyu Zhao, Wentao Zhang, Xupeng Miao, Yu He, Liang Wang, Zhi Yang, Bin Cui
We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs.
no code implementations • 19 Mar 2022 • Xiaojun Ma, Qin Chen, Yuanyi Ren, Guojie Song, Liang Wang
These experiments show the excellent expressive power of MWGNN in dealing with graph data with various distributions.
no code implementations • 11 Mar 2022 • Hanxing Chi, Baihong Lin, Jun Hu, Liang Wang
Recently, attention mechanisms have been extensively investigated in computer vision, but few of them show excellent performance on both large and mobile networks.
no code implementations • 10 Mar 2022 • Xuanwei Zhang, Libin Shen, Disheng Pan, Liang Wang, Yanjun Miao
We deploy a backward decoder which can act as an effective regularization method to the forward decoder.
1 code implementation • CVPR 2022 • Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones.
1 code implementation • CVPR 2022 • Linjiang Huang, Liang Wang, Hongsheng Li
Our method seeks to mine the representative snippets in each video for propagating information between video snippets to generate better pseudo labels.
Pseudo Label Weakly-supervised Temporal Action Localization +1
1 code implementation • ACL 2022 • Liang Wang, Wei Zhao, Zhuoyu Wei, Jingming Liu
Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links.
Ranked #2 on Link Prediction on WN18RR
no code implementations • 1 Mar 2022 • Ke Han, Chenyang Si, Yan Huang, Liang Wang, Tieniu Tan
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain.
no code implementations • 23 Jan 2022 • Ming-Ming Cheng, Peng-Tao Jiang, Ling-Hao Han, Liang Wang, Philip Torr
The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process.
no code implementations • 20 Jan 2022 • Zixuan Xu, Penghui Wei, Weimin Zhang, Shaoguo Liu, Liang Wang, Bo Zheng
Then a student model is trained on both clicked and unclicked ads with knowledge distillation, performing uncertainty modeling to alleviate the inherent noise in pseudo-labels.
no code implementations • 19 Jan 2022 • Junpeng Wang, Liang Wang, Yan Zheng, Chin-Chia Michael Yeh, Shubham Jain, Wei zhang
With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers.
1 code implementation • 18 Jan 2022 • Weizhi Xu, Junfei Wu, Qiang Liu, Shu Wu, Liang Wang
In this paper, we focus on the evidence-based fake news detection, where several evidences are utilized to probe the veracity of news (i. e., a claim).
no code implementations • CVPR 2022 • Chaowei Fang, Liang Wang, Dingwen Zhang, Jun Xu, Yixuan Yuan, Junwei Han
Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other.
no code implementations • 16 Dec 2021 • Wen Zhang, Shumin Deng, Mingyang Chen, Liang Wang, Qiang Chen, Feiyu Xiong, Xiangwen Liu, Huajun Chen
We first identity three important desiderata for e-commerce KG systems: 1) attentive reasoning, reasoning over a few target relations of more concerns instead of all; 2) explanation, providing explanations for a prediction to help both users and business operators understand why the prediction is made; 3) transferable rules, generating reusable rules to accelerate the deployment of a KG to new systems.
1 code implementation • NeurIPS 2021 • Keji He, Yan Huang, Qi Wu, Jianhua Yang, Dong An, Shuanglin Sima, Liang Wang
In Vision-and-Language Navigation (VLN) task, an agent is asked to navigate inside 3D indoor environments following given instructions.
no code implementations • 24 Nov 2021 • Liang Wang, Reza Arablouei, Flavio A. P. Alvarenga, Greg J. Bishop-Hurley
We study the classification of animal behavior using accelerometry data through various recurrent neural network (RNN) models.
no code implementations • 24 Nov 2021 • Reza Arablouei, Liang Wang, Lachlan Currie, Jordan Yates, Flavio A. P. Alvarenga, Greg J. Bishop-Hurley
We develop an end-to-end deep-neural-network-based algorithm for classifying animal behavior using accelerometry data on the embedded system of an artificial intelligence of things (AIoT) device installed in a wearable collar tag.
no code implementations • 22 Nov 2021 • Peng Wang, Jun Wen, Chenyang Si, Yuntao Qian, Liang Wang
Finally, in the Information Fuser, we explore varied strategies to combine the Sequence Reconstructor and Contrastive Motion Learner, and propose to capture postures and motions simultaneously via a knowledge-distillation based fusion strategy that transfers the motion learning from the Contrastive Motion Learner to the Sequence Reconstructor.
no code implementations • 15 Nov 2021 • Yuyang Sun, Zhiyong Zhang, Changzhen Qiu, Liang Wang, Zekai Wang
With the rapid development of generation model, AI-based face manipulation technology, which called DeepFakes, has become more and more realistic.
no code implementations • 15 Nov 2021 • Qiyue Yin, Jun Yang, Kaiqi Huang, Meijing Zhao, Wancheng Ni, Bin Liang, Yan Huang, Shu Wu, Liang Wang
Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs.
1 code implementation • 1 Nov 2021 • Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Mengqi Zhang, Shu Wu, Liang Wang
Although having access to multiple modalities might allow us to capture rich information, we argue that the simple coarse-grained fusion by linear combination or concatenation in previous work is insufficient to fully understand content information and item relationships. To this end, we propose a latent structure MIning with ContRastive mOdality fusion method (MICRO for brevity).
no code implementations • NeurIPS 2021 • Yiming Gao, Bei Shi, Xueying Du, Liang Wang, Guangwei Chen, Zhenjie Lian, Fuhao Qiu, Guoan Han, Weixuan Wang, Deheng Ye, Qiang Fu, Wei Yang, Lanxiao Huang
Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.
1 code implementation • 14 Oct 2021 • Qilong Yan, Yufeng Zhang, Qiang Liu, Shu Wu, Liang Wang
User profiling has long been an important problem that investigates user interests in many real applications.
no code implementations • 12 Oct 2021 • Liang Wang, Luis Carvalho
We investigate a general matrix factorization for deviance-based data losses, extending the ubiquitous singular value decomposition beyond squared error loss.
no code implementations • 29 Sep 2021 • Chin-Chia Michael Yeh, Mengting Gu, Yan Zheng, Huiyuan Chen, Javid Ebrahimi, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang
When applying such type of networks on graph without node feature, one can extract simple graph-based node features (e. g., number of degrees) or learn the input node representation (i. e., embeddings) when training the network.
no code implementations • 29 Sep 2021 • Yifan Zhang, Feng Li, Zhang Zhang, Liang Wang, DaCheng Tao, Tieniu Tan
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
no code implementations • 23 Sep 2021 • Muhammad Khalid, Liang Wang, Kezhi Wang, Cunhua Pan, Nauman Aslam, Yue Cao
In this paper, to reduce the congestion rate at the city center and increase the quality of experience (QoE) of each user, the framework of long-range autonomous valet parking (LAVP) is presented, where an Autonomous Vehicle (AV) is deployed in the city, which can pick up, drop off users at their required spots, and then drive to the car park out of city center autonomously.
no code implementations • 21 Sep 2021 • Chin-Chia Michael Yeh, Zhongfang Zhuang, Junpeng Wang, Yan Zheng, Javid Ebrahimi, Ryan Mercer, Liang Wang, Wei zhang
In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database.
no code implementations • EMNLP 2021 • Liang Wang, Wei Zhao, Jingming Liu
In this paper, we propose to align sentence representations from different languages into a unified embedding space, where semantic similarities (both cross-lingual and monolingual) can be computed with a simple dot product.
no code implementations • 16 Aug 2021 • Mengqi Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Liang Wang
In our work, different views can be obtained based on the various relations among nodes.
1 code implementation • ICCV 2021 • Linjiang Huang, Liang Wang, Hongsheng Li
In this paper, we present a framework named FAC-Net based on the I3D backbone, on which three branches are appended, named class-wise foreground classification branch, class-agnostic attention branch and multiple instance learning branch.
no code implementations • 10 Aug 2021 • Liping Wang, Fenyu Hu, Shu Wu, Liang Wang
These methods embed users and items in Euclidean space, and perform graph convolution on user-item interaction graphs.
no code implementations • 10 Aug 2021 • Liping Wang, Fenyu Hu, Shu Wu, Liang Wang
Graph Neural Networks (GNNs) have achieved great success among various domains.
1 code implementation • 31 Jul 2021 • Wentao Zhang, Zhi Yang, Yexin Wang, Yu Shen, Yang Li, Liang Wang, Bin Cui
Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets.
1 code implementation • 25 Jul 2021 • Wentao Zhang, Yuezihan Jiang, Yang Li, Zeang Sheng, Yu Shen, Xupeng Miao, Liang Wang, Zhi Yang, Bin Cui
Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs.
no code implementations • 23 Jul 2021 • Liang Wang, Huawei Fan, Jinghua Xiao, Yueheng Lan, Xingang Wang
Additionally, it is found that despite the synchronization degree of the original network, once properly trained, the reservoir network is always developed to the same critical state, exemplifying the "attractor" nature of this state in machine learning.
no code implementations • 22 Jul 2021 • Zhengxiong Luo, Zhicheng Wang, Yan Huang, Liang Wang, Tieniu Tan, Erjin Zhou
It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.
1 code implementation • 15 Jul 2021 • Dong An, Yuankai Qi, Yan Huang, Qi Wu, Liang Wang, Tieniu Tan
Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views.
Ranked #82 on Vision and Language Navigation on VLN Challenge
4 code implementations • 29 Jun 2021 • Yi-Fan Song, Zhang Zhang, Caifeng Shan, Liang Wang
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints.
Ranked #17 on Skeleton Based Action Recognition on NTU RGB+D 120
1 code implementation • 18 Jun 2021 • Yixin Liu, Shirui Pan, Yu Guang Wang, Fei Xiong, Liang Wang, Qingfeng Chen, Vincent CS Lee
Detecting anomalies for dynamic graphs has drawn increasing attention due to their wide applications in social networks, e-commerce, and cybersecurity.
1 code implementation • 16 Jun 2021 • Jianhua Yang, Yan Huang, Zhanyu Ma, Liang Wang
To solve this problem, we propose a simple yet effective Cascaded Multi-modal Fusion (CMF) module, which stacks multiple atrous convolutional layers in parallel and further introduces a cascaded branch to fuse visual and linguistic features.
1 code implementation • 13 Jun 2021 • Mengmeng Cui, Wei Wang, Jinjin Zhang, Liang Wang
However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder).
Ranked #15 on Scene Text Recognition on ICDAR2015
no code implementations • 25 May 2021 • Wentao Chen, Chenyang Si, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class.
1 code implementation • 25 May 2021 • Shu Wu, Zekun Li, Yunyue Su, Zeyu Cui, XiaoYu Zhang, Liang Wang
To solve the problems, we propose a novel approach, Graph Factorization Machine (GraphFM), by naturally representing features in the graph structure.
1 code implementation • NeurIPS 2021 • Prince Osei Aboagye, Jeff Phillips, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei zhang, Liang Wang, Hao Yang
Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP.
1 code implementation • 14 May 2021 • Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of the ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
Ranked #2 on Blind Super-Resolution on DIV2KRK - 4x upscaling
no code implementations • 12 May 2021 • Jiayi Lin, Yan Huang, Liang Wang
Recently, deformable alignment has drawn extensive attention in VSR community for its remarkable performance, which can adaptively align neighboring frames with the reference one.
no code implementations • 24 Apr 2021 • Han Zhang, Huawei Fan, Liang Wang, Xingang Wang
Reconstructing the KAM dynamics diagram of Hamiltonian system from the time series of a limited number of parameters is an outstanding question in nonlinear science, especially when the Hamiltonian governing the system dynamics are unknown.
1 code implementation • CVPR 2021 • Gang Xu, Jun Xu, Zhen Li, Liang Wang, Xing Sun, Ming-Ming Cheng
To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos.
1 code implementation • 19 Apr 2021 • Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Shuhui Wang, Liang Wang
To be specific, in the proposed LATTICE model, we devise a novel modality-aware structure learning layer, which learns item-item structures for each modality and aggregates multiple modalities to obtain latent item graphs.
1 code implementation • 15 Apr 2021 • Mengqi Zhang, Shu Wu, Xueli Yu, Qiang Liu, Liang Wang
We propose a new method named Dynamic Graph Neural Network for Sequential Recommendation (DGSR), which connects different user sequences through a dynamic graph structure, exploring the interactive behavior of users and items with time and order information.
no code implementations • 7 Apr 2021 • Zeyu Cui, Zekun Li, Shu Wu, XiaoYu Zhang, Qiang Liu, Liang Wang, Mengmeng Ai
We naturally generalizes the embedding propagation scheme of GCN to dynamic setting in an efficient manner, which is to propagate the change along the graph to update node embeddings.
1 code implementation • IEEE Transactions on Image Processing 2021 • Cairong Zhao, Xinbi Lv, Shuguang Dou, Shanshan Zhang, Jun Wu, Liang Wang
The adversarial suppression branch, embedded with two occlusion suppression module, minimizes the generated occlusion’s response and strengthens attentive feature representation on human non-occluded body regions.
Ranked #6 on Person Re-Identification on Occluded-DukeMTMC
no code implementations • CVPR 2021 • Ya Jing, Tao Kong, Wei Wang, Liang Wang, Lei LI, Tieniu Tan
Referring image segmentation aims to segment the objects referred by a natural language expression.
Generalized Referring Expression Segmentation Image Segmentation +2
no code implementations • 29 Mar 2021 • Yi-Fan Zhang, Zhang Zhang, Da Li, Zhen Jia, Liang Wang, Tieniu Tan
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community.
no code implementations • 29 Mar 2021 • Fenyu Hu, Liping Wang, Shu Wu, Liang Wang, Tieniu Tan
Graph classification is a challenging research problem in many applications across a broad range of domains.