no code implementations • 16 May 2024 • Tianyu Cui, Hongxia Li, Jingya Wang, Ye Shi
Federated Prompt Learning (FPL) incorporates large pre-trained Vision-Language models (VLM) into federated learning through prompt tuning.
1 code implementation • 7 Apr 2024 • Jiangnan Tang, Jingya Wang, Kaiyang Ji, Lan Xu, Jingyi Yu, Ye Shi
One of the biggest challenges to this task is the one-to-many mapping from sparse observations to dense full-body motions, which endowed inherent ambiguities.
no code implementations • 30 Mar 2024 • Juze Zhang, Jingyan Zhang, Zining Song, Zhanhe Shi, Chengfeng Zhao, Ye Shi, Jingyi Yu, Lan Xu, Jingya Wang
Humans naturally interact with both others and the surrounding multiple objects, engaging in various social activities.
no code implementations • 24 Mar 2024 • Jie Tian, Lingxiao Yang, Ran Ji, Yuexin Ma, Lan Xu, Jingyi Yu, Ye Shi, Jingya Wang
Here, the object motion diffusion model generates sequences of object motions based on gaze conditions, while the hand motion diffusion model produces hand motions based on the generated object motion.
no code implementations • 17 Mar 2024 • Qianyang Wu, Ye Shi, Xiaoshui Huang, Jingyi Yu, Lan Xu, Jingya Wang
This paper addresses new methodologies to deal with the challenging task of generating dynamic Human-Object Interactions from textual descriptions (Text2HOI).
1 code implementation • 29 Feb 2024 • Hongxia Li, Wei Huang, Jingya Wang, Ye Shi
Specifically, for each client, we learn a global prompt to extract consensus knowledge among clients, and a local prompt to capture client-specific category characteristics.
1 code implementation • 28 Feb 2024 • Bin Li, Ye Shi, Qian Yu, Jingya Wang
This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework.
no code implementations • 27 Feb 2024 • Yiming Ren, Xiao Han, Chengfeng Zhao, Jingya Wang, Lan Xu, Jingyi Yu, Yuexin Ma
For human-centric large-scale scenes, fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications.
1 code implementation • 5 Feb 2024 • Lingxiao Yang, Shutong Ding, Yifan Cai, Jingyi Yu, Jingya Wang, Ye Shi
We theoretically show the existence of manifold deviation by establishing a certain lower bound for the estimation error of the loss guidance.
no code implementations • 3 Feb 2024 • Youjia Wang, Yiwen Wu, Hengan Zhou, Hongyang Lin, Xingyue Peng, Yingwenqi Jiang, Yingsheng Zhu, Guanpeng Long, Yatu Zhang, Jingya Wang, Lan Xu, Jingyi Yu
In this paper, we propose IMUSIC to fill the gap, a novel path for facial expression capture using purely IMU signals, significantly distant from previous visual solutions. The key design in our IMUSIC is a trilogy.
1 code implementation • 30 Dec 2023 • Yilan Dong, Chunlin Yu, Ruiyang Ha, Ye Shi, Yuexin Ma, Lan Xu, Yanwei Fu, Jingya Wang
Existing gait recognition benchmarks mostly include minor clothing variations in the laboratory environments, but lack persistent changes in appearance over time and space.
1 code implementation • NeurIPS 2023 • Zhongyi Cai, Ye Shi, Wei Huang, Jingya Wang
Specifically, the online model learns general knowledge that is shared among all clients, while the offline model is trained locally to learn the specialized knowledge of each individual client.
1 code implementation • 13 Dec 2023 • Wenqian Zhang, Molin Huang, Yuxuan Zhou, Juze Zhang, Jingyi Yu, Jingya Wang, Lan Xu
We further provide a strong baseline method, BOTH2Hands, for the novel task: generating vivid two-hand motions from both implicit body dynamics and explicit text prompts.
1 code implementation • NeurIPS 2023 • Chunlin Yu, Ye Shi, Jingya Wang
Previous endeavors in self-supervised learning have enlightened the research of deep clustering from an instance discrimination perspective.
1 code implementation • NeurIPS 2023 • Wanxing Chang, Ye Shi, Jingya Wang
However, the current approaches rely heavily on the model's predictions and evaluate each sample independently without considering either the global and local structure of the sample distribution.
no code implementations • 10 Dec 2023 • Chengfeng Zhao, Juze Zhang, Jiashen Du, Ziwei Shan, Junye Wang, Jingyi Yu, Jingya Wang, Lan Xu
In this paper, we present I'm-HOI, a monocular scheme to faithfully capture the 3D motions of both the human and object in a novel setting: using a minimal amount of RGB camera and object-mounted Inertial Measurement Unit (IMU).
no code implementations • 8 Dec 2023 • Pei Lin, Sihang Xu, Hongdi Yang, Yiran Liu, Xin Chen, Jingya Wang, Jingyi Yu, Lan Xu
We further present a strong baseline method HandDiffuse for the controllable motion generation of interacting hands using various controllers.
1 code implementation • NeurIPS 2023 • Shutong Ding, Jingya Wang, Yali Du, Ye Shi
To the best of our knowledge, RPO is the first attempt that introduces GRG to RL as a way of efficiently handling both equality and inequality hard constraints.
1 code implementation • NeurIPS 2023 • Shutong Ding, Tianyu Cui, Jingya Wang, Ye Shi
Deep Equilibrium Models (DEQs) and Neural Ordinary Differential Equations (Neural ODEs) are two branches of implicit models that have achieved remarkable success owing to their superior performance and low memory consumption.
1 code implementation • 2 Feb 2023 • Juze Zhang, Ye Shi, Yuexin Ma, Lan Xu, Jingyi Yu, Jingya Wang
This paper presents an inverse kinematic optimization layer (IKOL) for 3D human pose and shape estimation that leverages the strength of both optimization- and regression-based methods within an end-to-end framework.
Ranked #30 on 3D Human Pose Estimation on 3DPW
no code implementations • 18 Jan 2023 • Jianfeng Weng, Kun Hu, Tingting Yao, Jingya Wang, Zhiyong Wang
Thus, in this work, a federated unsupervised cluster-contrastive (FedUCC) learning method is proposed for Person ReID.
no code implementations • CVPR 2023 • Juze Zhang, Haimin Luo, Hongdi Yang, Xinru Xu, Qianyang Wu, Ye Shi, Jingyi Yu, Lan Xu, Jingya Wang
We construct a dense multi-view dome to acquire a complex human object interaction dataset, named HODome, that consists of $\sim$75M frames on 10 subjects interacting with 23 objects.
no code implementations • 30 Nov 2022 • Peishan Cong, Yiteng Xu, Yiming Ren, Juze Zhang, Lan Xu, Jingya Wang, Jingyi Yu, Yuexin Ma
Motivated by this, we propose a monocular camera and single LiDAR-based method for 3D multi-person pose estimation in large-scale scenes, which is easy to deploy and insensitive to light.
1 code implementation • 29 Nov 2022 • Chunlin Yu, Ye Shi, Zimo Liu, Shenghua Gao, Jingya Wang
Lifelong person re-identification (LReID) is in significant demand for real-world development as a large amount of ReID data is captured from diverse locations over time and cannot be accessed at once inherently.
2 code implementations • ICCV 2023 • Yu-Tong Cao, Ye Shi, Baosheng Yu, Jingya Wang, DaCheng Tao
In this paper, we propose a federated active learning paradigm to efficiently learn a global model with limited annotation budget while protecting data privacy in a decentralized learning way.
no code implementations • 24 Nov 2022 • Yu-Tong Cao, Jingya Wang, Baosheng Yu, DaCheng Tao
To further enhance the active learner via large-scale unlabelled data, we introduce multiple peer students into the active learner which is trained by a novel learning paradigm, including the In-Class Peer Study on labelled data and the Out-of-Class Peer Study on unlabelled data.
no code implementations • 22 Nov 2022 • Xiao Han, Yiming Ren, Peishan Cong, Yujing Sun, Jingya Wang, Lan Xu, Yuexin Ma
In this paper, based on a single LiDAR, we present the Hierarchical Multi-representation Feature Interaction Network (HMRNet) for robust gait recognition.
1 code implementation • 3 Nov 2022 • Hongxia Li, Zhongyi Cai, Jingya Wang, Jiangnan Tang, Weiping Ding, Chin-Teng Lin, Ye Shi
Instead of using a vanilla personalization mechanism that maintains personalized self-attention layers of each client locally, we develop a learn-to-personalize mechanism to further encourage the cooperation among clients and to increase the scablability and generalization of FedTP.
1 code implementation • 31 Oct 2022 • Wanxing Chang, Ye Shi, Hoang Duong Tuan, Jingya Wang
Notably, UniOT is the first method with the capability to automatically discover and recognize private categories in the target domain for UniDA.
Ranked #3 on Universal Domain Adaptation on Office-Home
1 code implementation • 3 Oct 2022 • Haixiang Sun, Ye Shi, Jingya Wang, Hoang Duong Tuan, H. Vincent Poor, DaCheng Tao
In this paper, we developed a new framework, named Alternating Differentiation (Alt-Diff), that differentiates optimization problems (here, specifically in the form of convex optimization problems with polyhedral constraints) in a fast and recursive way.
no code implementations • 14 Sep 2022 • Zesong Qiu, Yuwei Li, Dongming He, Qixuan Zhang, Longwen Zhang, Yinghao Zhang, Jingya Wang, Lan Xu, Xudong Wang, Yuyao Zhang, Jingyi Yu
Named after the fossils of one of the oldest known human ancestors, our LUCY dataset contains high-quality Computed Tomography (CT) scans of the complete human head before and after orthognathic surgeries, critical for evaluating surgery results.
no code implementations • 16 Jul 2022 • Juze Zhang, Jingya Wang, Ye Shi, Fei Gao, Lan Xu, Jingyi Yu
This method first uses 2. 5D pose and geometry information to infer camera-centric root depths in a forward pass, and then exploits the root depths to further improve representation learning of 2. 5D pose estimation in a backward pass.
no code implementations • 17 Mar 2022 • Han Liang, Yannan He, Chengfeng Zhao, Mutian Li, Jingya Wang, Jingyi Yu, Lan Xu
Monocular 3D motion capture (mocap) is beneficial to many applications.
Ranked #1 on Pose Estimation on 3DPW
no code implementations • 23 Sep 2021 • Xianing Chen, Chunlin Xu, Qiong Cao, Jialang Xu, Yujie Zhong, Jiale Xu, Zhengxin Li, Jingya Wang, Shenghua Gao
Transformers have shown preferable performance on many vision tasks.
no code implementations • 1 Aug 2021 • Guoxing Sun, Xin Chen, Yizhang Chen, Anqi Pang, Pei Lin, Yuheng Jiang, Lan Xu, Jingya Wang, Jingyi Yu
In this paper, we propose a neural human performance capture and rendering system to generate both high-quality geometry and photo-realistic texture of both human and objects under challenging interaction scenarios in arbitrary novel views, from only sparse RGB streams.
no code implementations • 1 Jul 2021 • Jing Zhao, Jingya Wang, Madhav Sigdel, Bopeng Zhang, Phuong Hoang, Mengshu Liu, Mohammed Korayem
The overall improvement of our job to candidate matching system has demonstrated its feasibility and scalability at a major online recruitment site.
1 code implementation • CVPR 2021 • Song Guo, Jingya Wang, Xinchao Wang, DaCheng Tao
On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts.
1 code implementation • ECCV 2020 • Yu-Tong Cao, Jingya Wang, DaCheng Tao
The current state-of-the-art methods either focus on learning better cross-modal embeddings by mining only seen data, or they explicitly use generative adversarial networks (GANs) to synthesize unseen features.
1 code implementation • CVPR 2020 • Shang Gao, Jingya Wang, Huchuan Lu, Zimo Liu
Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario.
no code implementations • 23 Jul 2019 • Mengshu Liu, Jingya Wang, Kareem Abdelfatah, Mohammed Korayem
Job recommendation is a crucial part of the online job recruitment business.
no code implementations • CVPR 2018 • Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li
Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair.
Ranked #23 on Unsupervised Domain Adaptation on Market to Duke
no code implementations • ICCV 2017 • Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei Li
Recognising semantic pedestrian attributes in surveillance images is a challenging task for computer vision, particularly when the imaging quality is poor with complex background clutter and uncontrolled viewing conditions, and the number of labelled training data is small.
no code implementations • 30 May 2017 • Jingya Wang, Xiatian Zhu, Shaogang Gong
As a result, our model is able to discover more accurate semantic correlation between textual tags and visual features, and finally providing favourable visual semantics interpretation even with highly sparse and incomplete tags.