136 citations · 823 across the 50 of their papers we have counts for
50 papers
Multi-stage Factorized Spatio-Temporal Representation for RGB-D Action and Gesture Recognition
Yujun Ma, Benjia Zhou, Ruili Wang +1
RGB-D action and gesture recognition remain an interesting topic in human-centered scene understanding, primarily due to the multiple granularities and large variation in human mot…
SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels
Henry Hengyuan Zhao, Pichao Wang, Yuyang Zhao +3
Pre-trained vision transformers have strong representation benefits to various downstream tasks. Recently, many parameter-efficient fine-tuning (PEFT) methods have been proposed, a…
Revisiting Vision Transformer from the View of Path Ensemble
Shuning Chang, Pichao Wang, Hao Luo +2
Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks…
Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment
Sarah Ibrahimi, Xiaohang Sun, Pichao Wang +3
Text-to-video retrieval systems have recently made significant progress by utilizing pre-trained models trained on large-scale image-text pairs. However, most of the latest methods…
DOAD: Decoupled One Stage Action Detection Network
Shuning Chang, Pichao Wang, Fan Wang +2
Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stag…
PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation
Qitao Zhao, Ce Zheng, Mengyuan Liu +2
Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relation…
Making Vision Transformers Efficient from A Token Sparsification View
Shuning Chang, Pichao Wang, Ming Lin +4
The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to a…
Selective Structured State-Spaces for Long-Form Video Understanding
Jue Wang, Wentao Zhu, Pichao Wang +4
Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its lin…
Revisit Parameter-Efficient Transfer Learning: A Two-Stage Paradigm
Hengyuan Zhao, Hao Luo, Yuyang Zhao +3
Parameter-Efficient Transfer Learning (PETL) aims at efficiently adapting large models pre-trained on massive data to downstream tasks with limited task-specific data. In view of t…
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
Hansheng Chen, Wei Tian, Pichao Wang +3
Locating 3D objects from a single RGB image via Perspective-n-Point (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest…
Head-Free Lightweight Semantic Segmentation with Linear Transformer
Bo Dong, Pichao Wang, Fan Wang
Existing semantic segmentation works have been mainly focused on designing effective decoders; however, the computational load introduced by the overall structure has long been ign…
A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
Benjia Zhou, Pichao Wang, Jun Wan +2
Motion recognition is a promising direction in computer vision, but the training of video classification models is much harder than images due to insufficient data and considerable…
Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition
Zhimin Gao, Peitao Wang, Pei Lv +5
Despite great progress achieved by transformer in various vision tasks, it is still underexplored for skeleton-based action recognition with only a few attempts. Besides, these met…
Effective Vision Transformer Training: A Data-Centric Perspective
Benjia Zhou, Pichao Wang, Jun Wan +2
Vision Transformers (ViTs) have shown promising performance compared with Convolutional Neural Networks (CNNs), but the training of ViTs is much harder than CNNs. In this paper, we…
FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis
Zihui Guo, Yonghong Hou, Pichao Wang +3
Analysis of human interaction is one important research topic of human motion analysis. It has been studied either using first person vision (FPV) or third person vision (TPV). How…
BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective
Shanshan Wang, Lei Zhang, Pichao Wang
Triplet loss, one of the deep metric learning (DML) methods, is to learn the embeddings where examples from the same class are closer than examples from different classes. Motivate…
Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer
Pichao Wang, Fan Wang, Hao Li
The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillati…
ELSA: Enhanced Local Self-Attention for Vision Transformer
Jingkai Zhou, Pichao Wang, Fan Wang +3
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par w…
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
Benjia Zhou, Pichao Wang, Jun Wan +6
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognitio…
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Zhaoyuan Yin, Pichao Wang, Fan Wang +4
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up ap…
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
Hao Luo, Pichao Wang, Yi Xu +5
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it usual…
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Wenhao Li, Hong Liu, Hao Tang +2
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spat…
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Tongkun Xu, Weihua Chen, Pichao Wang +3
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on lear…
Scaled ReLU Matters for Training Vision Transformers
Pichao Wang, Xue Wang, Hao Luo +5
Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensit…