35 citations · 95 across the 24 of their papers we have counts for
25 papers
Identity-Aware Human-Object Interaction Motion Captioning
Yiming Wang, Yonghao Dang, Huilai Li +2
Existing human-object interaction (HOI) motion captioning methods typically describe what happens while referring to the subject using generic terms such as "a person" or "someone"…
EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing
Huilai Li, Xiaomeng Di, Ying Xing +3
Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Fac…
ResDiT: Evoking the Intrinsic Resolution Scalability in Diffusion Transformers
Yiyang Ma, Feng Zhou, Xuedan Yin +3
Leveraging pre-trained Diffusion Transformers (DiTs) for high-resolution (HR) image synthesis often leads to spatial layout collapse and degraded texture fidelity. Prior work mitig…
MaskSem: Semantic-Guided Masking for Learning 3D Hybrid High-Order Motion Representation
Wei Wei, Shaojie Zhang, Yonghao Dang +1
Human action recognition is a crucial task for intelligent robotics, particularly within the context of human-robot collaboration research. In self-supervised skeleton-based action…
3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving
Yixun Zhang, Lizhi Wang, Junjun Zhao +4
Camera-based perception in connected and autonomous vehicles remains exposed to physical adversarial attacks. Prior attacks often either optimize image-plane textures, weakening cr…
ESG-Net: Event-Aware Semantic Guided Network for Dense Audio-Visual Event Localization
Huilai Li, Yonghao Dang, Ying Xing +2
Dense audio-visual event localization (DAVE) aims to identify event categories and locate the temporal boundaries in untrimmed videos. Most studies only employ event-related semant…
L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation
Guoliang Xu, Jianqin Yin, Ren Zhang +3
Since COVID-19, crowd-counting tasks have gained wide applications. While supervised methods are reliable, annotation is more challenging in high-density scenes due to small head s…
GaussianCAD: Robust Self-Supervised CAD Reconstruction from Three Orthographic Views Using 3D Gaussian Splatting
Zheng Zhou, Zhe Li, Bo Yu +8
The automatic reconstruction of 3D computer-aided design (CAD) models from CAD sketches has recently gained significant attention in the computer vision community. Most existing me…
MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection
Yonghao Dang, Liyuan Liu, Hui Kang +2
Real-time 2D keypoint detection plays an essential role in computer vision. Although CNN-based and Transformer-based methods have achieved breakthrough progress, they often fail to…
Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
Meng Chen, Jiawei Tu, Chao Qi +4
The significant advancements in embodied vision navigation have raised concerns about its susceptibility to adversarial attacks exploiting deep neural networks. Investigating the a…
ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality
Guoliang Xu, Jianqin Yin, Feng Zhou +1
Previous methods usually only extract the image modality's information to recognize group activity. However, mining image information is approaching saturation, making it difficult…
Micro-expression recognition based on depth map to point cloud
Ren Zhang, Jianqin Yin, Chao Qi +3
Micro-expressions are nonverbal facial expressions that reveal the covert emotions of individuals, making the micro-expression recognition task receive widespread attention. Howeve…
DHRNet: A Dual-Path Hierarchical Relation Network for Multi-Person Pose Estimation
Yonghao Dang, Jianqin Yin, Liyuan Liu +3
Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision. Most existing methods predominantly concentrate on isolated interaction either b…
Full-frequency dynamic convolution: a physical frequency-dependent convolution for sound event detection
Haobo Yue, Zhicheng Zhang, Da Mu +3
Recently, 2D convolution has been found unqualified in sound event detection (SED). It enforces translation equivariance on sound events along frequency axis, which is not a shift-…
A Generically Contrastive Spatiotemporal Representation Enhancement for 3D Skeleton Action Recognition
Shaojie Zhang, Jianqin Yin, Yonghao Dang
Skeleton-based action recognition is a central task in computer vision and human-robot interaction. However, most previous methods suffer from overlooking the explicit exploitation…
BiHRNet: A Binary high-resolution network for Human Pose Estimation
Zhicheng Zhang, Xueyao Sun, Yonghao Dang +1
Human Pose Estimation (HPE) plays a crucial role in computer vision applications. However, it is difficult to deploy state-of-the-art models on resouce-limited devices due to the h…
SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition
Shaojie Zhang, Jianqin Yin, Yonghao Dang +1
Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition. However, previous GCN-based methods rely on elaborate human priors exce…
Physics-constrained Attack against Convolution-based Human Motion Prediction
Chengxu Duan, Zhicheng Zhang, Xiaoli Liu +2
Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk…
An Improved Baseline Framework for Pose Estimation Challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop
Jiajun Fu, Yonghao Dang, Ruoqi Yin +4
This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop. In this chal…
Leveraging the Video-level Semantic Consistency of Event for Audio-visual Event Localization
Yuanyuan Jiang, Jianqin Yin, Yonghao Dang
Audio-visual event (AVE) localization has attracted much attention in recent years. Most existing methods are often limited to independently encoding and classifying each video seg…
Kinematics Modeling Network for Video-based Human Pose Estimation
Yonghao Dang, Jianqin Yin, Shaojie Zhang +2
Estimating human poses from videos is critical in human-computer interaction. Joints cooperate rather than move independently during human movement. There are both spatial and temp…
Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction
Jiajun Fu, Fuxing Yang, Yonghao Dang +2
Human motion prediction is challenging due to the complex spatiotemporal feature modeling. Among all methods, graph convolution networks (GCNs) are extensively utilized because of…
Relation-Based Associative Joint Location for Human Pose Estimation in Videos
Yonghao Dang, Jianqin Yin, Shaojie Zhang
Video-based human pose estimation (VHPE) is a vital yet challenging task. While deep learning methods have made significant progress for the VHPE, most approaches to this task impl…
Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos
Jianqin Yin, Yanchun Wu, Huaping Liu +3
Action repetition counting is to estimate the occurrence times of the repetitive motion in one action, which is a relatively new, important but challenging measurement problem. To…