794 citations · 4.8k across the 152 of their papers we have counts for
20 papers · 1 filter
Audio-Driven Co-Speech Gesture Video Generation
Xian Liu, Qianyi Wu, Hang Zhou +4
Co-speech gesture is crucial for human-machine interaction and digital entertainment. While previous works mostly map speech audio to human skeletons (e.g., 2D keypoints), directly…
Factor Investing with a Deep Multi-Factor Model
Zikai Wei, Bo Dai, Dahua Lin
Modeling and characterizing multiple factors is perhaps the most important step in achieving excess returns over market benchmarks. Both academia and industry are striving to find…
Rethinking Trajectory Prediction via "Team Game"
Zikai Wei, Xinge Zhu, Bo Dai +1
To accurately predict trajectories in multi-agent settings, e.g. team games, it is important to effectively model the interactions among agents. Whereas a number of methods have be…
Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
Anyi Rao, Xuekun Jiang, Sichen Wang +7
The ability to choose an appropriate camera view among multiple cameras plays a vital role in TV shows delivery. But it is hard to figure out the statistical pattern and apply inte…
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
Haodong Duan, Jiaqi Wang, Kai Chen +1
Graph convolution networks (GCN) have been widely used in skeleton-based action recognition. We note that existing GCN-based approaches primarily rely on prescribed graphical struc…
Force-Aware Interface via Electromyography for Natural VR/AR Interaction
Yunxiang Zhang, Benjamin Liang, Boyuan Chen +4
While tremendous advances in visual and auditory realism have been made for virtual and augmented reality (VR/AR), introducing a plausible sense of physicality into the virtual wor…
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
Haodong Duan, Yue Zhao, Kai Chen +2
Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, p…
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Hongyang Li, Chonghao Sima, Jifeng Dai +19
Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches…
OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
Weijia Li, Yawen Lai, Linning Xu +5
This paper presents OmniCity, a new dataset for omnipotent city understanding from multi-level and multi-view images. More precisely, the OmniCity contains multi-view satellite ima…
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
Tong Wu, Jiaqi Wang, Xingang Pan +4
Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit m…
Static and Dynamic Concepts for Self-supervised Video Representation Learning
Rui Qian, Shuangrui Ding, Xian Liu +1
In this paper, we propose a novel learning scheme for self-supervised video representation learning. Motivated by how humans understand videos, we propose to first learn general vi…
Monocular 3D Object Detection with Depth from Motion
Tai Wang, Jiangmiao Pang, Dahua Lin
Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its economy compared to multi-sensor settings. It is notably difficult as a single image can not p…
Guided Diffusion Model for Adversarial Purification
Jinyi Wang, Zhaoyang Lyu, Dahua Lin +2
With wider application of deep neural networks (DNNs) in various algorithms and frameworks, security threats have become one of the concerns. Adversarial attacks disturb DNN-based…
Accelerating Diffusion Models via Early Stop of the Diffusion Process
Zhaoyang Lyu, Xudong XU, Ceyuan Yang +2
Denoising Diffusion Probabilistic Models (DDPMs) have achieved impressive performance on various generation tasks. By modeling the reverse process of gradually diffusing the data d…
Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis
Jingbo Wang, Yu Rong, Jingyuan Liu +3
The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are const…
PYSKL: Towards Good Practices for Skeleton Action Recognition
Haodong Duan, Jiaqi Wang, Kai Chen +1
We present PYSKL: an open-source toolbox for skeleton-based action recognition based on PyTorch. The toolbox supports a wide variety of skeleton action recognition algorithms, incl…
MINI: Mining Implicit Novel Instances for Few-Shot Object Detection
Yuhang Cao, Jiaqi Wang, Yiqi Lin +1
Learning from a few training samples is a desirable ability of an object detector, inspiring the explorations of Few-Shot Object Detection (FSOD). Most existing approaches employ a…
TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition
Haodong Duan, Nanxuan Zhao, Kai Chen +1
Recognizing transformation types applied to a video clip (RecogTrans) is a long-established paradigm for self-supervised video representation learning, which achieves much inferior…
SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition
Mingxin Huang, Yuliang Liu, Zhenghao Peng +6
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. How…
OCSampler: Compressing Videos to One Clip with Single-step Sampling
Jintao Lin, Haodong Duan, Kai Chen +2
In this paper, we propose a framework named OCSampler to explore a compact yet effective video representation with one short clip for efficient video recognition. Recent works pref…