98 citations · 675 across the 50 of their papers we have counts for
44 papers · 1 filter
Language-guided Human Motion Synthesis with Atomic Actions
Yuanhao Zhai, Mingzhen Huang, Tianyu Luan +5
Language-guided human motion synthesis has been a challenging task due to the inherent complexity and diversity of human behaviors. Previous methods face limitations in generalizat…
Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning
Qinji Yu, Nan Xi, Junsong Yuan +3
Unsupervised domain adaptation (UDA) has increasingly gained interests for its capacity to transfer the knowledge learned from a labeled source domain to an unlabeled target domain…
High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition
Tianyu Luan, Yuanhao Zhai, Jingjing Meng +4
Despite the impressive performance obtained by recent single-image hand modeling techniques, they lack the capability to capture sufficient details of the 3D hand mesh. This defici…
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting
Wentao Bao, Lele Chen, Libing Zeng +4
Hand trajectory forecasting from egocentric views is crucial for enabling a prompt understanding of human intentions when interacting with AR/VR systems. However, existing methods…
Neural Voting Field for Camera-Space 3D Hand Pose Estimation
Lin Huang, Chung-Ching Lin, Kevin Lin +4
We present a unified framework for camera-space 3D hand pose estimation from a single RGB image based on 3D implicit representation. As opposed to recent works, most of which first…
Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction
Xiangyu Xu, Lichang Chen, Changjiang Cai +6
Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules. However, this approach is constrained…
Harnessing Low-Frequency Neural Fields for Few-Shot View Synthesis
Liangchen Song, Zhong Li, Xuan Gong +4
Neural Radiance Fields (NeRF) have led to breakthroughs in the novel view synthesis problem. Positional Encoding (P.E.) is a critical factor that brings the impressive performance…
Progressive Multi-view Human Mesh Recovery with Self-Supervision
Xuan Gong, Liangchen Song, Meng Zheng +5
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-vie…
GRiT: A Generative Region-to-text Transformer for Object Understanding
Jialian Wu, Jianfeng Wang, Zhengyuan Yang +4
This paper presents a Generative RegIon-to-Text transformer, GRiT, for object understanding. The spirit of GRiT is to formulate object understanding as <region, text> pairs, where…
NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
Liangchen Song, Anpei Chen, Zhong Li +5
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are…
PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack
Junxuan Huang, Yatong An, Lu cheng +3
Despite recent success of self-supervised based contrastive learning model for 3D point clouds representation, the adversarial robustness of such pre-trained models raised concerns…
PREF: Predictability Regularized Neural Motion Fields
Liangchen Song, Xuan Gong, Benjamin Planche +5
Knowing the 3D motions in a dynamic scene is essential to many vision applications. Recent progress is mainly focused on estimating the activity of some specific elements like huma…
Neural Correspondence Field for Object Pose Estimation
Lin Huang, Tomas Hodan, Lingni Ma +7
We propose a method for estimating the 6DoF pose of a rigid object with an available 3D model from a single RGB image. Unlike classical correspondence-based methods which predict 3…
AiATrack: Attention in Attention for Transformer Visual Tracking
Shenyuan Gao, Chunluan Zhou, Chao Ma +2
Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the…
Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
Nitin Bansal, Pan Ji, Junsong Yuan +1
Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/infer…
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video
Jinlu Zhang, Zhigang Tu, Jianyu Yang +2
Recent transformer-based solutions have been introduced to estimate 3D human pose from 2D keypoint sequence by considering body joints among all frames globally to learn spatio-tem…
Optical Flow for Video Super-Resolution: A Survey
Zhigang Tu, Hongyan Li, Wei Xie +4
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-reso…
Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
Sudhir Yarram, Jialian Wu, Pan Ji +2
Video instance segmentation (VIS) task requires classifying, segmenting, and tracking object instances over all frames in a video clip. Recently, VisTR has been proposed as end-to-…
Efficient Video Instance Segmentation via Tracklet Query and Proposal
Jialian Wu, Sudhir Yarram, Hui Liang +4
Video Instance Segmentation (VIS) aims to simultaneously classify, segment, and track multiple object instances in videos. Recent clip-level VIS takes a short video clip as input e…
Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition
Zhigang Tu, Jiaxu Zhang, Hongyan Li +2
In recent years, graph convolutional networks (GCNs) play an increasingly critical role in skeleton-based human action recognition. However, most GCN-based methods still have two m…
Motion-driven Visual Tempo Learning for Video-based Action Recognition
Yuanzhong Liu, Junsong Yuan, Zhigang Tu
Action visual tempo characterizes the dynamics and the temporal scale of an action, which is helpful to distinguish human actions that share high similarities in visual dynamics an…
Consistent 3D Hand Reconstruction in Video via self-supervised Learning
Zhigang Tu, Zhisheng Huang, Yujin Chen +4
We present a method for reconstructing accurate and consistent 3D hands from a monocular video. We observe that detected 2D hand keypoints and the image texture provide important c…
Pseudo Supervised Monocular Depth Estimation with Teacher-Student Network
Huan Liu, Junsong Yuan, Chen Wang +1
Despite recent improvement of supervised monocular depth estimation, the lack of high quality pixel-wise ground truth annotations has become a major hurdle for further progress. In…
Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track
Yuanhao Zhai, Le Wang, David Doermann +1
This technical report presents our solution to the HACS Temporal Action Localization Challenge 2021, Weakly-Supervised Learning Track. The goal of weakly-supervised temporal action…