b'Junsong Yuan'

research

∙ 09/03/2023

SOAR: Scene-debiasing Open-set Action Recognition

Deep learning models have a risk of utilizing spurious clues to make pre...

0 Yuanhao Zhai, et al. ∙

research

∙ 09/03/2023

Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning

As advanced image manipulation techniques emerge, detecting the manipula...

0 Yuanhao Zhai, et al. ∙

research

∙ 08/18/2023

Language-guided Human Motion Synthesis with Atomic Actions

Language-guided human motion synthesis has been a challenging task due t...

0 Yuanhao Zhai, et al. ∙

research

∙ 07/19/2023

Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning

Unsupervised domain adaptation (UDA) has increasingly gained interests f...

0 Qinji Yu, et al. ∙

research

∙ 07/17/2023

Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting

Hand trajectory forecasting from egocentric views is crucial for enablin...

0 Wentao Bao, et al. ∙

research

∙ 07/08/2023

High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition

Despite the impressive performance obtained by recent single-image hand ...

0 Tianyu Luan, et al. ∙

research

∙ 05/18/2023

RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texture

The techniques for 3D indoor scene capturing are widely used, but the me...

0 Liangchen Song, et al. ∙

research

∙ 05/07/2023

Neural Voting Field for Camera-Space 3D Hand Pose Estimation

We present a unified framework for camera-space 3D hand pose estimation ...

0 Lin Huang, et al. ∙

research

∙ 04/12/2023

Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction

Direct optimization of interpolated features on multi-resolution voxel g...

3 Xiangyu Xu, et al. ∙

research

∙ 03/15/2023

Harnessing Low-Frequency Neural Fields for Few-Shot View Synthesis

Neural Radiance Fields (NeRF) have led to breakthroughs in the novel vie...

0 Liangchen Song, et al. ∙

research

∙ 12/10/2022

Progressive Multi-view Human Mesh Recovery with Self-Supervision

To date, little attention has been given to multi-view 3D human mesh est...

0 Xuan Gong, et al. ∙

research

∙ 12/01/2022

GRiT: A Generative Region-to-text Transformer for Object Understanding

This paper presents a Generative RegIon-to-Text transformer, GRiT, for o...

0 Jialian Wu, et al. ∙

research

∙ 10/28/2022

NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields

Visually exploring in a real-world 4D spatiotemporal space freely in VR ...

0 Liangchen Song, et al. ∙

research

∙ 10/16/2022

Federated Learning with Privacy-Preserving Ensemble Attention Distillation

Federated Learning (FL) is a machine learning paradigm where many local ...

0 Xuan Gong, et al. ∙

research

∙ 09/21/2022

PREF: Predictability Regularized Neural Motion Fields

Knowing the 3D motions in a dynamic scene is essential to many vision ap...

0 Liangchen Song, et al. ∙

research

∙ 09/14/2022

PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack

Despite recent success of self-supervised based contrastive learning mod...

0 Junxuan Huang, et al. ∙

research

∙ 07/30/2022

Neural Correspondence Field for Object Pose Estimation

We propose a method for estimating the 6DoF pose of a rigid object with ...

0 Lin Huang, et al. ∙

research

∙ 07/20/2022

AiATrack: Attention in Attention for Transformer Visual Tracking

Transformer trackers have achieved impressive advancements recently, whe...

0 Shenyuan Gao, et al. ∙

research

∙ 06/21/2022

Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth

Multi-task learning (MTL) paradigm focuses on jointly learning two or mo...

0 Nitin Bansal, et al. ∙

research

∙ 03/20/2022

Optical Flow for Video Super-Resolution: A Survey

Video super-resolution is currently one of the most active research topi...

0 Zhigang Tu, et al. ∙

research

∙ 03/12/2022

Deformable VisTR: Spatio temporal deformable attention for video instance segmentation

Video instance segmentation (VIS) task requires classifying, segmenting,...

0 Sudhir Yarram, et al. ∙

research

∙ 03/03/2022

Efficient Video Instance Segmentation via Tracklet Query and Proposal

Video Instance Segmentation (VIS) aims to simultaneously classify, segme...

0 Jialian Wu, et al. ∙

research

∙ 03/02/2022

MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video

Recent transformer-based solutions have been introduced to estimate 3D h...

7 Jinlu Zhang, et al. ∙

research

∙ 02/24/2022

Slow-Fast Visual Tempo Learning for Video-based Action Recognition

Action visual tempo characterizes the dynamics and the temporal scale of...

0 Yuanzhong Liu, et al. ∙

research

∙ 02/08/2022

Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition

In recent years, graph convolutional networks (GCNs) play an increasingl...

3 Zhigang Tu, et al. ∙

research

∙ 01/24/2022

Consistent 3D Hand Reconstruction in Video via self-supervised Learning

We present a method for reconstructing accurate and consistent 3D hands ...

13 Zhigang Tu, et al. ∙

research

∙ 08/08/2021

OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning

We introduce the task of open-vocabulary visual instance search (OVIS). ...

0 Sheng Liu, et al. ∙

research

∙ 06/21/2021

Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track

This technical report presents our solution to the HACS Temporal Action ...

0 Yuanhao Zhai, et al. ∙

research

∙ 05/15/2021

NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field

In this paper, we present an efficient and robust deep learning solution...

10 Celong Liu, et al. ∙

research

∙ 03/30/2021

Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context

Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to...

0 Ziyi Liu, et al. ∙

research

∙ 03/28/2021

ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization

The object of Weakly-supervised Temporal Action Localization (WS-TAL) is...

0 Ziyi Liu, et al. ∙

research

∙ 03/22/2021

Model-based 3D Hand Reconstruction via Self-Supervised Learning

Reconstructing a 3D hand from a single-view RGB image is challenging due...

7 Yujin Chen, et al. ∙

research

∙ 03/16/2021

Track to Detect and Segment: An Online Multi-Object Tracker

Most online multi-object trackers perform object detection stand-alone i...

10 Jialian Wu, et al. ∙

research

∙ 02/01/2021

Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective

Knowledge distillation is an effective approach to leverage a well-train...

19 Helong Zhou, et al. ∙

research

∙ 01/10/2021

SPAGAN: Shortest Path Graph Attention Network

Graph convolutional networks (GCN) have recently demonstrated their pote...

0 Yiding Yang, et al. ∙

research

∙ 11/07/2020

Interventional Domain Adaptation

Domain adaptation (DA) aims to transfer discriminative features learned ...

0 Jun Wen, et al. ∙

research

∙ 10/22/2020

Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization

Weakly-supervised Temporal Action Localization (W-TAL) aims to classify ...

0 Yuanhao Zhai, et al. ∙

research

∙ 09/30/2020

Attention-Aware Noisy Label Learning for Image Classification

Deep convolutional neural networks (CNNs) learned on large-scale labeled...

0 Zhenzhen Wang, et al. ∙

research

∙ 08/14/2020

ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection

We consider the problem of Human-Object Interaction (HOI) Detection, whi...

0 Ye Liu, et al. ∙

research

∙ 08/13/2020

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

Despite the previous success of object analysis, detecting and segmentin...

27 Jialian Wu, et al. ∙

research

∙ 08/12/2020

Revisiting Modified Greedy Algorithm for Monotone Submodular Maximization with a Knapsack Constraint

Monotone submodular maximization with a knapsack constraint is NP-hard. ...

13 Jing Tang, et al. ∙

research

∙ 08/11/2020

Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene

Learning on 3D scene-based point cloud has received extensive attention ...

0 Xinke Li, et al. ∙

research

∙ 08/10/2020

Deep Reinforcement Learning with Label Embedding Reward for Supervised Image Hashing

Deep hashing has shown promising results in image retrieval and recognit...

0 Zhenzhen Wang, et al. ∙

research

∙ 07/15/2020

Temporal Distinct Representation Learning for Action Recognition

Motivated by the previous success of Two-Dimensional Convolutional Neura...

0 Junwu Weng, et al. ∙

research

∙ 07/04/2020

Structure-Aware Human-Action Generation

Generating long-range skeleton-based human actions has been a challengin...

2 Ping Yu, et al. ∙

research

∙ 06/28/2020

Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion

Accurate 3D reconstruction of the hand and object shape from a hand-obje...

22 Yujin Chen, et al. ∙

research

∙ 05/14/2020

Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition

Skeleton-based action recognition has attracted increasing attention due...

2 Tianhang Zheng, et al. ∙

research

∙ 05/12/2020

3DV: 3D Dynamic Voxel for Action Recognition in Depth Video

To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) ...

6 Yancheng Wang, et al. ∙

research

∙ 04/12/2020

Image Co-skeletonization via Co-segmentation

Recent advances in the joint processing of images have certainly shown i...

0 Koteswar Rao Jerripothula, et al. ∙

research

∙ 03/30/2020

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

In this work, we study how well different type of approaches generalise ...

1 Anil Armagan, et al. ∙

Junsong Yuan

Featured Co-authors