20 citations · 45 across the 12 of their papers we have counts for
12 papers
VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs
Chaokang Jiang, Desen Zhou, Jiuming Liu +1
Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due…
Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning
Bo Wan, Yongfei Liu, Desen Zhou +2
Human object interaction (HOI) detection plays a crucial role in human-centric scene understanding and serves as a fundamental building-block for many vision tasks. One generalizab…
Temporal Segment Transformer for Action Segmentation
Zhichao Liu, Leshan Wang, Desen Zhou +5
Recognizing human actions from untrimmed videos is an important task in activity understanding, and poses unique challenges in modeling long-range temporal relations. Recent works…
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition
Tailin Chen, Desen Zhou, Jian Wang +6
In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel…
Action Quality Assessment with Temporal Parsing Transformer
Yang Bai, Desen Zhou, Songyang Zhang +5
Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art meth…
Human-Object Interaction Detection via Disentangled Transformer
Desen Zhou, Zhichao Liu, Jian Wang +4
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decode…
Automatic spinal curvature measurement on ultrasound spine images using Faster R-CNN
Zhichao Liu, Liyue Qian, Wenke Jing +4
Ultrasound spine imaging technique has been applied to the assessment of spine deformity. However, manual measurements of scoliotic angles on ultrasound images are time-consuming a…
LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action Recognition
Tailin Chen, Shidong Wang, Desen Zhou +1
Modelling various spatio-temporal dependencies is the key to recognising human actions in skeleton sequences. Most existing methods excessively relied on the design of traversal ru…
Single Image 3D Object Estimation with Primitive Graph Networks
Qian He, Desen Zhou, Bo Wan +1
Reconstructing 3D object from a single image (RGB or depth) is a fundamental problem in visual scene understanding and yet remains challenging due to its ill-posed nature and compl…
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
Tailin Chen, Desen Zhou, Jian Wang +4
The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. E…
Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network
Hong-Ye Zeng, Song-Han Ge, Yu-Chong Gao +5
Objective: The spinous process angle (SPA) is one of the essential parameters to denote three-dimensional (3-D) deformity of spine. We propose an automatic segmentation method base…
Pose-aware Multi-level Feature Network for Human Object Interaction Detection
Bo Wan, Desen Zhou, Yongfei Liu +2
Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large vari…