Zehai Niu

According to our database, Zehai Niu authored at least 12 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

FoodSAM: Any Food Segmentation.

Xing Lan, Jiayi Lyu, Hanyu Jiang, Kun Dong, Zehai Niu, Yi Zhang, Jian Xue

IEEE Trans. Multim., 2025

2024

Dynamic spatial-temporal topology graph network for skeleton-based action recognition.

Lian Chen, Ke Lu, Zehai Niu, Runchen Wei, Jian Xue

Multim. Syst., December, 2024

From Methods to Applications: A Review of Deep 3D Human Motion Capture.

Zehai Niu, Ke Lu, Jian Xue, Xiaoyu Qin, Jinbao Wang, Ling Shao

IEEE Trans. Circuits Syst. Video Technol., November, 2024

Skeleton Cluster Tracking for robust multi-view multi-person 3D human pose estimation.

Zehai Niu, Ke Lu, Jian Xue, Jinbao Wang

Comput. Vis. Image Underst., 2024

Realistic Full-Body Motion Generation from Sparse Tracking with State Space Model.

Kun Dong, Jian Xue, Zehai Niu, Xing Lan, Ke Lu, Qingyuan Liu, Xiaoyu Qin

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

VS3D: A Vote-Based Semi-Supervised 3D Object Detection Framework for Point Clouds.

Shuhua Wang, Ke Lu, Yang Zhao, Hengsheng Lun, Zehai Niu, Jian Xue

Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

Anatomically-Informed Vector Quantization Variational Auto-Encoder for Text to Motion Generation.

Lian Chen, Zehai Niu, Qingyuan Liu, Jinbao Wang, Jian Xue, Ke Lu

Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

AdaptControl: Adaptive Human Motion Control and Generation via User Prompt and Spatial Trajectory Guidance.

Qingyuan Liu, Zehai Niu, Ke Lu, Kun Dong, Jian Xue, Xiaoyu Qin, Jinbao Wang

Proceedings of the 5th International Workshop on Human-centric Multimedia Analysis, 2024

Motion Reconstruction via Human Anatomy Diffusion from Sparse Tracking.

Zehai Niu, Ke Lu, Kun Dong, Jian Xue, Xiaoyu Qin, Jinbao Wang

Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

FlexControl: Flexible and Efficient Full-Body Controllable Text-to-Motion Generation.

Qingyuan Liu, Ke Lu, Zehai Niu, Kun Dong, Jian Xue, Xiaoyu Qin, Jinbao Wang

Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

2022

Local to Global Transformer for Video Based 3d Human Pose Estimation.

Haifeng Ma, Ke Lu, Jian Xue, Zehai Niu, Pengcheng Gao

Proceedings of the IEEE International Conference on Multimedia and Expo Workshops, 2022

2021

Multi-view 3D Smooth Human Pose Estimation based on Heatmap Filtering and Spatio-temporal Information.

Zehai Niu, Ke Lu, Jian Xue, Haifeng Ma, Runchen Wei

Proceedings of the MM '21: ACM Multimedia Conference, Virtual Event, China, October 20, 2021