6 Papers Accepted in ICCV 2025
We are delighted to announce that members of the UNC-Charlotte AI4Health Center have had six papers accepted at the International Conference on Computer Vision (ICCV) 2025, one of the world’s premier conferences in AI and computer vision.
This significant accomplishment underscores both the strength and collaborative spirit of AI research at the AI4Health Center. The supervising faculty for these papers include Dr. Pu Wang, Dr. Hongfei Xue, Dr. Ahmed Helmy, Dr. Srijan Das, Dr. Aidong Lu, and Dr. Depeng Xu.
A notable highlight is the paper, “Spatio-Temporal Control for Masked Motion Synthesis,” which received a perfect review score and was selected for an oral presentation. This is an exceptional distinction, awarded to only 1.68% of all submissions based on the 2023 benchmark. The work was led by PhD students Ekkasit Pinyoanuntapong and Muhammad Usama Saleem, co-advised by Dr. Pu Wang, Dr. Hongfei Xue, Dr. Ahmed Helmy, and Dr. Srijan Das.
About ICCV 2025
ICCV is a highly selective and influential conference, playing a key role in the computer science field. Its prestige is highlighted by the following metrics:
- Ranked 10th in Engineering & Computer Science on the h5-index rankings.
- Ranked 25th in all subject categories on the h5-index rankings.
- The conference received 11,239 submissions with a competitive 24% acceptance rate.
- Along with CVPR and ECCV, ICCV is one of three conferences counted toward the CS program national ranking by CSRankings.
Accepted Papers
Spatio-Temporal Control for Masked Motion Synthesis
Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, Sergey Tulyakov
MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild
Muhammad Usama Saleem, Ekkasit Pinyoanuntapong, Mayur Jagdishbhai Patel, Hongfei Xue, Ahmed Helmy, Srijan Das, Pu Wang
mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework
Bingyi Liu, Jian Teng, Hongfei Xue, Enshu Wang, Chuanhui Zhu, Pu Wang, Libing Wu
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
Wenhan Wu, Zhishuai Guo, Chen Chen, Hongfei Xue, Aidong Lu
Privacy-centric Deep Motion Retargeting for Anonymization of Skeleton-Based Motion Visualization
Thomas Carr, Depeng Xu, Shuhan Yuan, Aidong Lu
GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology
Saarthak Kapse*, Pushpak Pati*, Srikar Yellapragada†, Srijan Das†, Rajarsi R. Gupta, Joel Saltz, Dimitris Samaras, Prateek Prasanna *Co-first authors, †Co-second authors