| Alignedreid: Surpassing human-level performance in person re-identification X Zhang, H Luo, X Fan, W Xiang, Y Sun, Q Xiao, W Jiang, C Zhang, J Sun arXiv preprint arXiv:1711.08184, 2017 | 709 | 2017 |
| Denoising Diffusion Autoencoders are Unified Self-supervised Learners W Xiang, H Yang, D Huang, Y Wang Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 128 | 2023 |
| Multi-agent embodied question answering in interactive environments S Tan, W Xiang, H Liu, D Guo, F Sun European Conference on Computer Vision, 663-678, 2020 | 46 | 2020 |
| Multi-view Gait Video Synthesis W Xiang, H Yang, D Huang, Y Wang Proceedings of the 30th ACM International Conference on Multimedia, 6783-6791, 2022 | 5 | 2022 |
| DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning W Xiang, H Yang, D Huang, Y Wang arXiv preprint arXiv:2505.10999, 2025 | 1 | 2025 |
Jian SunChief Scientist of Megvii, Managing Director of Megvii ResearchVerified email at megvii.com
