Mmbench-video: A long-form multi-shot benchmark for holistic video understanding X Fang, K Mao, H Duan, X Zhao, Y Li, D Lin, K Chen Advances in Neural Information Processing Systems 37, 89098-89124, 2025 | 32 | 2025 |
Oakink2: A dataset of bimanual hands-object manipulation in complex task completion X Zhan, L Yang, Y Zhao, K Mao, H Xu, Z Lin, K Li, C Lu Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 12 | 2024 |