Our group has co-authored five accepted papers in ICCV 2023.

1. S.S. Rambhatla, I. Misra, R. Chellappa, A. Shrivastava, “MOST: Multiple Object Localization with Self-supervised Transformers for Object Discovery”, Proc. Intl. Conf. Computer Vision, Paris, France, October 2023.

2. S.S. Rambhatla, S. Suri, R. Chellappa and A. Shrivastava, “Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach”, Proc. Intl. Conf. Computer Vision, Paris, France, October 2023.

3. A. Shah, B. Lundell, H. Sawhney and R. Chellappa, “STEPs: Self-Supervised Key Step Extraction from Unlabeled Procedural Videos”, Proc. Intl. Conf. Computer Vision, Paris, France, October 2023.

4. S. Pramanick, Y. Song, S. Nag, K. Qinghong Lin, H. Shah, M. Z. Shou, R. Chellappa, P. Zhang, “EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone”, Proc. Intl. Conf. Computer Vision, Paris, France, October 2023.

5. K. Qinghong Lin, P. Zhang, J. Chen, S. Pramanick, D. Gao, A. JP. Wang, R. Yan, M. Z. Shou, “UniVTG: Towards Unified Video-Language Temporal Grounding”, Proc. Intl. Conf. Computer Vision, Paris, France, October 2023.