2025: Paper 'Language-guided recursive spatiotemporal graph modeling for video summarization' accepted by International Journal of Computer Vision (IJCV).
2025: Two papers accepted to CVPR 2025.
2024: Paper 'Bridging vision and language spaces with assignment prediction' accepted by ICLR 2024.
2023: Paper 'Bootstrap your own views: Masked ego-exo modeling for fine-grained view-invariant video representations' accepted by CVPR 2023.
2023: Paper 'Dual-path adaptation from image to video transformers' accepted by CVPR 2023.
2022: Paper 'Probabilistic representations for video contrastive learning' accepted by CVPR 2022.
2021: Paper 'Bridge to answer: Structure-aware graph interaction network for video question answering' accepted by CVPR 2021.