| Molmo2: Open weights and data for vision-language models with video understanding and grounding C Clark, J Zhang, Z Ma, JS Park, R Tripathi, S Lee, M Salehi, J Ren, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2026 | 166* | 2026 |
| MMTSA: Multi-modal temporal segment attention network for efficient human activity recognition Z Gao, Y Wang, J Chen, J Xing, S Patel, X Liu, Y Shi Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous …, 2023 | 42 | 2023 |
| Generate any scene: Scene graph driven data synthesis for visual generation training Z Gao, W Huang, J Zhang, A Kembhavi, R Krishna International Conference on Learning Representations 2026, 124660-124702, 2026 | 11* | 2026 |
| One trajectory, one token: Grounded video tokenization via panoptic sub-object trajectory C Zheng, J Zhang, M Salehi, Z Gao, V Iyengar, N Kobori, Q Kong, ... 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 23156-23166, 2025 | 10 | 2025 |
| Synthetic Object Compositions for scalable and accurate learning in detection, segmentation, and grounding W Huang, J Zhang, T Jia, C Zheng, Z Gao, JS Park, R Krishna Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2026 | 4 | 2026 |
| Synthetic Visual Genome 2: Extracting Large-Scale Spatio-Temporal Scene Graphs from Videos Z Gao, J Zhang, WO Ikechukwu, JS Park, TG You, D Ogbu, C Zheng, ... European Conference on Computer Vision, 19-37, 2026 | 1 | 2026 |
| Vision-Language Grounding as Bidirectional Concept Correspondence J Zhang, Z Gao, L Zettlemoyer, R Krishna arXiv preprint arXiv:2608.07886, 2026 | | 2026 |
