8. PMLR, 2020.
Tapaswi et al. (2016)
Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, and Sanja Fidler.
Movieqa: Understanding stories in movies through question-answering.
In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4631–4640, 2016.
Wang et al. (2020)
Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell.
Tent: Fully test-time adaptation by entropy minimization.
arXiv preprint arXiv:2006.10726, 2020.
Wang et al. (2022)
Qin Wang, Olga Fink, Luc Van Gool, and Dengxin Dai.
Continual test-time domain adaptation.
In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7191–7201. IEEE, 2022.
Wang et al. (2025a)
Weihan Wang, Zehai He, Wenyi Hong, Yean Cheng, Xiaohan Zhang, Ji Qi, Ming Ding, Xiaotao Gu, Shiyu Huang, Bin Xu, et al.
Lvbench: An extreme long video understanding benchmark.
In 2025 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 22958–22967. IEEE, 2025a.
Wang et al. (2024)
Xiao Wang, Qingyi Si, Jianlong Wu, Shiyu Zhu, Li Cao, and Liqiang Nie.
Retake: Reducing temporal and knowledge redundancy for long video understanding.
arXiv preprint arXiv:2412.20504, 2024.
Wang et al. (2025b)
Xiao Wang, Qingyi Si, Shiyu Zhu, Jianlong Wu, Li Cao, and Liqiang Nie.
Adaretake: Adaptive redundancy reduction to perceive longer for video-language understanding.
In Findings of the Association for Computational Linguistics: ACL 2025, pp. 5417–5432, 2025b.
Wu et al. (2024)
Haoning Wu, Dongxu Li, Bei Chen, and Junnan Li.
Longvideobench: A benchmark for long-context interleaved video-language understanding.
Advances in Neural Information Processing Systems, 37:28828–28857, 2024.
Xiao et al. (2021)
Junbin Xiao, Xindi Shang, Angela Yao, and Tat-Seng Chua.
Next-qa: Next phase of question-answering to explaining temporal actions.
In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9772–9781. IEEE, 2021.
Yang et al. (2025)
Zeyuan Yang, Delin Chen, Xueyang Yu, Maohao Shen, and Chuang Gan.
Vca: Video curious agent for long video understanding.
In 2025 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 20168–20179. IEEE, 2025.
Zhang et al. (2025)
Boqiang Zhang, Kehan Li, Zesen Cheng, Zhiqiang Hu, Yuqian Yuan, Guanzheng Chen, Sicong Leng, Yuming Jiang, Hang Zhang, Xin Li, et al.
Videollama 3: Frontier multimodal foundation models for image and video understanding.
arXiv preprint arXiv:2501.13106, 2025.
Zhang et al. (2023)
Hang Zhang, Xin Li, and Lidong Bing.
Video-llama: An instruction-tuned audio-visual language model for video understanding.
In Proceedings of the 2023 conference on empirical methods in natural language processing: system demonstrations, pp. 543–553, 2023.
Zhang et al. (2022)
Marvin Zhang, Sergey Levine, and Chelsea Finn.
Memo: Test time robustness via adaptation and augmentation.
Advances in neural information processing systems, 35:38629–38642, 2022.
Zhang et al. (2024)
Peiyuan Zhang, Kaichen Zhang, Bo Li, Guangtao Zeng, Jingkang Yang, Yuanhan Zhang, Ziyue Wang, Haoran Tan, Chunyuan Li, and Ziwei Liu.
Long context transfer from language to vision.
arXiv preprint arXiv:2406.16852, 2024.
Zhang et al. (2026)
Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li, Bin Li, Houqiang Li, and Yan Lu.
Deep video discovery: Agentic search with tool use for long-form video understanding.
Advances in Neural Information Processing Systems, 38:89863–89895, 2026.
Appendix A Training Data Construction and Examples
This section provides additional implementation details for the multi-scale supervision introduced in Section 3.2, together with representative training examples. To balance temporal coverage and redundancy, the 5-, 10-, and 20-second windows are non-overlapping, while windows of 40 seconds or longer use 50% overlap with a stride equal to half the window length. For windows up to 40 seconds, overlapping content from the low-, mid-, and high-level descriptions