{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:18:05Z","timestamp":1780607885298,"version":"3.54.1"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s11263-025-02555-8","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T12:59:10Z","timestamp":1754657950000},"page":"7726-7747","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5085-0765","authenticated-orcid":false,"given":"Hongjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Limin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"key":"2555_CR1","unstructured":"(1990). Imdb. http:\/\/www.imdb.com\/."},{"key":"2555_CR2","unstructured":"(2021). https:\/\/www.youtube.com\/c\/movieclips."},{"key":"2555_CR3","doi-asserted-by":"crossref","unstructured":"Argaw, D.M., Lee, J.Y., Woodson, M., Kweon, I.S., & Heilbron, F.C. (2023). Long-range multimodal pretraining for movie understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13392\u201313403.","DOI":"10.1109\/ICCV51070.2023.01232"},{"key":"2555_CR4","unstructured":"Castro, S., Azab, M., Stroud, J., Noujaim, C., Wang, R., Deng, J., & Mihalcea, R. (2020). Lifeqa: A real-life dataset for video question answering. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 4352\u20134358."},{"key":"2555_CR5","unstructured":"Castro, S., Deng, N., Huang, P., Burzo, M., & Mihalcea, R. (2022). Wildqa: In-the-wild video question answering. arXiv preprint arXiv:2209.06650."},{"key":"2555_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, F., & Bertasius, G. (2022). Tallformer: Temporal action localization with a long-memory transformer. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXIV, Springer, pp. 503\u2013521.","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"2555_CR7","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1609\/aaai.v35i2.16203","volume":"35","author":"S Choi","year":"2021","unstructured":"Choi, S., On, K. W., Heo, Y. J., Seo, A., Jang, Y., Lee, M., & Zhang, B. T. (2021). Dramaqa: Character-centered Video Story Understanding with Hierarchical Qa. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 1166\u20131174.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2555_CR8","doi-asserted-by":"crossref","unstructured":"Fu, C., Dai, Y., Luo, Y., Li, L., Ren, S., Zhang, R., Wang, Z., Zhou, C., Shen, Y., Zhang, M., et\u00a0al. (2024). Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis. arXiv preprint arXiv:2405.21075.","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"2555_CR9","doi-asserted-by":"crossref","unstructured":"Gao, D., Zhou, L., Ji, L., Zhu, L., Yang, Y., & Shou, M.Z. (2023). Mist: Multi-modal iterative spatial-temporal transformer for long-form video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14773\u201314783.","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"2555_CR10","doi-asserted-by":"crossref","unstructured":"Grauman, K., Westbury, A., Byrne, E., Chavis, Z., Furnari, A., Girdhar, R., Hamburger, J., Jiang, H., Liu, M., Liu, X., et\u00a0al. (2022). Ego4d: Around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012.","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"2555_CR11","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., & Zisserman, A. (2022). Temporal alignment networks for long-term video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2906\u20132916.","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"2555_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xiong, Y., Rao, A,. Wang, J., & Lin, D. (2020a). Movienet: A holistic dataset for movie understanding. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV 16, Springer, pp. 709\u2013727.","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"2555_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Y., Cai, M., Li, Z., & Sato, Y. (2018). Predicting gaze in egocentric video by learning task-dependent attention transition. In: Proceedings of the European conference on computer vision (ECCV), pp. 754\u2013769.","DOI":"10.1007\/978-3-030-01225-0_46"},{"key":"2555_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Y., Sugano, Y., & Sato, Y. (2020b). Improving action segmentation via graph-based temporal reasoning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14024\u201314034.","DOI":"10.1109\/CVPR42600.2020.01404"},{"key":"2555_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Y., Yang, L., & Sato, Y. (2023). Weakly supervised temporal sentence grounding with uncertainty-guided self-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18908\u201318918.","DOI":"10.1109\/CVPR52729.2023.01813"},{"key":"2555_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chen, G., Xu, J., Zhang, M., Yang, L., Pei, B., Zhang, H., Lu, D., Wang, Y., Wang, L., & Qiao, Y. (2024). Egoexolearn: A dataset for bridging asynchronous ego- and exo-centric view of procedural activities in real world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","DOI":"10.1109\/CVPR52733.2024.02084"},{"key":"2555_CR17","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., & Kim, G. (2017). Tgif-qa: Toward spatio-temporal reasoning in visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2758\u20132766.","DOI":"10.1109\/CVPR.2017.149"},{"key":"2555_CR18","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., & Torresani, L. (2019). Scsampler: Sampling salient clips from video for efficient action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6232\u20136242.","DOI":"10.1109\/ICCV.2019.00633"},{"key":"2555_CR19","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., & Berg, T.L. (2018). Tvqa: Localized, compositional video question answering. arXiv preprint arXiv:1809.01696.","DOI":"10.18653\/v1\/D18-1167"},{"key":"2555_CR20","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., & Bansal, M. (2019). Tvqa+: Spatio-temporal grounding for video question answering. arXiv preprint arXiv:1904.11574.","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"2555_CR21","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., & Liu, Z. (2023a). Otter: A multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726."},{"key":"2555_CR22","unstructured":"Li, B., Zhang, Y., Guo, D., Zhang, R., Li, F., Zhang, H., Zhang, K., Zhang, P., Li, Y., Liu, Z., et\u00a0al. (2024a). Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326."},{"key":"2555_CR23","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023b). Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597."},{"key":"2555_CR24","unstructured":"Li, K., He, Y., Wang, Y., Li, Y., Wang, W., Luo, P., Wang, Y., Wang, L., & Qiao, Y. (2023c). Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355."},{"key":"2555_CR25","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., He, Y., Li, Y., Wang, Y., Liu, Y., Wang, Z., Xu, J., Chen, G., Luo, P., et\u00a0al. (2024b). Mvbench: A comprehensive multi-modal video understanding benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22195\u201322206.","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"2555_CR26","doi-asserted-by":"crossref","unstructured":"Li, L., Chen, Y.C., Cheng, Y., Gan, Z., Yu, L., & Liu, J. (2020). Hero: Hierarchical encoder for video+ language omni-representation pre-training. arXiv preprint arXiv:2005.00200.","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"2555_CR27","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Lei, J., Bansal, M., & Bertasius, G. (2022). Eclipse: Efficient long-range video retrieval using sight and sound. In: European Conference on Computer Vision, Springer, pp. 413\u2013430.","DOI":"10.1007\/978-3-031-19830-4_24"},{"key":"2555_CR28","doi-asserted-by":"crossref","unstructured":"Liu, X., Bai, S., & Bai, X. (2022). An empirical study of end-to-end temporal action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20010\u201320019.","DOI":"10.1109\/CVPR52688.2022.01938"},{"key":"2555_CR29","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., & Khan, F.S. (2023). Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424.","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"2555_CR30","doi-asserted-by":"crossref","unstructured":"Maharaj, T., Ballas, N., Rohrbach, A., Courville, A., & Pal, C. (2017). A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6884\u20136893.","DOI":"10.1109\/CVPR.2017.778"},{"key":"2555_CR31","unstructured":"Mangalam, K., Akshulakov, R., & Malik, J. (2023). Egoschema: A diagnostic benchmark for very long-form video language understanding. arXiv preprint arXiv:2308.09126"},{"key":"2555_CR32","doi-asserted-by":"crossref","unstructured":"Mullapudi, R.T., Chen, S., Zhang, K., Ramanan, D., & Fatahalian, K. (2019). Online model distillation for efficient video inference. In: Proceedings of the IEEE\/CVF International conference on computer vision, pp. 3573\u20133582.","DOI":"10.1109\/ICCV.2019.00367"},{"key":"2555_CR33","doi-asserted-by":"crossref","unstructured":"Mun, J., Hongsuck\u00a0Seo, P., Jung, I., & Han, B. (2017). Marioqa: Answering questions by watching gameplay videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2867\u20132875.","DOI":"10.1109\/ICCV.2017.312"},{"key":"2555_CR34","unstructured":"OpenAI (2024). Gpt-4o system card."},{"key":"2555_CR35","unstructured":"OpenAI T (2022). Chatgpt: Optimizing language models for dialogue. OpenAI."},{"key":"2555_CR36","first-page":"42748","volume":"36","author":"V Patraucean","year":"2023","unstructured":"Patraucean, V., Smaira, L., Gupta, A., Recasens, A., Markeeva, L., Banarse, D., Koppula, S., Malinowski, M., Yang, Y., Doersch, C., et al. (2023). Perception Test: A Diagnostic Benchmark for Multimodal Video Models. Advances in Neural Information Processing Systems, 36, 42748\u201342761.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2555_CR37","doi-asserted-by":"crossref","unstructured":"Pei, W., Baltrusaitis, T., Tax, D.M., & Morency, L.P. (2017). Temporal attention-gated model for robust sequence classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6730\u20136739.","DOI":"10.1109\/CVPR.2017.94"},{"key":"2555_CR38","doi-asserted-by":"crossref","unstructured":"Potapov, D., Douze, M., Harchaoui, Z., & Schmid, C. (2014). Category-specific video summarization. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13, Springer, pp. 540\u2013555.","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"2555_CR39","unstructured":"Rawal, R., Saifullah, K., Basri, R., Jacobs, D., Somepalli, G., & Goldstein, T. (2024). Cinepile: A long video question answering dataset and benchmark. arXiv preprint arXiv:2405.08813."},{"key":"2555_CR40","unstructured":"Reid, M., Savinov, N., Teplyashin, D., Lepikhin, D., Lillicrap, T., Alayrac, J.B., Soricut, R., Lazaridou, A., Firat, O., Schrittwieser, J., et\u00a0al. (2024). Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530."},{"key":"2555_CR41","doi-asserted-by":"crossref","unstructured":"Reimers, N., & Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982\u20133992.","DOI":"10.18653\/v1\/D19-1410"},{"key":"2555_CR42","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., & Hou, L. (2023). Timechat: A time-sensitive multimodal large language model for long video understanding. arXiv preprint arXiv:2312.02051.","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"2555_CR43","doi-asserted-by":"crossref","unstructured":"Shou, M.Z., Lei, S.W., Wang, W., Ghadiyaram, D., & Feiszli, M. (2021). Generic event boundary detection: A benchmark for event segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8075\u20138084.","DOI":"10.1109\/ICCV48922.2021.00797"},{"key":"2555_CR44","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., & Chang, S.F. (2016). Temporal action localization in untrimmed videos via multi-stage cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1049\u20131058.","DOI":"10.1109\/CVPR.2016.119"},{"key":"2555_CR45","doi-asserted-by":"crossref","unstructured":"Soldan, M., Pardo, A., Alc\u00e1zar, J.L., Caba, F., Zhao, C., Giancola, S., & Ghanem, B. (2022). Mad: A scalable dataset for language grounding in videos from movie audio descriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5026\u20135035.","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"2555_CR46","doi-asserted-by":"crossref","unstructured":"Song, E., Chai, W., Wang, G., Zhang, Y., Zhou, H., Wu, F., Guo, X., Ye, T., Lu, Y., Hwang, J.N., et\u00a0al. (2023). Moviechat: From dense token to sparse memory for long video understanding. arXiv preprint arXiv:2307.16449.","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"2555_CR47","first-page":"38032","volume":"35","author":"Y Sun","year":"2022","unstructured":"Sun, Y., Xue, H., Song, R., Liu, B., Yang, H., & Fu, J. (2022). Long-form Video-language Pre-training with Multimodal Temporal Contrastive Learning. Advances in neural information processing systems, 35, 38032\u201338045.","journal-title":"Advances in neural information processing systems"},{"key":"2555_CR48","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., & Fidler, S. (2016). Movieqa: Understanding stories in movies through question-answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4631\u20134640.","DOI":"10.1109\/CVPR.2016.501"},{"key":"2555_CR49","unstructured":"Team, I. (2023). Internlm: A multilingual language model with progressively enhanced capabilities."},{"key":"2555_CR50","doi-asserted-by":"crossref","unstructured":"Vicol, P., Tapaswi, M., Castrejon, L., & Fidler, S. (2018). Moviegraphs: Towards understanding human-centric situations from videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8581\u20138590.","DOI":"10.1109\/CVPR.2018.00895"},{"key":"2555_CR51","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., et\u00a0al. (2024a). Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191."},{"key":"2555_CR52","unstructured":"Wang, W., He, Z., Hong, W., Cheng, Y., Zhang, X., Qi, J., Huang, S., Xu, B., Dong, Y., Ding, M., et\u00a0al. (2024b). Lvbench: An extreme long video understanding benchmark. arXiv preprint arXiv:2406.08035."},{"key":"2555_CR53","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., & Gan, C. (2021). Star: A benchmark for situated reasoning in real-world videos. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"2555_CR54","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., & Krahenbuhl, P. (2021). Towards long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1884\u20131894.","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"2555_CR55","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., & Girshick, R. (2019). Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293.","DOI":"10.1109\/CVPR.2019.00037"},{"key":"2555_CR56","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Li, Y., Mangalam, K., Fan, H., Xiong, B., Malik, J., & Feichtenhofer, C. (2022). Memvit: Memory-augmented multiscale vision transformer for efficient long-term video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13587\u201313597.","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"2555_CR57","unstructured":"Wu, H., Li, D., Chen, B., & Li, J. (2024). Longvideobench: A benchmark for long-context interleaved video-language understanding. arXiv preprint arXiv:2407.15754."},{"key":"2555_CR58","doi-asserted-by":"crossref","unstructured":"Xiao, F., Kundu, K., Tighe, J., & Modolo, D. (2022). Hierarchical self-supervised representation learning for movie understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9727\u20139736.","DOI":"10.1109\/CVPR52688.2022.00950"},{"key":"2555_CR59","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., & Chua, T.S. (2021). Next-qa: Next phase of question-answering to explaining temporal actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9777\u20139786.","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"2555_CR60","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Huang, Q., Guo, L., Zhou, H., Zhou, B., & Lin, D. (2019). A graph-based framework to bridge movies and synopses. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4592\u20134601.","DOI":"10.1109\/ICCV.2019.00469"},{"key":"2555_CR61","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhao, Z., Xiao, J., Wu, F., Zhang, H., He, X., & Zhuang, Y. (2017). Video question answering via gradually refined attention over appearance and motion. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 1645\u20131653.","DOI":"10.1145\/3123266.3123427"},{"key":"2555_CR62","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., & Schmid, C. (2022). Zero-shot video question answering via frozen bidirectional language models. arXiv preprint arXiv:2206.08155."},{"key":"2555_CR63","doi-asserted-by":"crossref","unstructured":"Yang, L., Huang, Y., Sugano, Y., & Sato, Y. (2021). Stacked temporal attention: Improving first-person action recognition by emphasizing discriminative clips. arXiv preprint arXiv:2112.01038.","DOI":"10.5244\/C.35.64"},{"key":"2555_CR64","unstructured":"Ye, Q., Xu, H., Xu, G., Ye, J., Yan, M., Zhou, Y., Wang, J., Hu, A., Shi, P., Shi, Y., Jiang, C., Li, C., Xu, Y., Chen, H., Tian, J., Qi, Q., Zhang, J., & Huang, F. (2023a). mplug-owl: Modularization empowers large language models with multimodality. arXiv: 2304.14178."},{"key":"2555_CR65","unstructured":"Ye, Q., Xu, H., Xu, G., Ye, J., Yan, M., Zhou, Y., Wang, J., Hu, A., Shi, P., Shi, Y., et\u00a0al. (2023b). mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178."},{"key":"2555_CR66","unstructured":"Yu, S., Cho, J., Yadav, P., & Bansal, M. (2023). Self-chained image-language model for video localization and question answering. arXiv preprint\u00a0 arXiv:2305.06988"},{"key":"2555_CR67","doi-asserted-by":"publisher","first-page":"9127","DOI":"10.1609\/aaai.v33i01.33019127","volume":"33","author":"Z Yu","year":"2019","unstructured":"Yu, Z., Xu, D., Yu, J., Yu, T., Zhao, Z., Zhuang, Y., & Tao, D. (2019). Activitynet-qa: A Dataset for Understanding Complex Web Videos via Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 9127\u20139134.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2555_CR68","doi-asserted-by":"crossref","unstructured":"Yue, Z., Zhang, Q., Hu, A., Zhang, L., Wang, Z., & Jin, Q. (2023). Movie101: A new movie understanding benchmark. arXiv preprint arXiv:2305.12140.","DOI":"10.18653\/v1\/2023.acl-long.257"},{"key":"2555_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, C.L., Wu, J., & Li, Y. (2022). Actionformer: Localizing moments of actions with transformers. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part IV, Springer, pp. 492\u2013510.","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"2555_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, K., Chao, W.L., Sha, F., & Grauman, K. (2016). Video summarization with long short-term memory. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VII 14, Springer, pp. 766\u2013782.","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"2555_CR71","unstructured":"Zhang, P., Zhang, K., Li, B., Zeng, G., Yang, J., Zhang, Y., Wang, Z., Tan, H., Li, C., & Liu. Z. (2024a). Long context transfer from language to vision. arXiv preprint arXiv:2406.16852."},{"key":"2555_CR72","unstructured":"Zhang, Y., Wu, J., Li, W., Li, B., Ma, Z., Liu, Z., & Li, C. (2024b). Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02555-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02555-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02555-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T06:27:09Z","timestamp":1762928829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02555-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":72,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["2555"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02555-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]},"assertion":[{"value":"26 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2025","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The article has been corrected","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}