{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T16:30:11Z","timestamp":1793377811744,"version":"4.5.0"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729881","type":"print"},{"value":"9783031729898","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72989-8_4","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"58-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":115,"title":["VideoAgent: Long-Form Video Understanding with\u00a0Large Language Model as\u00a0Agent"],"prefix":"10.1007","author":[{"given":"Xiaohan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Orr","family":"Zohar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serena","family":"Yeung-Levy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"4_CR1","unstructured":"Bai, Z., Wang, R., Chen, X.: Glance and focus: memory prompting for multi-event video question answering. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR2","unstructured":"Bala\u017eevi\u0107, I., Shi, Y., Papalampidi, P., Chaabouni, R., Koppula, S., H\u00e9naff, O.J.: Memory consolidation enables long-context video understanding. arXiv preprint arXiv:2402.05861 (2024)"},{"key":"4_CR3","unstructured":"Brohan, A., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818 (2023)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Buch, S., Eyzaguirre, C., Gaidon, A., Wu, J., Fei-Fei, L., Niebles, J.C.: Revisiting the \u201cvideo\" in video-language understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2917\u20132927 (2022)","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"4_CR5","unstructured":"Driess, D et\u00a0al.: PALM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"4_CR6","unstructured":"Gao, D., et al.: AssistGPT: a general multi-modal assistant that can plan, execute, inspect, and learn. arXiv preprint arXiv:2306.08640 (2023)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Gao, D., Zhou, L., Ji, L., Zhu, L., Yang, Y., Shou, M.Z.: 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 (2023)","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Kan, M.Y., Poria, S.: SAS Video-QA: self-adaptive sampling for efficient video question-answering (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.162"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Hong, W., et\u00a0al.: CogAgent: a visual language model for GUI agents. arXiv preprint arXiv:2312.08914 (2023)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"4_CR10","unstructured":"Hussein, N., Gavves, E., Smeulders, A.W.: VideoGraph: recognizing minutes-long human activities in videos. arXiv preprint arXiv:1905.05143 (2019)"},{"key":"4_CR11","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: OpenCLIP (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773, https:\/\/doi.org\/10.5281\/zenodo.5143773, if you use this software, please cite it as below","DOI":"10.5281\/zenodo.5143773"},{"key":"4_CR12","doi-asserted-by":"publisher","unstructured":"Islam, M.M., Bertasius, G.: Long movie clip classification with state-space video models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13695. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_6","DOI":"10.1007\/978-3-031-19833-5_6"},{"issue":"11","key":"4_CR13","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998). https:\/\/doi.org\/10.1109\/34.730558","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR14","unstructured":"Jiang, A.Q., et\u00a0al.: Mixtral Of Experts. arXiv preprint arXiv:2401.04088 (2024)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, C., Cao, X., Yuan, L.: Chat-UniVI: unified visual representation empowers large language models with image and video understanding (2023)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"4_CR16","unstructured":"Kim, S., Kim, J.H., Lee, J., Seo, M.: Semi-parametric video-grounded text generation. arXiv preprint arXiv:2301.11507 (2023)"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: clipBERT for video-and-language learning via sparse sampling. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"4_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"4_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"4_CR20","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding (2023)"},{"key":"4_CR21","unstructured":"Li, Y., Chen, X., Hu, B., Zhang, M.: LLMs meet long video: advancing long video comprehension with an interactive visual adapter in LLMs (2024)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-LLaVA: learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"4_CR23","unstructured":"Liu, H., Yan, W., Zaharia, M., Abbeel, P.: World model on million-length video and language with ringAttention. arXiv preprint arXiv:2402.08268 (2024)"},{"key":"4_CR24","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"4_CR25","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/tacl_a_00638","volume":"12","author":"NF Liu","year":"2024","unstructured":"Liu, N.F., et al.: Lost in the middle: how language models use long contexts. Trans. Assoc. Comput. Linguist. 12, 157\u2013173 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"4_CR26","unstructured":"Liu, X., et\u00a0al.: AgentBench: evaluating LLMS as agents. arXiv preprint arXiv:2308.03688 (2023)"},{"key":"4_CR27","unstructured":"Ma, C., et al.: AgentBoard: an analytical evaluation board of multi-turn LLM agents. arXiv preprint arXiv:2401.13178 (2024)"},{"key":"4_CR28","unstructured":"Ma, F., Jin, X., Wang, H., Xian, Y., Feng, J., Yang, Y.: VISTA-LLAMA: reliable video narrator via equal distance to visual tokens. arXiv preprint arXiv:2312.08870 (2023)"},{"key":"4_CR29","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. arXiv preprint arXiv:2308.09126 (2023)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Momeni, L., Caron, M., Nagrani, A., Zisserman, A., Schmid, C.: Verbs in Action: improving verb understanding in video-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15579\u201315591 (2023)","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"4_CR31","first-page":"2846","volume":"35","author":"E Nguyen","year":"2022","unstructured":"Nguyen, E., et al.: S4ND: modeling images and videos as multidimensional signals with state spaces. Adv. Neural. Inf. Process. Syst. 35, 2846\u20132861 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR32","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"4_CR33","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: Retrieving-to-Answer: zero-shot video question answering with frozen large language models (2023)","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Papalampidi, P., et al.: A simple recipe for contrastively pre-training video-first encoders beyond 16 frames. arXiv preprint arXiv:2312.07395 (2023)","DOI":"10.1109\/CVPR52733.2024.01364"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Park, J.S., O\u2019Brien, J., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative agents: Interactive simulacra of human behavior. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pp. 1\u201322 (2023)","DOI":"10.1145\/3586183.3606763"},{"key":"4_CR37","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: TimeChat: a time-sensitive multimodal large language model for long video understanding (2023)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"4_CR39","unstructured":"Romero, D., Solorio, T.: Question-instructed visual descriptions for zero-shot video question answering (2024)"},{"key":"4_CR40","unstructured":"Schick, T., et al.: Toolformer: language models can teach themselves to use tools. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR41","unstructured":"Shi, F., et al.: Large language models can be easily distracted by irrelevant context. In: International Conference on Machine Learning, pp. 31210\u201331227. PMLR (2023)"},{"key":"4_CR42","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. arXiv preprint arXiv:2307.16449 (2023)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"4_CR44","unstructured":"Sun, Q., et al.: EVA-CLIP-18B: scaling clip to 18 billion parameters. arXiv preprint arXiv:2402.04252 (2024)"},{"key":"4_CR45","first-page":"38032","volume":"35","author":"Y Sun","year":"2022","unstructured":"Sun, Y., Xue, H., Song, R., Liu, B., Yang, H., Fu, J.: Long-form video-language pre-training with multimodal temporal contrastive learning. Adv. Neural. Inf. Process. Syst. 35, 38032\u201338045 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: ViperGPT: visual inference via python execution for reasoning. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"4_CR47","unstructured":"Tay, Y., et al.: Long Range Arena: a benchmark for efficient transformers. arXiv preprint arXiv:2011.04006 (2020)"},{"key":"4_CR48","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"4_CR49","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"issue":"1","key":"4_CR50","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97\u2013136 (1980)","journal-title":"Cogn. Psychol."},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Q., Do, M.Q., Agarwal, N., Lee, K., Sun, C.: Vamos: Versatile action models for video understanding (2023)","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Bertasius, G., Oh, T.H., Gupta, A., Hoai, M., Torresani, L.: Supervoxel attention graphs for long-range video modeling. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 155\u2013166 (2021)","DOI":"10.1109\/WACV48630.2021.00020"},{"key":"4_CR53","unstructured":"Wang, Y., et\u00a0al.: InternVideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"4_CR54","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., et al.: 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 (2022)","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"4_CR56","doi-asserted-by":"crossref","unstructured":"Xiao, J., et al.: Contrastive video question answering via video graph transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13265\u201313280 (2023)","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: 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 (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"4_CR58","unstructured":"Xu, J., Lan, C., Xie, W., Chen, X., Lu, Y.: Retrieval-based video language model for efficient long video question answering (2023)"},{"key":"4_CR59","doi-asserted-by":"crossref","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Just Ask: learning to answer questions from millions of narrated videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1686\u20131697 (2021)","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"4_CR60","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Zero-shot video question answering via frozen bidirectional language models. In: NeurIPS (2022)"},{"key":"4_CR61","unstructured":"Yang, J., Zhu, Y., Wang, Y., Yi, R., Zadeh, A., Morency, L.P.: What gives the answer away? Question answering bias analysis on video QA datasets. arXiv preprint arXiv:2007.03626 (2020)"},{"key":"4_CR62","unstructured":"Yang, Z., Chen, G., Li, X., Wang, W., Yang, Y.: DoraemonGPT: Toward understanding dynamic scenes with large language models. arXiv preprint arXiv:2401.08392 (2024)"},{"key":"4_CR63","first-page":"20744","volume":"35","author":"S Yao","year":"2022","unstructured":"Yao, S., Chen, H., Yang, J., Narasimhan, K.: WebShop: towards scalable real-world web interaction with grounded language agents. Adv. Neural. Inf. Process. Syst. 35, 20744\u201320757 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR64","unstructured":"Yao, S., et al.: Tree of thoughts: Deliberate problem solving with large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"4_CR65","unstructured":"Yao, S., et al.: React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"Ye, Q., Xu, G., Yan, M., Xu, H., Qian, Q., Zhang, J., Huang, F.: HiTeA: hierarchical temporal-aware video-language pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15405\u201315416 (2023)","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2678\u20132687 (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"4_CR68","unstructured":"Yu, S., Cho, J., Yadav, P., Bansal, M.: Self-chained image-language model for video localization and question answering. NeurIPS (2023)"},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: A simple LLM framework for long-range video question-answering. arXiv preprint arXiv:2312.17235 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Misra, I., Kr\u00e4henb\u00fchl, P., Girdhar, R.: Learning video representations from large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6586\u20136597 (2023)","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"4_CR71","unstructured":"Zheng, L., et al.: Efficiently programming large language models using SGLang (2023)"},{"key":"4_CR72","unstructured":"Zhou, D., et\u00a0al.: Least-to-most prompting enables complex reasoning in large language models. In: ICLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72989-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:31:44Z","timestamp":1732955504000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72989-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031729881","9783031729898"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72989-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}