{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:10:26Z","timestamp":1783437026671,"version":"3.54.6"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734137","type":"print"},{"value":"9783031734144","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-73414-4_26","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:02:54Z","timestamp":1729789374000},"page":"453-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["LongVLM: Efficient Long Video Understanding via\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Yuetian","family":"Weng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfei","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohan","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"26_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"26_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: Your ViT but faster. In: ICLR (2022)"},{"key":"26_CR3","unstructured":"Brown, T., et al.: Language models are few-shot learners. NIPS 33, 1877\u20131901 (2020)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Buch, S., Eyzaguirre, C., Gaidon, A., Wu, J., Fei-Fei, L., Niebles, J.C.: Revisiting the\" video\" in video-language understanding. In: CVPR, pp. 2917\u20132927 (2022)","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"26_CR5","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL. Portland, OR (June 2011)"},{"key":"26_CR6","unstructured":"Chen, J., Zhu, D., Haydarov, K., Li, X., Elhoseiny, M.: Video chatCaptioner: towards the enriched spatiotemporal descriptions. arXiv preprint arXiv:2304.04227 (2023)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, F., Wang, X., Lei, J., Crandall, D., Bansal, M., Bertasius, G.: VindLU: a recipe for effective video-and-language pretraining. In: CVPR, pp. 10739\u201310750 (2023)","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"26_CR8","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality. https:\/\/vicuna.lmsys.org (2023)"},{"key":"26_CR9","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Victor\u00a0Escorcia, B.G., Niebles, J.C.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"26_CR12","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: CLIP2Video: mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Fernando, B., Gavves, E., Oramas, J., Ghodrati, A., Tuytelaars, T.: Rank pooling for action recognition. PAMI 39(4), 773\u2013787 (2016)","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"26_CR14","unstructured":"Fu, T.J., et al.: VIOLET: end-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681 (2021)"},{"issue":"11","key":"26_CR15","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization of actions with actoms. TPAMI 35(11), 2782\u20132795 (2013)","journal-title":"TPAMI"},{"key":"26_CR16","unstructured":"Gao, P., et\u00a0al.: LLaMA-Adapter v2: Parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Ghodrati, A., Bejnordi, B.E., Habibian, A.: FrameExit: conditional early exiting for efficient video recognition. In: CVPR, pp. 15608\u201315618 (2021)","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Gowda, S.N., Rohrbach, M., Sevilla-Lara, L.: Smart frame selection for action recognition. In: AAAI, vol.\u00a035, pp. 1451\u20131459 (2021)","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Han, M., Wang, Y., Li, Z., Yao, L., Chang, X., Qiao, Y.: HTML: hybrid temporal-scale multimodal learning framework for referring video object segmentation. In: ICCV, pp. 13414\u201313423 (2023)","DOI":"10.1109\/ICCV51070.2023.01234"},{"key":"26_CR20","unstructured":"Han, M., Yang, L., Chang, X., Wang, H.: Shot2Story20k: a new benchmark for comprehensive understanding of multi-shot videos. arXiv preprint arXiv:2311.17043 (2023)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Temporal alignment networks for long-term video. In: CVPR, pp. 2906\u20132916 (2022)","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Hussein, N., Gavves, E., Smeulders, A.W.: Timeception for complex action recognition. In: CVPR, pp. 254\u2013263 (2019)","DOI":"10.1109\/CVPR.2019.00034"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Kondratyuk, D., et al.: MoViNets: mobile video networks for efficient video recognition. In: CVPR, pp. 16020\u201316030 (2021)","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Korbar, B., Tran, D., Torresani, L.: Scsampler: sampling salient clips from video for efficient action recognition. In: ICCV, pp. 6232\u20136242 (2019)","DOI":"10.1109\/ICCV.2019.00633"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Lei, J., Li, L., Zhou, L., Gan, Z., Berg, T.L., Bansal, M., Liu, J.: Less is more: CLIPBERT for video-and-language learning via sparse sampling. In: CVPR, pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"26_CR26","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"26_CR27","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: UniFormerV2: unlocking the potential of image ViTs for video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1632\u20131643 (2023)","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Unmasked teacher: towards training-efficient video foundation models. arXiv preprint arXiv:2303.16058 (2023)","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"26_CR30","unstructured":"Li, K., et al.: UniFormer: unified transformer for efficient spatial-temporal representation learning. In: ICLR (2021)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: LAVENDER: unifying video-language understanding as masked language modeling. In: CVPR, pp. 23119\u201323129 (2023)","DOI":"10.1109\/CVPR52729.2023.02214"},{"key":"26_CR32","unstructured":"Liu, H., et al.: Video-teller: enhancing cross-modal generation with fusion and decoupling. arXiv preprint arXiv:2310.04991 (2023)"},{"key":"26_CR33","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Liu, R., Li, C., Ge, Y., Shan, Y., Li, T.H., Li, G.: One for all: video conversation is feasible without video instruction tuning. arXiv preprint arXiv:2309.15785 (2023)","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Lu, Y., Lu, C., Tang, C.K.: Online video object detection using association LSTM. In: ICCV, pp. 2344\u20132352 (2017)","DOI":"10.1109\/ICCV.2017.257"},{"key":"26_CR36","unstructured":"Luo, H., et al.: UniVL: a unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"26_CR37","unstructured":"Luo, R., et al.: Valley: video assistant with large language model enhanced ability. arXiv preprint arXiv:2306.07207 (2023)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"26_CR39","unstructured":"OpenAI: ChatGPT. https:\/\/openai.com\/blog\/chatgpt\/ (2023)"},{"key":"26_CR40","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. NIPS 35, 27730\u201327744 (2022)","journal-title":"NIPS"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., He, H., Liu, J., Cai, J.: Less is more: pay less attention in vision transformers. In: AAAI, vol.\u00a036, pp. 2035\u20132043 (2022)","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"26_CR42","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"26_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-030-58517-4_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Sener","year":"2020","unstructured":"Sener, F., Singhania, D., Yao, A.: Temporal aggregate representations for long-range video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 154\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_10"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. In: CVPR, pp. 18221\u201318232 (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"26_CR45","unstructured":"Taori, R., et al.: Stanford alpaca: An instruction-following llama model (2023)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Tian, Y., et al.: View while moving: efficient video recognition in long-untrimmed videos. In: ACMMM, pp. 173\u2013183 (2023)","DOI":"10.1145\/3581783.3612035"},{"key":"26_CR47","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"26_CR48","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"issue":"2","key":"26_CR49","first-page":"810","volume":"23","author":"L Wang","year":"2013","unstructured":"Wang, L., Qiao, Y., Tang, X.: Latent hierarchical model of temporal structure for complex activity classification. TIP 23(2), 810\u2013822 (2013)","journal-title":"TIP"},{"key":"26_CR50","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"issue":"11","key":"26_CR51","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. TPAMI 41(11), 2740\u20132755 (2018)","journal-title":"TPAMI"},{"key":"26_CR52","unstructured":"Wang, Y., et\u00a0al.: InternVideo: general video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"26_CR53","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"26_CR54","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: CVPR, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"26_CR55","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Krahenbuhl, P.: Towards long-form video understanding. In: CVPR, pp. 1884\u20131894 (2021)","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., et al.: MeMViT: memory-augmented multiscale vision transformer for efficient long-term video recognition. In: CVPR, pp. 13587\u201313597 (2022)","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"26_CR57","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: ACMMM, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"26_CR58","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: CVPR, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"26_CR59","first-page":"124","volume":"35","author":"A Yang","year":"2022","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Zero-shot video question answering via frozen bidirectional language models. NeurIPS 35, 124\u2013141 (2022)","journal-title":"NeurIPS"},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Yang, T., Chan, A.B.: Learning dynamic memory networks for object tracking. In: ECCV, pp. 152\u2013167 (2018)","DOI":"10.1007\/978-3-030-01240-3_10"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Yu, Z., Xu, D., Yu, J., Yu, T., Zhao, Z., Zhuang, Y., Tao, D.: ActivityNet-QA: a dataset for understanding complex web videos via question answering. In: AAAI, vol.\u00a033, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gupta, A., Zisserman, A.: Temporal query networks for fine-grained video understanding. In: CVPR, pp. 4486\u20134496 (2021)","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"26_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"26_CR64","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"26_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Luo, C., Tang, C., Chen, D., Codella, N., Zha, Z.J.: Streaming video model. In: CVPR, pp. 14602\u201314612 (2023)","DOI":"10.1109\/CVPR52729.2023.01403"},{"key":"26_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: ECCV, pp. 803\u2013818 (2018)","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"26_CR67","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (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\/978-3-031-73414-4_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:12:20Z","timestamp":1729789940000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73414-4_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031734137","9783031734144"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73414-4_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 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"}}]}}