{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T02:16:13Z","timestamp":1784513773230,"version":"3.55.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729973","type":"print"},{"value":"9783031729980","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72998-0_1","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:01:58Z","timestamp":1727632918000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["ST-LLM: Large Language Models Are Effective Temporal Learners"],"prefix":"10.1007","author":[{"given":"Ruyang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixiao","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"1_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"1_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1_CR3","unstructured":"Anil, R., et\u00a0al.: PaLM 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"1_CR4","unstructured":"Awadalla, A., et\u00a0al.: Openflamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"1_CR6","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"1_CR7","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"1_CR8","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"1_CR9","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Escorcia, V., Ghanem, B., Carlos\u00a0Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1_CR12","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"1_CR13","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality (2023). See https:\/\/vicunalmsys.org. Accessed 14 Apr 2023"},{"key":"1_CR14","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. arxiv$$.$$ Preprint posted online on June 15, 2023 (2023)"},{"key":"1_CR15","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1_CR16","unstructured":"Driess, D., et\u00a0al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The something something video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"1_CR18","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021)"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, X., Chen, H., Song, Z., Zhu, W.: Vtimellm: empower llm to grasp video moments. arXiv preprint arXiv:2311.18445 (2023)","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"1_CR20","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. arXiv preprint arXiv:2311.08046 (2023)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"1_CR21","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"1_CR22","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726 (2023)"},{"key":"1_CR23","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":"1_CR24","unstructured":"Li, K., et al.: Videochat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Mvbench: a comprehensive multi-modal video understanding benchmark. arXiv preprint arXiv:2311.17005 (2023)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"1_CR26","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":"1_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: Llama-vid: an image is worth 2 tokens in large language models. arXiv preprint arXiv:2311.17043 (2023)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"1_CR28","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":"1_CR29","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Liu, R., Huang, J., Li, G., Feng, J., Wu, X., Li, T.H.: Revisiting temporal modeling for clip-based image-to-video knowledge transferring. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6555\u20136564 (2023)","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"1_CR31","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":"1_CR32","unstructured":"Luo, R., et al.: Valley: video assistant with large language model enhanced ability. arXiv preprint arXiv:2306.07207 (2023)"},{"key":"1_CR33","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":"1_CR34","unstructured":"OpenAI: Chatgpt (2023). https:\/\/openai.com\/blog\/chatgpt"},{"key":"1_CR35","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":"1_CR36","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"1_CR37","unstructured":"Peng, Z., Dong, L., Bao, H., Ye, Q., Wei, F.: Beit v2: masked image modeling with vector-quantized visual tokenizers. arXiv preprint arXiv:2208.06366 (2022)"},{"key":"1_CR38","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":"1_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"1_CR40","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following llama model (2023)"},{"key":"1_CR41","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1_CR42","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"1_CR43","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Wu, Z., Yao, T., Fu, Y., Jiang, Y.G.: Deep learning for video classification and captioning. In: Frontiers of Multimedia Research, pp. 3\u201329. ACM (2017)","DOI":"10.1145\/3122865.3122867"},{"key":"1_CR46","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":"1_CR47","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"1_CR48","unstructured":"Xue, H., et al.: CLIP-VIP: adapting pre-trained image-text model to video-language representation alignment. arXiv preprint arXiv:2209.06430 (2022)"},{"key":"1_CR49","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. Adv. Neural Inf. Process. Syst. 35, 124\u2013141 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1_CR50","unstructured":"Ye, Q., et\u00a0al.: Mplug-owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"1_CR51","unstructured":"Yi, K., et al.: Clevrer: collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442 (2019)"},{"key":"1_CR52","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":"1_CR53","unstructured":"Zhang, R., et al.: Llama-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"1_CR54","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\/978-3-031-72998-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:28:47Z","timestamp":1732829327000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72998-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031729973","9783031729980"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72998-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}