{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:47:21Z","timestamp":1773154041708,"version":"3.50.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729324","type":"print"},{"value":"9783031729331","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"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\/978-3-031-72933-1_16","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T12:02:53Z","timestamp":1727870573000},"page":"276-293","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Open Vocabulary Multi-label Video Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9068-7429","authenticated-orcid":false,"given":"Rohit","family":"Gupta","sequence":"first","affiliation":[]},{"given":"Mamshad Nayeem","family":"Rizve","sequence":"additional","affiliation":[]},{"given":"Jayakrishnan","family":"Unnikrishnan","sequence":"additional","affiliation":[]},{"given":"Ashish","family":"Tawari","sequence":"additional","affiliation":[]},{"given":"Son","family":"Tran","sequence":"additional","affiliation":[]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[]},{"given":"Benjamin","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Trishul","family":"Chilimbi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"16_CR1","unstructured":"Abu-El-Haija, S., et al.: YouTube-8m: a large-scale video classification benchmark (2016)"},{"key":"16_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: Proceedings of the International Conference on Machine Learning (ICML) (2021)"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58558-7_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Dave","year":"2020","unstructured":"Dave, A., Khurana, T., Tokmakov, P., Schmid, C., Ramanan, D.: TAO: a large-scale benchmark for tracking any object. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_26"},{"key":"16_CR4","unstructured":"Desai, K., Kaul, G., Aysola, Z., Johnson, J.: Redcaps: web-curated image-text data created by the people, for the people. arXiv preprint arXiv:2111.11431 (2021)"},{"key":"16_CR5","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., Tian, Y.: Improving clip training with language rewrites. In: NeurIPS (2023)"},{"key":"16_CR6","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2video: mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Gorti, S.K., et al.: X-pool: cross-modal language-video attention for text-video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5006\u20135015 (2022)","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, R., et al.: Class prototypes based contrastive learning for classifying multi-label and fine-grained educational videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19923\u201319933 (2023)","DOI":"10.1109\/CVPR52729.2023.01908"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Heilbron, F.C., Niebles, J.C.: Collecting and annotating human activities in web videos. In: Proceedings of International Conference on Multimedia Retrieval, ICMR 2014, pp. 377\u2013384. Association for Computing Machinery, New York (2014). https:\/\/doi.org\/10.1145\/2578726.2578775","DOI":"10.1145\/2578726.2578775"},{"key":"16_CR10","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"16_CR11","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 4904\u20134916. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/jia21b.html"},{"key":"16_CR12","unstructured":"Kaul, P., Xie, W., Zisserman, A.: Multi-modal classifiers for open-vocabulary object detection. In: International Conference on Machine Learning (2023)"},{"key":"16_CR13","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017)"},{"key":"16_CR14","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=e2TBb5y0yFf"},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.243. https:\/\/aclanthology.org\/2021.emnlp-main.243","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"16_CR16","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 12888\u201312900. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"16_CR17","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9694\u20139705 (2021)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 4582\u20134597. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.353. https:\/\/aclanthology.org\/2021.acl-long.353","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Lin, W., et al.: Match, expand and improve: unsupervised finetuning for zero-shot action recognition with language knowledge. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00267"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Lin, X., Petroni, F., Bertasius, G., Rohrbach, M., Chang, S.F., Torresani, L.: Learning to recognize procedural activities with distant supervision. arXiv preprint arXiv:2201.10990 (2022)","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"16_CR22","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. (2023)"},{"key":"16_CR23","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":"16_CR24","doi-asserted-by":"publisher","unstructured":"Liu, X., et al.: GPT understands, too. AI Open (2023). https:\/\/doi.org\/10.1016\/j.aiopen.2023.08.012. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2666651023000141","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: Clip4clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"16_CR26","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=jlAjNL8z5cs"},{"key":"16_CR27","unstructured":"Miech, A., Alayrac, J.B., Laptev, I., Sivic, J., Zisserman, A.: RareAct: a video dataset of unusual interactions. arxiv:2008.01018 (2020)"},{"key":"16_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"16_CR29","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-19772-7_1","volume-title":"ECCV 2022","author":"B Ni","year":"2022","unstructured":"Ni, B., et al.: Expanding language-image pretrained models for general video recognition. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13664, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_1"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., Farhadi, A.: What does a platypus look like? Generating customized prompts for zero-shot image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15691\u201315701 (2023)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"16_CR31","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":"16_CR32","doi-asserted-by":"crossref","unstructured":"Rasheed, H., khattak, M.U., Maaz, M., Khan, S., Khan, F.S.: Finetuned clip models are efficient video learners. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Roth, K., Kim, J.M., Koepke, A.S., Vinyals, O., Schmid, C., Akata, Z.: Waffling around for performance: visual classification with random words and broad concepts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15746\u201315757 (2023)","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"16_CR34","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"16_CR35","unstructured":"Schuhmann, C., et al.: LAION-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Shvetsova, N., Kukleva, A., Hong, X., Rupprecht, C., Schiele, B., Kuehne, H.: HowToCaption: prompting LLMs to transform video annotations at scale (2023)","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"16_CR39","unstructured":"Sun, X., Hu, P., Saenko, K.: DualCoop: fast adaptation to multi-label recognition with limited annotations. In: Advances in Neural Information Processing Systems, vol. 35, pp. 30569\u201330582 (2022)"},{"issue":"2","key":"16_CR40","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016). https:\/\/doi.org\/10.1145\/2812802","journal-title":"Commun. ACM"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Wasim, S.T., Naseer, M., Khan, S., Khan, F.S., Shah, M.: Vita-clip: video and text adaptive clip via multimodal prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23034\u201323044 (2023)","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"16_CR42","unstructured":"Weng, Z., Yang, X., Li, A., Wu, Z., Jiang, Y.G.: Open-VCLIP: transforming CLIP to an open-vocabulary video model via interpolated weight optimization. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 36978\u201336989. PMLR (2023). https:\/\/proceedings.mlr.press\/v202\/weng23b.html"},{"key":"16_CR43","unstructured":"Weng, Z., Yang, X., Li, A., Wu, Z., Jiang, Y.G.: Open-VCLIP: transforming clip to an open-vocabulary video model via interpolated weight optimization. In: ICML (2023)"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Challenges of zero-shot recognition with vision-language models: granularity and correctness (2023)","DOI":"10.1109\/CVPRW63382.2024.00189"},{"key":"16_CR46","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":"16_CR47","doi-asserted-by":"crossref","unstructured":"Yang, Y., Panagopoulou, A., Zhou, S., Jin, D., Callison-Burch, C., Yatskar, M.: Language in a bottle: language model guided concept bottlenecks for interpretable image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19187\u201319197 (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"16_CR48","unstructured":"Yao, L., et al.: Filip: fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)"},{"key":"16_CR49","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Misra, I., Kr\u00e4henb\u00fchl, P., Girdhar, R.: Learning video representations from large language models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00637"},{"issue":"9","key":"16_CR51","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: PointCLIP v2: prompting clip and GPT for powerful 3d open-world learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2639\u20132650 (2023)","DOI":"10.1109\/ICCV51070.2023.00249"}],"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\/978-3-031-72933-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:27:43Z","timestamp":1732840063000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72933-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"ISBN":["9783031729324","9783031729331"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72933-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,3]]},"assertion":[{"value":"3 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"}}]}}