{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T16:17:04Z","timestamp":1788970624802,"version":"build-2803163510"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Committee","doi-asserted-by":"publisher","award":["JCYJ20241202130548062"],"award-info":[{"award-number":["JCYJ20241202130548062"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.cviu.2026.104876","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T15:39:39Z","timestamp":1784561979000},"page":"104876","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Open-vocabulary multi-label action recognition in movies via LLM-enhanced prompt tuning"],"prefix":"10.1016","volume":"271","author":[{"given":"Rongjiang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7573-4279","authenticated-orcid":false,"given":"Yuheng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104876_b1","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.cviu.2026.104876_b2","series-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b3","series-title":"Low-code LLM: visual programming over LLMs","author":"Cai","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b4","series-title":"Computer Vision \u2013 ECCV 2020: 16th European Conference","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.cviu.2026.104876_b5","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18888","article-title":"OST: Refining text knowledge with optimal spatio-temporal descriptor for general video recognition","author":"Chen","year":"2024"},{"key":"10.1016\/j.cviu.2026.104876_b6","series-title":"IEEE Winter Conference on Applications of Computer Vision","first-page":"151","article-title":"TAN: temporal aggregation network for dense multi-label action recognition","author":"Dai","year":"2019"},{"key":"10.1016\/j.cviu.2026.104876_b7","unstructured":"Dosovitskiy,\u00a0A., Beyer,\u00a0L., Kolesnikov,\u00a0A., Weissenborn,\u00a0D., Zhai,\u00a0X., Unterthiner,\u00a0T., Dehghani,\u00a0M., Minderer,\u00a0M., Heigold,\u00a0G., Gelly,\u00a0S., Uszkoreit,\u00a0J., Houlsby,\u00a0N., 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: 9th International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.cviu.2026.104876_b8","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"203","article-title":"X3D: expanding architectures for efficient video recognition","author":"Feichtenhofer","year":"2020"},{"key":"10.1016\/j.cviu.2026.104876_b9","series-title":"2019 IEEE\/CVF International Conference on Computer Vision","first-page":"6201","article-title":"SlowFast networks for video recognition","author":"Feichtenhofer","year":"2019"},{"key":"10.1016\/j.cviu.2026.104876_b10","series-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6047","article-title":"AVA: A video dataset of spatio-temporally localized atomic visual actions","author":"Gu","year":"2018"},{"key":"10.1016\/j.cviu.2026.104876_b11","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14953","article-title":"Visual programming: Compositional visual reasoning without training","author":"Gupta","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b12","series-title":"Computer Vision - ECCV 2020 - 16th European Conference","first-page":"709","article-title":"MovieNet: A holistic dataset for movie understanding","author":"Huang","year":"2020"},{"key":"10.1016\/j.cviu.2026.104876_b13","unstructured":"Huang,\u00a0X., Zhou,\u00a0H., Yao,\u00a0K., Han,\u00a0K., 2024. FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition. In: The Twelfth International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.cviu.2026.104876_b14","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia, MM","first-page":"4640","article-title":"Generating action-conditioned prompts for open-vocabulary video action recognition","author":"Jia","year":"2024"},{"key":"10.1016\/j.cviu.2026.104876_b15","series-title":"Computer Vision - ECCV 2022 - 17th European Conference","first-page":"105","article-title":"Prompting visual-language models for efficient video understanding","author":"Ju","year":"2022"},{"key":"10.1016\/j.cviu.2026.104876_b16","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18547","article-title":"VicTR: Video-conditioned text representations for activity recognition","author":"Kahatapitiya","year":"2024"},{"key":"10.1016\/j.cviu.2026.104876_b17","series-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","first-page":"25566","article-title":"Reformulating zero-shot action recognition for multi-label actions","author":"Kerrigan","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b18","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"1","article-title":"Walking and talking: A bilinear approach to multi-label action recognition","author":"Khamis","year":"2015"},{"key":"10.1016\/j.cviu.2026.104876_b19","series-title":"Computer Vision - ECCV 2024 - 18th European Conference","first-page":"74","article-title":"Leveraging temporal contextualization for video action recognition","author":"Kim","year":"2024"},{"key":"10.1016\/j.cviu.2026.104876_b20","unstructured":"Kingma,\u00a0D.P., Ba,\u00a0J., 2015. Adam: A Method for Stochastic Optimization. In: 3rd International Conference on Learning Representations, ICLR San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings."},{"key":"10.1016\/j.cviu.2026.104876_b21","unstructured":"Li,\u00a0J., Li,\u00a0D., Savarese,\u00a0S., Hoi,\u00a0S.C.H., 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In: International Conference on Machine Learning. ICML, pp. 19730\u201319742."},{"key":"10.1016\/j.cviu.2026.104876_b22","unstructured":"Li,\u00a0J., Li,\u00a0D., Xiong,\u00a0C., Hoi,\u00a0S.C.H., 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In: International Conference on Machine Learning. ICML, pp. 12888\u201312900."},{"key":"10.1016\/j.cviu.2026.104876_b23","series-title":"Align before fuse: Vision and language representation learning with momentum distillation","first-page":"9694","author":"Li","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b24","series-title":"Computer Vision - ECCV 2022 - 17th European Conference","first-page":"388","article-title":"Frozen CLIP models are efficient video learners","author":"Lin","year":"2022"},{"key":"10.1016\/j.cviu.2026.104876_b25","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2839","article-title":"MAtch, expand and improve: Unsupervised finetuning for zero-shot action recognition with language knowledge","author":"Lin","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b26","unstructured":"Menon,\u00a0S., Vondrick,\u00a0C., 2023. Visual Classification via Description from Large Language Models. In: The Eleventh International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.cviu.2026.104876_b27","series-title":"IEEE\/CVF International Conference on Computer Vision","first-page":"784","article-title":"Actor-agnostic multi-label action recognition with multi-modal query","author":"Mondal","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b28","series-title":"2021 IEEE\/CVF International Conference on Computer Vision","first-page":"8731","article-title":"Discriminative region-based multi-label zero-shot learning","author":"Narayan","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b29","series-title":"Computer Vision - ECCV 2022 - 17th European Conference","first-page":"1","article-title":"Expanding language-image pretrained models for general video recognition","volume":"vol. 13664","author":"Ni","year":"2022"},{"key":"10.1016\/j.cviu.2026.104876_b30","series-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","author":"Pan","year":"2022"},{"key":"10.1016\/j.cviu.2026.104876_b31","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b32","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6545","article-title":"Fine-tuned CLIP models are efficient video learners","author":"Rasheed","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b33","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","article-title":"ChatGPT-powered hierarchical comparisons for image classification","author":"Ren","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b34","series-title":"The truth of the F-measure","author":"Sasaki","year":"2007"},{"key":"10.1016\/j.cviu.2026.104876_b35","series-title":"Proceedings of the 2015 International Conference on the Theory of Information Retrieval","first-page":"349","article-title":"A relationship between the average precision and the area under the ROC curve","author":"Su","year":"2015"},{"key":"10.1016\/j.cviu.2026.104876_b36","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","article-title":"DualCoOp: Fast adaptation to multi-label recognition with limited annotations","author":"Sun","year":"2022"},{"key":"10.1016\/j.cviu.2026.104876_b37","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1460","article-title":"Modeling multi-label action dependencies for temporal action localization","author":"Tirupattur","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b38","doi-asserted-by":"crossref","first-page":"8483","DOI":"10.52202\/068431-0617","article-title":"Language models with image descriptors are strong few-shot video-language learners","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"10.1016\/j.cviu.2026.104876_b39","first-page":"5517","article-title":"M2-CLIP: A multimodal, multi-task adapting framework for video action recognition","volume":"38","author":"Wang","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104876_b40","series-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b41","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23034","article-title":"Vita-CLIP: Video and text adaptive CLIP via multimodal prompting","author":"Wasim","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b42","article-title":"Emergent abilities of large language models","volume":"2022","author":"Wei","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.cviu.2026.104876_b43","series-title":"International Conference on Machine Learning","first-page":"36978","article-title":"Open-VCLIP: Transforming CLIP to an open-vocabulary video model via interpolated weight optimization","volume":"vol. 202","author":"Weng","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b44","first-page":"2847","article-title":"Revisiting classifier: Transferring vision-language models for video recognition","volume":"37","author":"Wu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b45","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"7694","article-title":"LLM-grounder: Open-vocabulary 3D visual grounding with large language model as an agent","author":"Yang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104876_b46","series-title":"The Eleventh International Conference on Learning Representations","article-title":"AIM: Adapting image models for efficient video action recognition","author":"Yang","year":"2023"},{"key":"10.1016\/j.cviu.2026.104876_b47","first-page":"9689","article-title":"Building a multi-modal spatiotemporal expert for zero-shot action recognition with CLIP","volume":"39","author":"Yu","year":"2025"},{"key":"10.1016\/j.cviu.2026.104876_b48","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14625","article-title":"Multi-label activity recognition using activity-specific features and activity correlations","author":"Zhang","year":"2021"},{"key":"10.1016\/j.cviu.2026.104876_b49","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16816","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"issue":"9","key":"10.1016\/j.cviu.2026.104876_b50","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002432?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002432?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:49:32Z","timestamp":1788968972000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226002432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":50,"alternative-id":["S1077314226002432"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104876","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Open-vocabulary multi-label action recognition in movies via LLM-enhanced prompt tuning","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104876","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104876"}}