{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T19:16:21Z","timestamp":1783192581916,"version":"3.54.6"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["020214380140"],"award-info":[{"award-number":["020214380140"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008048","name":"Nanjing University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008048","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160900"],"award-info":[{"award-number":["2022ZD0160900"]}],"id":[{"id":"10.13039\/501100012166","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":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104825","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T07:06:18Z","timestamp":1779951978000},"page":"104825","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Aligning video regions with action descriptions for open-vocabulary spatio-temporal action detection"],"prefix":"10.1016","volume":"270","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1028-6919","authenticated-orcid":false,"given":"Tao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3989-9963","authenticated-orcid":false,"given":"Shuqiu","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104825_b1","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.cviu.2026.104825_b2","doi-asserted-by":"crossref","first-page":"33781","DOI":"10.52202\/068431-2448","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume":"35","author":"Bangalath","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104825_b3","series-title":"Exploiting VLM localizability and semantics for open vocabulary action detection","author":"Bao","year":"2024"},{"key":"10.1016\/j.cviu.2026.104825_b4","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.cviu.2026.104825_b5","series-title":"A short note about kinetics-600","author":"Carreira","year":"2018"},{"key":"10.1016\/j.cviu.2026.104825_b6","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Xie, E., Ge, C., Wu, J., Ma, L., Shen, J., Luo, P., 2021. Watch only once: An end-to-end video action detection framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8178\u20138187.","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"10.1016\/j.cviu.2026.104825_b7","series-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"issue":"240","key":"10.1016\/j.cviu.2026.104825_b8","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cviu.2026.104825_b9","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C., 2021. Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6824\u20136835.","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"10.1016\/j.cviu.2026.104825_b10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K., 2019. Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6202\u20136211.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"10.1016\/j.cviu.2026.104825_b11","series-title":"European Conference on Computer Vision","first-page":"701","article-title":"Promptdet: Towards open-vocabulary detection using uncurated images","author":"Feng","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b12","series-title":"Towards open vocabulary object detection without human-provided bounding boxes","author":"Gao","year":"2021"},{"key":"10.1016\/j.cviu.2026.104825_b13","series-title":"CVPR","first-page":"244","article-title":"Video action transformer network","author":"Girdhar","year":"2019"},{"key":"10.1016\/j.cviu.2026.104825_b14","doi-asserted-by":"crossref","unstructured":"Gritsenko, A.A., Xiong, X., Djolonga, J., Dehghani, M., Sun, C., Lucic, M., Schmid, C., Arnab, A., 2024. End-to-end spatio-temporal action localisation with video transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18373\u201318383.","DOI":"10.1109\/CVPR52733.2024.01739"},{"key":"10.1016\/j.cviu.2026.104825_b15","series-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"10.1016\/j.cviu.2026.104825_b16","doi-asserted-by":"crossref","unstructured":"Gu, C., Sun, C., Ross, D.A., Vondrick, C., Pantofaru, C., Li, Y., Vijayanarasimhan, S., Toderici, G., Ricco, S., Sukthankar, R., et al., 2018. Ava: A video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6047\u20136056.","DOI":"10.1109\/CVPR.2018.00633"},{"key":"10.1016\/j.cviu.2026.104825_b17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R., 2017. Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"10.1016\/j.cviu.2026.104825_b18","series-title":"ICCV","first-page":"5823","article-title":"Tube convolutional neural network (T-CNN) for action detection in videos","author":"Hou","year":"2017"},{"key":"10.1016\/j.cviu.2026.104825_b19","series-title":"Spatio-temporal context prompting for zero-shot action detection","author":"Huang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104825_b20","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.J., 2013. Towards understanding action recognition. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3192\u20133199.","DOI":"10.1109\/ICCV.2013.396"},{"key":"10.1016\/j.cviu.2026.104825_b21","series-title":"Generating action-conditioned prompts for open-vocabulary video action recognition","author":"Jia","year":"2023"},{"key":"10.1016\/j.cviu.2026.104825_b22","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.cviu.2026.104825_b23","series-title":"European Conference on Computer Vision","first-page":"105","article-title":"Prompting visual-language models for efficient video understanding","author":"Ju","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b24","series-title":"ICCV","first-page":"4415","article-title":"Action tubelet detector for spatio-temporal action localization","author":"Kalogeiton","year":"2017"},{"key":"10.1016\/j.cviu.2026.104825_b25","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N., 2021. Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1780\u20131790.","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"10.1016\/j.cviu.2026.104825_b26","series-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"10.1016\/j.cviu.2026.104825_b27","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T., 2014. Referitgame: Referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. EMNLP, pp. 787\u2013798.","DOI":"10.3115\/v1\/D14-1086"},{"key":"10.1016\/j.cviu.2026.104825_b28","series-title":"You only watch once: A unified cnn architecture for real-time spatiotemporal action localization","author":"K\u00f6p\u00fckl\u00fc","year":"2019"},{"key":"10.1016\/j.cviu.2026.104825_b29","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104825_b30","series-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","author":"Kuo","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b31","doi-asserted-by":"crossref","unstructured":"Li, F., Liu, W., Chen, J., Zhang, R., Wang, Y., Zhong, X., Wang, Z., 2025. Anomize: Better open vocabulary video anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 29203\u201329212.","DOI":"10.1109\/CVPR52734.2025.02719"},{"key":"10.1016\/j.cviu.2026.104825_b32","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XVI 16","first-page":"68","article-title":"Actions as moving points","author":"Li","year":"2020"},{"key":"10.1016\/j.cviu.2026.104825_b33","doi-asserted-by":"crossref","unstructured":"Li, L.H., Zhang, P., Zhang, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., Hwang, J.-N., et al., 2022. Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10965\u201310975.","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"10.1016\/j.cviu.2026.104825_b34","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P., 2017. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"10.1016\/j.cviu.2026.104825_b35","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.cviu.2026.104825_b36","series-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104825_b37","doi-asserted-by":"crossref","unstructured":"Ma, Y., Xu, G., Sun, X., Yan, M., Zhang, J., Ji, R., 2022. X-clip: End-to-end multi-grained contrastive learning for video-text retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia. pp. 638\u2013647.","DOI":"10.1145\/3503161.3547910"},{"key":"10.1016\/j.cviu.2026.104825_b38","doi-asserted-by":"crossref","unstructured":"Momeni, L., Caron, M., Nagrani, A., Zisserman, A., Schmid, C., 2023. Verbs in action: Improving verb understanding in video-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15579\u201315591.","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"10.1016\/j.cviu.2026.104825_b39","doi-asserted-by":"crossref","unstructured":"Ntinou, I., Sanchez, E., Tzimiropoulos, G., 2024. Multiscale vision transformers meet bipartite matching for efficient single-stage action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18827\u201318836.","DOI":"10.1109\/CVPR52733.2024.01781"},{"key":"10.1016\/j.cviu.2026.104825_b40","doi-asserted-by":"crossref","unstructured":"Pan, J., Chen, S., Shou, M.Z., Liu, Y., Shao, J., Li, H., 2021. Actor-context-actor relation network for spatio-temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 464\u2013474.","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"10.1016\/j.cviu.2026.104825_b41","doi-asserted-by":"crossref","first-page":"26462","DOI":"10.52202\/068431-1919","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume":"35","author":"Pan","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104825_b42","series-title":"European Conference on Computer Vision","first-page":"744","article-title":"Multi-region two-stream R-CNN for action detection","author":"Peng","year":"2016"},{"key":"10.1016\/j.cviu.2026.104825_b43","series-title":"ICML","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.2026.104825_b44","doi-asserted-by":"crossref","unstructured":"Rasheed, H., Khattak, M.U., Maaz, M., Khan, S., Khan, F.S., 2023. Fine-tuned clip models are efficient video learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6545\u20136554.","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"10.1016\/j.cviu.2026.104825_b45","series-title":"Open-vocabulary temporal action detection with off-the-shelf image-text features","author":"Rathod","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b46","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104825_b47","doi-asserted-by":"crossref","unstructured":"Shang, X., Di, D., Xiao, J., Cao, Y., Yang, X., Chua, T.-S., 2019. Annotating objects and relations in user-generated videos. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval. pp. 279\u2013287.","DOI":"10.1145\/3323873.3325056"},{"key":"10.1016\/j.cviu.2026.104825_b48","series-title":"CVPR","first-page":"11987","article-title":"Tacnet: Transition-aware context network for spatio-temporal action detection","author":"Song","year":"2019"},{"key":"10.1016\/j.cviu.2026.104825_b49","series-title":"UCF101: a dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"10.1016\/j.cviu.2026.104825_b50","doi-asserted-by":"crossref","unstructured":"Sui, L., Zhang, C.-L., Gu, L., Han, F., 2023. A simple and efficient pipeline to build an end-to-end spatial-temporal action detector. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 5999\u20136008.","DOI":"10.1109\/WACV56688.2023.00594"},{"key":"10.1016\/j.cviu.2026.104825_b51","series-title":"ECCV","first-page":"318","article-title":"Actor-centric relation network","author":"Sun","year":"2018"},{"issue":"12","key":"10.1016\/j.cviu.2026.104825_b52","doi-asserted-by":"crossref","first-page":"8238","DOI":"10.1109\/TCSVT.2021.3085907","article-title":"Human-centric spatio-temporal video grounding with visual transformers","volume":"32","author":"Tang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.cviu.2026.104825_b53","series-title":"European Conference on Computer Vision","first-page":"71","article-title":"Asynchronous interaction aggregation for action detection","author":"Tang","year":"2020"},{"key":"10.1016\/j.cviu.2026.104825_b54","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2021.103242","article-title":"Long term spatio-temporal modeling for action detection","volume":"210","author":"Tapaswi","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cviu.2026.104825_b55","doi-asserted-by":"crossref","first-page":"10078","DOI":"10.52202\/068431-0732","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104825_b56","article-title":"Paxion: Patching action knowledge in video-language foundation models","volume":"36","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104825_b57","series-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023"},{"key":"10.1016\/j.cviu.2026.104825_b58","series-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"10.1016\/j.cviu.2026.104825_b59","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","author":"Weng","year":"2023"},{"key":"10.1016\/j.cviu.2026.104825_b60","doi-asserted-by":"crossref","unstructured":"Wu, T., Cao, M., Gao, Z., Wu, G., Wang, L., 2023. STMixer: A One-Stage Sparse Action Detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14720\u201314729.","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"10.1016\/j.cviu.2026.104825_b61","doi-asserted-by":"crossref","unstructured":"Wu, C.-Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R., 2019. Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 284\u2013293.","DOI":"10.1109\/CVPR.2019.00037"},{"key":"10.1016\/j.cviu.2026.104825_b62","series-title":"European Conference on Computer Vision","first-page":"440","article-title":"Context-aware rcnn: A baseline for action detection in videos","author":"Wu","year":"2020"},{"key":"10.1016\/j.cviu.2026.104825_b63","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhang, W., Jin, S., Liu, W., Loy, C.C., 2023. Aligning bag of regions for open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15254\u201315264.","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"10.1016\/j.cviu.2026.104825_b64","doi-asserted-by":"crossref","unstructured":"Wu, P., Zhou, X., Pang, G., Sun, Y., Liu, J., Wang, P., Zhang, Y., 2024a. Open-vocabulary video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18297\u201318307.","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"10.1016\/j.cviu.2026.104825_b65","doi-asserted-by":"crossref","unstructured":"Wu, P., Zhou, X., Pang, G., Yang, Z., Yan, Q., Wang, P., Zhang, Y., 2024b. Weakly supervised video anomaly detection and localization with spatio-temporal prompts. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 9301\u20139310.","DOI":"10.1145\/3664647.3681442"},{"key":"10.1016\/j.cviu.2026.104825_b66","series-title":"Videoclip: Contrastive pre-training for zero-shot video-text understanding","author":"Xu","year":"2021"},{"key":"10.1016\/j.cviu.2026.104825_b67","doi-asserted-by":"crossref","unstructured":"Yang, X., Yang, X., Liu, M.-Y., Xiao, F., Davis, L.S., Kautz, J., 2019. Step: Spatio-temporal progressive learning for video action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 264\u2013272.","DOI":"10.1109\/CVPR.2019.00035"},{"key":"10.1016\/j.cviu.2026.104825_b68","doi-asserted-by":"crossref","first-page":"9125","DOI":"10.52202\/068431-0663","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104825_b69","series-title":"European Conference on Computer Vision","first-page":"106","article-title":"Open-vocabulary detr with conditional matching","author":"Zang","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b70","series-title":"CVPR","first-page":"14393","article-title":"Open-vocabulary object detection using captions","author":"Zareian","year":"2021"},{"key":"10.1016\/j.cviu.2026.104825_b71","series-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b72","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhao, Z., Zhao, Y., Wang, Q., Liu, H., Gao, L., 2020. Where does it exist: Spatio-temporal video grounding for multi-form sentences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10668\u201310677.","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"10.1016\/j.cviu.2026.104825_b73","doi-asserted-by":"crossref","unstructured":"Zhao, J., 2026. ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 308\u2013317.","DOI":"10.1109\/WACV61042.2026.00038"},{"key":"10.1016\/j.cviu.2026.104825_b74","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhang, Y., Li, X., Chen, H., Shuai, B., Xu, M., Liu, C., Kundu, K., Xiong, Y., Modolo, D., et al., 2022. Tuber: Tubelet transformer for video action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13598\u201313607.","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"10.1016\/j.cviu.2026.104825_b75","series-title":"European Conference on Computer Vision","first-page":"159","article-title":"Exploiting unlabeled data with vision and language models for object detection","author":"Zhao","year":"2022"},{"key":"10.1016\/j.cviu.2026.104825_b76","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., Li, C., Codella, N., Li, L.H., Zhou, L., Dai, X., Yuan, L., Li, Y., et al., 2022. Regionclip: Region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16793\u201316803.","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"10.1016\/j.cviu.2026.104825_b77","series-title":"European Conference on Computer Vision","first-page":"350","article-title":"Detecting twenty-thousand classes using image-level supervision","author":"Zhou","year":"2022"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S107731422600192X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S107731422600192X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T18:56:22Z","timestamp":1783191382000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S107731422600192X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":77,"alternative-id":["S107731422600192X"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104825","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Aligning video regions with action descriptions for open-vocabulary spatio-temporal action detection","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104825","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":"104825"}}