{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:05:11Z","timestamp":1757624711906,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819500994"},{"type":"electronic","value":"9789819501007"}],"license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-0100-7_16","type":"book-chapter","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T04:37:25Z","timestamp":1755491845000},"page":"248-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["STA-TAD: Spatial-Temporal Adapter on\u00a0ViT for\u00a0Temporal Action Detection"],"prefix":"10.1007","author":[{"given":"Zhongguang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingwei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1130\u20131139 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"16_CR2","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"16_CR3","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"16_CR4","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_CR5","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014). http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"16_CR6","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint: arXiv:1705.06950 (2017)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Kim, H.J., Hong, J.H., Kong, H., Lee, S.W.: TE-TAD: towards full end-to-end temporal action detection via time-aligned coordinate expression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18837\u201318846 (2024)","DOI":"10.1109\/CVPR52733.2024.01782"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. arXiv preprint: arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Lin, C., et al. Learning salient boundary feature for anchor-free temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3320\u20133329 (2021)","DOI":"10.1109\/CVPR46437.2021.00333"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999\u20133007 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wang, Z.: Progressive boundary refinement network for temporal action detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11612\u201311619 (2020)","DOI":"10.1609\/aaai.v34i07.6829"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, C.L., Zhao, C., Ghanem, B.: End-to-end temporal action detection with 1B parameters across 1000 frames. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18591\u201318601 (2024)","DOI":"10.1109\/CVPR52733.2024.01759"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Ma, L., Zhang, Y., Liu, W., Chang, S.F.: Multi-granularity generator for temporal action proposal. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3604\u20133613 (2019)","DOI":"10.1109\/CVPR.2019.00372"},{"issue":"6","key":"16_CR16","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Shao, J., Wang, X., Quan, R., Zheng, J., Yang, J., Yang, Y.: Action sensitivity learning for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13457\u201313469 (2023)","DOI":"10.1109\/ICCV51070.2023.01238"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Shi, D., Zhong, Y., Cao, Q., Ma, L., Li, J., Tao, D.: TriDet: temporal action detection with relative boundary modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18857\u201318866 (2023)","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Shi, D., et al.: ReAct: temporal action detection with relational queries. In: European Conference on Computer Vision, pp. 105\u2013121. Springer (2022)","DOI":"10.1007\/978-3-031-20080-9_7"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Tan, J., Tang, J., Wang, L., Wu, G.: Relaxed transformer decoders for direct action proposal generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13526\u201313535 (2021)","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"16_CR21","unstructured":"Tan, J., Zhao, X., Shi, X., Kang, B., Wang, L.: PointTAD: multi-label temporal action detection with learnable query points. In: Advances in Neural Information Processing Systems, vol. 35, pp. 15268\u201315280 (2022)"},{"key":"16_CR22","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems, vol. 35, 10078\u201310093 (2022)"},{"key":"16_CR23","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Wang, B., Zhao, Y., Yang, L., Long, T., Li, X.: Temporal action localization in the deep learning era: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: InternVideo2: scaling foundation models for multimodal video understanding. In: European Conference on Computer Vision, pp. 396\u2013416. Springer (2024)","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"16_CR27","unstructured":"Wang, Y., et\u00a0al.: InternVideo: general video foundation models via generative and discriminative learning. arXiv preprint: arXiv:2212.03191 (2022)"},{"key":"16_CR28","doi-asserted-by":"publisher","first-page":"70477","DOI":"10.1109\/ACCESS.2020.2986861","volume":"8","author":"H Xia","year":"2020","unstructured":"Xia, H., Zhan, Y.: A survey on temporal action localization. IEEE Access 8, 70477\u201370487 (2020)","journal-title":"IEEE Access"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhao, C., Rojas, D.S., Thabet, A., Ghanem, B.: G-TAD: sub-graph localization for temporal action detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10156\u201310165 (2020)","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Yang, M., Gao, H., Guo, P., Wang, L.: Adapting short-term transformers for action detection in untrimmed videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18570\u201318579 (2024)","DOI":"10.1109\/CVPR52733.2024.01757"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Zeng, R., et al.: Graph convolutional networks for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7094\u20137103 (2019)","DOI":"10.1109\/ICCV.2019.00719"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, C.L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: European Conference on Computer Vision, pp. 492\u2013510. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, C., Liu, S., Mangalam, K., Ghanem, B.: Re2TAl: rewiring pretrained video backbones for reversible temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10637\u201310647 (2023)","DOI":"10.1109\/CVPR52729.2023.01025"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, C., Ramazanova, M., Xu, M., Ghanem, B.: SegTAD: precise temporal action detection via semantic segmentation. In: European Conference on Computer Vision, pp. 576\u2013593. Springer (2022)","DOI":"10.1007\/978-3-031-25069-9_37"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, C., Thabet, A.K., Ghanem, B.: Video self-stitching graph network for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13658\u201313667 (2021)","DOI":"10.1109\/ICCV48922.2021.01340"},{"key":"16_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/978-3-030-58598-3_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Zhao","year":"2020","unstructured":"Zhao, P., Xie, L., Ju, C., Zhang, Y., Wang, Y., Tian, Q.: Bottom-up temporal action localization with mutual regularization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 539\u2013555. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_32"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wang, D., Zhao, X.: Movement enhancement toward multi-scale video feature representation for temporal action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13555\u201313564 (2023)","DOI":"10.1109\/ICCV51070.2023.01247"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Tang, W., Wang, L., Zheng, N., Hua, G.: Enriching local and global contexts for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13516\u201313525 (2021)","DOI":"10.1109\/ICCV48922.2021.01326"}],"container-title":["Lecture Notes in Computer Science","Computer Animation and Social Agents"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0100-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T15:17:10Z","timestamp":1757431030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0100-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"ISBN":["9789819500994","9789819501007"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0100-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"19 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Animation and Social Agents","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"casa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/casa2025.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}