{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:46:21Z","timestamp":1742913981094,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787913"},{"type":"electronic","value":"9789819787920"}],"license":[{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:00:00Z","timestamp":1731110400000},"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\/978-981-97-8792-0_24","type":"book-chapter","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T06:56:27Z","timestamp":1731048987000},"page":"342-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Focus on Subtle Actions: Semantic and Saliency Knowledge Co-Propagation Method for Weakly-Supervised Temporal Action Localization"],"prefix":"10.1007","author":[{"given":"Yuanjie","family":"Dang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Shou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruohong","family":"Huan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,9]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.visres.2013.07.016","volume":"91","author":"A Borji","year":"2013","unstructured":"Borji, A., Sihite, D.N., Itti, L.: What stands out in a scene? a study of human explicit saliency judgment. Vision. Res. 91, 62\u201377 (2013)","journal-title":"Vision. Res."},{"key":"24_CR2","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":"24_CR3","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":"24_CR4","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Wang, W., Cheng, M.M., Shen, J.: Shifting more attention to video salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8554\u20138564 (2019)","DOI":"10.1109\/CVPR.2019.00875"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, M., Xu, C.: Fine-grained temporal contrastive learning for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19999\u201320009 (2022)","DOI":"10.1109\/CVPR52688.2022.01937"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"He, B., Yang, X., Kang, L., Cheng, Z., Zhou, X., Shrivastava, A.: Asm-loc: Action-aware segment modeling for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13925\u201313935 (2022)","DOI":"10.1109\/CVPR52688.2022.01355"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Hong, F.T., Feng, J.C., Xu, D., Shan, Y., Zheng, W.S.: Cross-modal consensus network for weakly supervised temporal action localization. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1591\u20131599 (2021)","DOI":"10.1145\/3474085.3475298"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, L., Li, H.: Weakly supervised temporal action localization via representative snippet knowledge propagation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3272\u20133281 (2022)","DOI":"10.1109\/CVPR52688.2022.00327"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Islam, A., Long, C., Radke, R.: A hybrid attention mechanism for weakly-supervised temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1637\u20131645 (2021)","DOI":"10.1609\/aaai.v35i2.16256"},{"key":"24_CR11","unstructured":"Jiang, Y.G., Liu, J., Zamir, A.R., Toderici, G., Laptev, I., Shah, M., Sukthankar, R.: Thumos challenge: Action recognition with a large number of classes (2014)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Lee, P., Uh, Y., Byun, H.: Background suppression network for weakly-supervised temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11320\u201311327 (2020)","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Li, H., Chen, G., Li, G., Yu, Y.: Motion guided attention for video salient object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7274\u20137283 (2019)","DOI":"10.1109\/ICCV.2019.00737"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Hou, X., Koch, C., Rehg, J.M., Yuille, A.L.: The secrets of salient object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 280\u2013287 (2014)","DOI":"10.1109\/CVPR.2014.43"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Z., Liu, Q.: Actionness inconsistency-guided contrastive learning for weakly-supervised temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1513\u20131521 (2023)","DOI":"10.1609\/aaai.v37i2.25237"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Ge, Y., Yu, J., Chen, Z.: Forcing the whole video as background: An adversarial learning strategy for weakly temporal action localization. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5371\u20135379 (2022)","DOI":"10.1145\/3503161.3548300"},{"key":"24_CR17","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":"24_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wang, Z., Rong, S., Li, J., Zhang, Y.: Revisiting foreground and background separation in weakly-supervised temporal action localization: A clustering-based approach. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10433\u201310443 (2023)","DOI":"10.1109\/ICCV51070.2023.00957"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Luo, W., Zhang, T., Yang, W., Liu, J., Mei, T., Wu, F., Zhang, Y.: Action unit memory network for weakly supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9969\u20139979 (2021)","DOI":"10.1109\/CVPR46437.2021.00984"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Ma, J., Gorti, S.K., Volkovs, M., Yu, G.: Weakly supervised action selection learning in video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7587\u20137596 (2021)","DOI":"10.1109\/CVPR46437.2021.00750"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cholakkal, H., Khan, F.S., Shao, L.: 3c-net: Category count and center loss for weakly-supervised action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8679\u20138687 (2019)","DOI":"10.1109\/ICCV.2019.00877"},{"issue":"6","key":"24_CR22","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TPAMI.2013.242","volume":"36","author":"P Ochs","year":"2013","unstructured":"Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1187\u20131200 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: Videomoco: Contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-talc: Weakly-supervised temporal activity localization and classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 563\u2013579 (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"24_CR25","unstructured":"Qu, S., Chen, G., Li, Z., Zhang, L., Lu, F., Knoll, A.: Acm-net: Action context modeling network for weakly-supervised temporal action localization. arXiv:2104.02967 (2021)"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Ren, H., Yang, W., Zhang, T., Zhang, Y.: Proposal-based multiple instance learning for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2394\u20132404 (2023)","DOI":"10.1109\/CVPR52729.2023.00237"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Su, Y., Deng, J., Sun, R., Lin, G., Su, H., Wu, Q.: A unified transformer framework for group-based segmentation: Co-segmentation, co-saliency detection and video salient object detection. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3264883"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Tang, X., Fan, J., Luo, C., Zhang, Z., Zhang, M., Yang, Z.: Ddg-net: Discriminability-driven graph network for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6622\u20136632 (2023)","DOI":"10.1109\/ICCV51070.2023.00609"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Xiang, J., Dang, Y., Chen, P., Liang, R., Huan, R., Zhang, Z.: Spatial-angular quality-aware representation learning for blind light field image quality assessment. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1077\u20131087 (2023)","DOI":"10.1145\/3581783.3611927"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Yu, T., Chen, P., Dang, Y., Huan, R., Liang, R.: Multi-speed global contextual subspace matching for few-shot action recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2344\u20132352 (2023)","DOI":"10.1145\/3581783.3612380"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, B., Dang, Y., Chen, P., Liang, R., Gao, N., Huan, R., He, X.: Task-agnostic self-distillation for few-shot action recognition. In: International joint conference on artificial intelligence. Int. Joint Conf. Artif. Intell. (2024)","DOI":"10.24963\/ijcai.2024\/600"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cao, M., Yang, D., Chen, J., Zou, Y.: Cola: Weakly-supervised temporal action localization with snippet contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16010\u201316019 (2021)","DOI":"10.1109\/CVPR46437.2021.01575"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8792-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T07:11:07Z","timestamp":1731049867000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8792-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,9]]},"ISBN":["9789819787913","9789819787920"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8792-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,9]]},"assertion":[{"value":"9 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}