{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T03:37:57Z","timestamp":1776310677570,"version":"3.50.1"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T00:00:00Z","timestamp":1724976000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T00:00:00Z","timestamp":1724976000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the University Synergy Innovation Program of Anhui Province, China","award":["GXXT-2022-033"],"award-info":[{"award-number":["GXXT-2022-033"]}]},{"name":"the University Synergy Innovation Program of Anhui Province, China","award":["GXXT-2022-033"],"award-info":[{"award-number":["GXXT-2022-033"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00530-024-01445-2","type":"journal-article","created":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T10:02:47Z","timestamp":1725012167000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Weakly-supervised temporal action localization using multi-branch attention weighting"],"prefix":"10.1007","volume":"30","author":[{"given":"Mengxue","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangzhen","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangjun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,30]]},"reference":[{"key":"1445_CR1","doi-asserted-by":"publisher","first-page":"5410","DOI":"10.1109\/TMM.2023.3333206","volume":"26","author":"Y Hu","year":"2024","unstructured":"Hu, Y., Gao, J., Dong, J., Fan, B., Liu, H.: Exploring rich semantics for open-set action recognition. IEEE Trans. Multimedia 26, 5410\u20135421 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3333206","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"1445_CR2","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.1109\/TCSVT.2021.3075470","volume":"32","author":"J Gao","year":"2022","unstructured":"Gao, J., Xu, C.: Learning video moment retrieval without a single annotated video. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1646\u20131657 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3075470","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"10","key":"1445_CR3","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TPAMI.2020.2985708","volume":"43","author":"J Gao","year":"2021","unstructured":"Gao, J., Zhang, T., Xu, C.: Learning to model relationships for zero-shot video classification. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3476\u20133491 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2985708","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1445_CR4","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","volume":"118","author":"G Yao","year":"2019","unstructured":"Yao, G., Lei, T., Zhong, J.: A review of convolutional-neural-network-based action recognition. Pattern Recognit. Lett. 118, 14\u201322 (2019). https:\/\/doi.org\/10.1016\/j.patrec.2018.05.018","journal-title":"Pattern Recognit. Lett."},{"key":"1445_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108725","author":"K Xia","year":"2022","unstructured":"Xia, K., Wang, L., Zhou, S., Hua, G., Tang, W.: Dual relation network for temporal action localization. Pattern Recognit. (2022). https:\/\/doi.org\/10.1016\/j.patcog.2022.108725","journal-title":"Pattern Recognit."},{"key":"1445_CR6","doi-asserted-by":"crossref","unstructured":"Zeng, R., Huang, W., Tan, M., Rong, Y., Zhao, P., Huang, J., Gan, C.: 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":"1445_CR7","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":"1445_CR8","unstructured":"Nawhal, M., Mori, G.: Activity graph transformer for temporal action localization. arXiv preprint arXiv:2101.08540 (2021)"},{"key":"1445_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, C., Yang, J., Li, Z., Guo, C.: Boundary-aware proposal generation method for temporal action localization. arXiv preprint arXiv:2309.13810 (2023)","DOI":"10.1109\/VCIP59821.2023.10402685"},{"key":"1445_CR10","doi-asserted-by":"publisher","unstructured":"Yan, X., Zheng, Z., Gao, Y.: Improved weakly supervised image semantic segmentation method based on sec. In: Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2022, vol. 153. pp. 621\u2013628 (2023). https:\/\/doi.org\/10.1007\/978-3-031-20738-9_71","DOI":"10.1007\/978-3-031-20738-9_71"},{"key":"1445_CR11","doi-asserted-by":"crossref","unstructured":"Shimoda, W., Yanai, K.: Self-supervised difference detection for weakly-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5208\u20135217 (2019)","DOI":"10.1109\/ICCV.2019.00531"},{"key":"1445_CR12","doi-asserted-by":"publisher","DOI":"10.1145\/3589343","author":"Y Guo","year":"2023","unstructured":"Guo, Y., Liang, X., Wu, B., Zheng, X., Zhang, X.: Dual-aware domain mining and cross-aware supervision for weakly-supervised semantic segmentation. ACM Trans. Knowl. Discov. Data (2023). https:\/\/doi.org\/10.1145\/3589343","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"1445_CR13","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761 (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"1445_CR14","doi-asserted-by":"crossref","unstructured":"Yu, T., Ren, Z., Li, Y., Yan, E., Xu, N., Yuan, J.: Temporal structure mining for weakly supervised action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5522\u20135531 (2019)","DOI":"10.1109\/ICCV.2019.00562"},{"key":"1445_CR15","doi-asserted-by":"publisher","unstructured":"Nguyen, P., Ramanan, D., Fowlkes, C.: Weakly-supervised action localization with background modeling. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5501\u20135510 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00560","DOI":"10.1109\/ICCV.2019.00560"},{"issue":"12","key":"1445_CR16","doi-asserted-by":"publisher","first-page":"5797","DOI":"10.1109\/TIP.2019.2922108","volume":"28","author":"R Zeng","year":"2019","unstructured":"Zeng, R., Gan, C., Chen, P., Huang, W., Wu, Q., Tan, M.: Breaking winner-takes-all: Iterative-winners-out networks for weakly supervised temporal action localization. IEEE Trans. Image Process. 28(12), 5797\u20135808 (2019). https:\/\/doi.org\/10.1109\/TIP.2019.2922108","journal-title":"IEEE Trans. Image Process."},{"key":"1445_CR17","doi-asserted-by":"publisher","unstructured":"Huang, L., Wang, L., Li, H.: Foreground-action consistency network for weakly supervised temporal action localization. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV 2021), pp. 7982\u20137991 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00790","DOI":"10.1109\/ICCV48922.2021.00790"},{"key":"1445_CR18","doi-asserted-by":"crossref","unstructured":"Luo, Z., Guillory, D., Shi, B., Ke, W., Wan, F., Darrell, T., Xu, H.: Weakly-supervised action localization with expectation-maximization multi-instance learning. In: European Conference on Computer Vision, pp. 729\u2013745. Springer (2020)","DOI":"10.1007\/978-3-030-58526-6_43"},{"key":"1445_CR19","doi-asserted-by":"crossref","unstructured":"Liu, D., Jiang, T., Wang, Y.: Completeness modeling and context separation for weakly supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1298\u20131307 (2019)","DOI":"10.1109\/CVPR.2019.00139"},{"key":"1445_CR20","doi-asserted-by":"crossref","unstructured":"Islam, A., Radke, R.: Weakly supervised temporal action localization using deep metric learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 547\u2013556 (2020)","DOI":"10.1109\/WACV45572.2020.9093620"},{"key":"1445_CR21","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":"1445_CR22","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. 34, pp. 11320\u201311327 (2020)","DOI":"10.1609\/aaai.v34i07.6793"},{"key":"1445_CR23","unstructured":"Zhou, Z.-H.: Multi-instance learning: a survey. Department of Computer Science & Technology, Nanjing University, Tech. Rep 1 (2004)"},{"key":"1445_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees, H., Zamir, A.R., Jiang, Y.-G., Gorban, A., Laptev, I., Sukthankar, R., Shah, M.: The thumos challenge on action recognition for videos in the wild. Comput. Vis. Image Underst. 155, 1\u201323 (2017). https:\/\/doi.org\/10.1016\/j.cviu.2016.10.018","journal-title":"Comput. Vis. Image Underst."},{"key":"1445_CR25","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":"1445_CR26","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":"1445_CR27","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":"1445_CR28","doi-asserted-by":"crossref","unstructured":"Su, H., Gan, W., Wu, W., Qiao, Y., Yan, J.: BSN++: Complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation. arXiv preprint arXiv:2009.07641 (2020)","DOI":"10.1609\/aaai.v35i3.16363"},{"key":"1445_CR29","doi-asserted-by":"crossref","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.-F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5734\u20135743 (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"1445_CR30","doi-asserted-by":"crossref","unstructured":"Yang, K., Qiao, P., Li, D., Lv, S., Dou, Y.: Exploring temporal preservation networks for precise temporal action localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12234"},{"key":"1445_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C.-L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: Computer Vision\u2014ECCV 2022, pp. 492\u2013510 (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"1445_CR32","doi-asserted-by":"publisher","unstructured":"Shi, D., Zhong, Y., Cao, Q., Ma, L., Li, J., Tao, D.: TriDet: temporal action detection with relative boundary modeling. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18857\u201318866 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01808","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"1445_CR33","doi-asserted-by":"crossref","unstructured":"Lin, C., Li, J., Wang, Y., Tai, Y., Luo, D., Cui, Z., Wang, C., Li, J., Huang, F., Ji, R.: Fast learning of temporal action proposal via dense boundary generator. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11499\u201311506 (2020)","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"1445_CR34","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"},{"issue":"12","key":"1445_CR35","doi-asserted-by":"publisher","first-page":"15896","DOI":"10.1109\/TPAMI.2023.3308571","volume":"45","author":"M Chen","year":"2023","unstructured":"Chen, M., Gao, J., Xu, C.: Uncertainty-aware dual-evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15896\u201315911 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3308571","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"1445_CR36","doi-asserted-by":"publisher","first-page":"15949","DOI":"10.1109\/TPAMI.2023.3311447","volume":"45","author":"J Gao","year":"2023","unstructured":"Gao, J., Chen, M., Xu, C.: Vectorized evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 15949\u201315963 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3311447","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1445_CR37","unstructured":"Sanqing, Q., Guang, C., Zhijun, L., Lijun, Z., Fanf, L., Knoll, A.: ACM-Net: action context modeling network for weakly-supervised temporal action localization. arXiv preprint arXiv:2104.02967 (2021)"},{"key":"1445_CR38","doi-asserted-by":"crossref","unstructured":"Islam, A., Long, C., Radke, R.: A hybrid attention mechanism for weakly-supervised temporal action localization. arXiv preprint arXiv:2101.00545 (2021)","DOI":"10.1609\/aaai.v35i2.16256"},{"key":"1445_CR39","doi-asserted-by":"crossref","unstructured":"Min, K., Corso, J.J.: Adversarial background-aware loss for weakly-supervised temporal activity localization. In: European Conference on Computer Vision, pp. 283\u2013299. Springer (2020)","DOI":"10.1007\/978-3-030-58568-6_17"},{"key":"1445_CR40","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":"1445_CR41","doi-asserted-by":"crossref","unstructured":"Shi, B., Dai, Q., Mu, Y., Wang, J.: Weakly-supervised action localization by generative attention modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1009\u20131019 (2020)","DOI":"10.1109\/CVPR42600.2020.00109"},{"key":"1445_CR42","doi-asserted-by":"publisher","first-page":"137","DOI":"10.5201\/ipol.2013.26","volume":"3","author":"J S\u00e1nchez P\u00e9rez","year":"2013","unstructured":"S\u00e1nchez P\u00e9rez, J., Meinhardt-Llopis, E., Facciolo, G.: TV-L1 optical flow estimation. Image Process. OnLine 3, 137\u2013150 (2013)","journal-title":"Image Process. OnLine"},{"key":"1445_CR43","doi-asserted-by":"crossref","unstructured":"Shou, Z., Gao, H., Zhang, L., Miyazawa, K., Chang, S.-F.: AutoLoc: weakly-supervised temporal action localization in untrimmed videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 154\u2013171 (2018)","DOI":"10.1007\/978-3-030-01270-0_10"},{"key":"1445_CR44","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1445_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Zhang, Q., Tang, W., Yuan, J., Zheng, N., Hua, G.: ACSNet: action-context separation network for weakly supervised temporal action localization. arXiv preprint arXiv:2103.15088 (2021)","DOI":"10.1609\/aaai.v35i3.16322"},{"key":"1445_CR46","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":"1445_CR47","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"1445_CR48","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in PyTorch (2017)"},{"key":"1445_CR49","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"1445_CR50","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.-F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"1445_CR51","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5783\u20135792 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"1445_CR52","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"},{"key":"1445_CR53","doi-asserted-by":"crossref","unstructured":"Xia, K., Wang, L., Zhou, S., Zheng, N., Tang, W.: Learning to refactor action and co-occurrence features for temporal action localization. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Conference on Computer Vision and Pattern Recognition, pp. 13874\u201313883 (2022)","DOI":"10.1109\/CVPR52688.2022.01351"},{"key":"1445_CR54","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1109\/TIP.2021.3137649","volume":"31","author":"L Huang","year":"2022","unstructured":"Huang, L., Wang, L., Li, H.: Multi-modality self-distillation for weakly supervised temporal action localization. IEEE Trans. Image Processing 31, 1504\u20131519 (2022). https:\/\/doi.org\/10.1109\/TIP.2021.3137649","journal-title":"IEEE Trans. Image Processing"},{"key":"1445_CR55","doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, M., Xu, C.: Fine-grained temporal contrastive learning for weakly-supervised temporal action localization. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), pp. 19967\u201319977 (2022)","DOI":"10.1109\/CVPR52688.2022.01937"},{"issue":"11","key":"1445_CR56","doi-asserted-by":"publisher","first-page":"6939","DOI":"10.1109\/TCSVT.2023.3272891","volume":"33","author":"M Moniruzzaman","year":"2023","unstructured":"Moniruzzaman, M., Yin, Z.: Collaborative foreground, background, and action modeling network for weakly supervised temporal action localization. IEEE Trans. Circuits Syst. Video Technol. 33(11), 6939\u20136951 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3272891","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1445_CR57","unstructured":"Yuan, Y., Lyu, Y., Shen, X., Tsang, I.W., Yeung, D.-Y.: Marginalized average attentional network for weakly-supervised learning. arXiv preprint arXiv:1905.08586 (2019)"},{"key":"1445_CR58","doi-asserted-by":"crossref","unstructured":"Li, J., Yang, T., Ji, W., Wang, J., Cheng, L.: Exploring denoised cross-video contrast for weakly-supervised temporal action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19914\u201319924 (2022)","DOI":"10.1109\/CVPR52688.2022.01929"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01445-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01445-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01445-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T14:11:04Z","timestamp":1730124664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01445-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,30]]},"references-count":58,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1445"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01445-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4079741\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,30]]},"assertion":[{"value":"12 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"260"}}