{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T13:32:58Z","timestamp":1771680778999,"version":"3.50.1"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guilin Science and Technology Program"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00530-024-01511-9","type":"journal-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T10:07:13Z","timestamp":1730887633000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Local and global context cooperation for temporal action detection"],"prefix":"10.1007","volume":"30","author":[{"given":"Lanxi","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luhui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,6]]},"reference":[{"key":"1511_CR1","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.neucom.2022.03.069","volume":"491","author":"X Hu","year":"2022","unstructured":"Hu, X., Dai, J., Li, M., Peng, C., Li, Y., Du, S.: Online human action detection and anticipation in videos: a survey. Neurocomputing 491, 395\u2013413 (2022)","journal-title":"Neurocomputing"},{"key":"1511_CR2","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Gan, C., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6016\u20136025 (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"1511_CR3","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"1511_CR4","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.neucom.2022.11.028","volume":"519","author":"S-S Zang","year":"2023","unstructured":"Zang, S.-S., Yu, H., Song, Y., Zeng, R.: Unsupervised video summarization using deep non-local video summarization networks. Neurocomputing 519, 26\u201335 (2023)","journal-title":"Neurocomputing"},{"issue":"10","key":"1511_CR5","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TPAMI.2020.2985708","volume":"43","author":"J Gao","year":"2020","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 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"1511_CR6","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.1109\/TCSVT.2021.3075470","volume":"32","author":"J Gao","year":"2021","unstructured":"Gao, J., Xu, C.: Learning video moment retrieval without a single annotated video. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1646\u20131657 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"1511_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":"1511_CR8","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":"1511_CR9","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":"1511_CR10","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":"1511_CR11","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":"1511_CR12","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":"1511_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, F., Bertasius, G.: Tallformer: temporal action localization with a long-memory transformer. In: European Conference on Computer Vision, pp. 503\u2013521. Springer, Berlin (2022)","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"1511_CR14","doi-asserted-by":"crossref","unstructured":"Dou, Z.-Y., Xu, Y., Gan, Z., Wang, J., Wang, S., Wang, L., Zhu, C., Zhang, P., Yuan, L., Peng, N., : An empirical study of training end-to-end vision-and-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"1511_CR15","doi-asserted-by":"crossref","unstructured":"Lin, C., Xu, C., Luo, D., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., Fu, Y.: 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":"1511_CR16","doi-asserted-by":"publisher","first-page":"103692","DOI":"10.1016\/j.cviu.2023.103692","volume":"232","author":"M Yang","year":"2023","unstructured":"Yang, M., Chen, G., Zheng, Y.-D., Lu, T., Wang, L.: Basictad: an astounding RGB-only baseline for temporal action detection. Comput. Vis. Image Understand. 232, 103692 (2023)","journal-title":"Comput. Vis. Image Understand."},{"key":"1511_CR17","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, Berlin (2022)","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"1511_CR18","doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, M., Xu, C.: Vectorized evidential learning for weakly-supervised temporal action localization. IEEE Trans. Pattern Anal. Mach. intelligence (2023)","DOI":"10.1109\/CVPR52729.2023.01416"},{"key":"1511_CR19","unstructured":"Tang, T.N., Kim, K., Sohn, K.: Temporalmaxer: Maximize Temporal Context With Only Max Pooling for Temporal Action Localization. arXiv preprint arXiv:2303.09055 (2023)"},{"key":"1511_CR20","doi-asserted-by":"publisher","first-page":"103945","DOI":"10.1016\/j.cviu.2024.103945","volume":"240","author":"X Xiang","year":"2024","unstructured":"Xiang, X., Yin, H., Qiao, Y., El Saddik, A.: Temporal adaptive feature pyramid network for action detection. Comput. Vis. Image Understand. 240, 103945 (2024)","journal-title":"Comput. Vis. Image Understand."},{"key":"1511_CR21","doi-asserted-by":"crossref","unstructured":"Chen, G., Zheng, Y.-D., Chen, Z., Wang, J., Lu, T.: Elan: Enhancing temporal action detection with location awareness. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1020\u20131025 (2023). IEEE","DOI":"10.1109\/ICME55011.2023.00179"},{"key":"1511_CR22","doi-asserted-by":"publisher","first-page":"102585","DOI":"10.1016\/j.aei.2024.102585","volume":"62","author":"H Wang","year":"2024","unstructured":"Wang, H., You, D., Zhang, S.: Exploiting relation of video segments for temporal action detection. Adv. Eng. Inf. 62, 102585 (2024)","journal-title":"Adv. Eng. Inf."},{"key":"1511_CR23","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1109\/TMM.2021.3050067","volume":"24","author":"C Sun","year":"2021","unstructured":"Sun, C., Song, H., Wu, X., Jia, Y., Luo, J.: Exploiting informative video segments for temporal action localization. IEEE Trans. Multimed. 24, 274\u2013287 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"1511_CR24","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neucom.2022.08.075","volume":"511","author":"C Zhong","year":"2022","unstructured":"Zhong, C., Hu, L., Xia, S.: Spatial-temporal modeling for prediction of stylized human motion. Neurocomputing 511, 34\u201342 (2022)","journal-title":"Neurocomputing"},{"issue":"10","key":"1511_CR25","doi-asserted-by":"publisher","first-page":"6209","DOI":"10.1109\/TPAMI.2021.3090167","volume":"44","author":"R Zeng","year":"2021","unstructured":"Zeng, R., Huang, W., Tan, M., Rong, Y., Zhao, P., Huang, J., Gan, C.: Graph convolutional module for temporal action localization in videos. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6209\u20136223 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1511_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems, vol. 30 (2017)"},{"key":"1511_CR27","doi-asserted-by":"crossref","unstructured":"Dai, R., Minciullo, L., Garattoni, L., Francesca, G., Bremond, F.: Self-attention temporal convolutional network for long-term daily living activity detection. In: 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20137 (2019). IEEE","DOI":"10.1109\/AVSS.2019.8909841"},{"key":"1511_CR28","doi-asserted-by":"publisher","first-page":"126617","DOI":"10.1016\/j.neucom.2023.126617","volume":"554","author":"J Huang","year":"2023","unstructured":"Huang, J., Zhao, P., Wang, G., Yang, S., Lin, J.: Self-attention-based long temporal sequence modeling method for temporal action detection. Neurocomputing 554, 126617 (2023)","journal-title":"Neurocomputing"},{"key":"1511_CR29","doi-asserted-by":"crossref","unstructured":"Sridhar, D., Quader, N., Muralidharan, S., Li, Y., Dai, P., Lu, J.: Class semantics-based attention for action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13739\u201313748 (2021)","DOI":"10.1109\/ICCV48922.2021.01348"},{"key":"1511_CR30","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 \u201cin the wild\u2019\u2019. Comput. Vis. Image Understand. 155, 1\u201323 (2017)","journal-title":"Comput. Vis. Image Understand."},{"key":"1511_CR31","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"1511_CR32","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van\u00a0Gool, L.: Temporal segment networks: towards good practices for deep action recognition. In: European Conference on Computer Vision, pp. 20\u201336. Springer, Berlin (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"1511_CR33","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 (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1511_CR34","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"1511_CR35","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1511_CR36","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S.-F., Paluri, M.: Convnet Architecture Search for Spatiotemporal Feature Learning. arXiv preprint arXiv:1708.05038 (2017)"},{"key":"1511_CR37","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., Van\u00a0Gool, L.: Appearance-and-relation networks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1430\u20131439 (2018)","DOI":"10.1109\/CVPR.2018.00155"},{"key":"1511_CR38","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"1511_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., Li, J., Huang, F., Lu, T.: TEINET: towards an efficient architecture for video recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"1511_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: TAM: temporal adaptive module for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13708\u201313718 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"1511_CR41","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"1511_CR42","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"1511_CR43","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: I know the relationships: zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8303\u20138311 (2019)","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"1511_CR44","doi-asserted-by":"crossref","unstructured":"Chen, G., Zheng, Y.-D., Wang, L., Lu, T.: DCAN: improving temporal action detection via dual context aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 248\u2013257 (2022)","DOI":"10.1609\/aaai.v36i1.19900"},{"key":"1511_CR45","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":"1511_CR46","doi-asserted-by":"crossref","unstructured":"Liu, X., Hu, Y., Bai, S., Ding, F., Bai, X., Torr, P.H.S.: Multi-shot temporal event localization: a benchmark. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12591\u201312601 (2021)","DOI":"10.1109\/CVPR46437.2021.01241"},{"key":"1511_CR47","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":"1511_CR48","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Chen, K., Sun, C., Nevatia, R.: Turn tap: Temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3628\u20133636 (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"1511_CR49","doi-asserted-by":"crossref","unstructured":"Long, F., Yao, T., Qiu, Z., Tian, X., Luo, J., Mei, T.: Gaussian temporal awareness networks for action localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 344\u2013353 (2019)","DOI":"10.1109\/CVPR.2019.00043"},{"key":"1511_CR50","doi-asserted-by":"publisher","first-page":"121330","DOI":"10.1016\/j.eswa.2023.121330","volume":"237","author":"J Yang","year":"2024","unstructured":"Yang, J., Wang, K., Zhao, L., Jiang, Z., Li, R.: Actionmixer: temporal action detection with optimal action segment assignment and mixers. Expert Syst. Appl. 237, 121330 (2024)","journal-title":"Expert Syst. Appl."},{"key":"1511_CR51","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 988\u2013996 (2017)","DOI":"10.1145\/3123266.3123343"},{"key":"1511_CR52","doi-asserted-by":"publisher","first-page":"8535","DOI":"10.1109\/TIP.2020.3016486","volume":"29","author":"L Yang","year":"2020","unstructured":"Yang, L., Peng, H., Zhang, D., Fu, J., Han, J.: Revisiting anchor mechanisms for temporal action localization. IEEE Trans. Image Process. 29, 8535\u20138548 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"1511_CR53","doi-asserted-by":"crossref","unstructured":"Pan, J., Chen, S., Shou, M.Z., Liu, Y., Shao, J., Li, H.: 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 (2021)","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"1511_CR54","doi-asserted-by":"publisher","first-page":"108725","DOI":"10.1016\/j.patcog.2022.108725","volume":"129","author":"K Xia","year":"2022","unstructured":"Xia, K., Wang, L., Zhou, S., Hua, G., Tang, W.: Dual relation network for temporal action localization. Pattern Recogn. 129, 108725 (2022)","journal-title":"Pattern Recogn."},{"issue":"10","key":"1511_CR55","doi-asserted-by":"publisher","first-page":"2723","DOI":"10.1109\/TMM.2019.2959977","volume":"22","author":"P Chen","year":"2019","unstructured":"Chen, P., Gan, C., Shen, G., Huang, W., Zeng, R., Tan, M.: Relation attention for temporal action localization. IEEE Trans. Multimed. 22(10), 2723\u20132733 (2019)","journal-title":"IEEE Trans. Multimed."},{"issue":"12","key":"1511_CR56","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)","journal-title":"IEEE Trans. Image Process."},{"key":"1511_CR57","doi-asserted-by":"publisher","first-page":"109135","DOI":"10.1016\/j.patcog.2022.109135","volume":"134","author":"Y Tang","year":"2023","unstructured":"Tang, Y., Zheng, Y., Wei, C., Guo, K., Hu, H., Liang, J.: Video representation learning for temporal action detection using global-local attention. Pattern Recogn. 134, 109135 (2023)","journal-title":"Pattern Recogn."},{"key":"1511_CR58","doi-asserted-by":"publisher","first-page":"4746","DOI":"10.1109\/TIP.2022.3182866","volume":"31","author":"Y Zhao","year":"2022","unstructured":"Zhao, Y., Zhang, H., Gao, Z., Guan, W., Nie, J., Liu, A., Wang, M., Chen, S.: A temporal-aware relation and attention network for temporal action localization. IEEE Trans. Image Process. 31, 4746\u20134760 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"1511_CR59","doi-asserted-by":"crossref","unstructured":"Cao, C., Wang, Y., Zhang, Y., Lu, Y., Zhang, X., Zhang, Y.: Co-occurrence matters: learning action relation for temporal action localization. IEEE Trans. Circuits Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3321508"},{"key":"1511_CR60","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An Image is Worth 16x16 words: Transformers for Image Recognition at Scale. arxiv 2020. arXiv preprint arXiv:2010.11929 (2010)"},{"key":"1511_CR61","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":"1511_CR62","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z.-H., Tay, F.E., Feng, J., Yan, S.: Tokens-to-token vit: Training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 558\u2013567 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"1511_CR63","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1511_CR64","unstructured":"Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., Gao, J.: Focal self-attention for local-global interactions in vision transformers. arXiv preprint arXiv:2107.00641 (2021)"},{"key":"1511_CR65","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol. 2, p. 4 (2021)"},{"key":"1511_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, X., Liu, C., Shuai, B., Zhu, Y., Brattoli, B., Chen, H., Marsic, I., Tighe, J.: VIDTR: video transformer without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13577\u201313587 (2021)","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"1511_CR67","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. In: Advances in Neural Information Processing Systems, vol. 34, pp. 30392\u201330400 (2021)"},{"key":"1511_CR68","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1511_CR69","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1511_CR70","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS\u2014improving object detection with one line of code. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5561\u20135569 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"1511_CR71","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":"1511_CR72","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., Doughty, H., Farinella, G.M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vis. 130, 33\u201355 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"1511_CR73","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic Gradient Descent With Warm Restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"1511_CR74","doi-asserted-by":"crossref","unstructured":"Alwassel, H., Giancola, S., Ghanem, B.: TSP: temporally-sensitive pretraining of video encoders for localization tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3173\u20133183 (2021)","DOI":"10.1109\/ICCVW54120.2021.00356"},{"key":"1511_CR75","doi-asserted-by":"crossref","unstructured":"Qing, Z., Su, H., Gan, W., Wang, D., Wu, W., Wang, X., Qiao, Y., Yan, J., Gao, C., Sang, N.: Temporal context aggregation network for temporal action proposal refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 485\u2013494 (2021)","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"1511_CR76","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu, X., Wang, Q., Hu, Y., Tang, X., Zhang, S., Bai, S., Bai, X.: End-to-end temporal action detection with transformer. IEEE Trans. Image Process. 31, 5427\u20135441 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"1511_CR77","doi-asserted-by":"publisher","first-page":"5705","DOI":"10.1109\/TMM.2023.3338082","volume":"26","author":"J Yang","year":"2024","unstructured":"Yang, J., Wei, P., Ren, Z., Zheng, N.: Gated multi-scale transformer for temporal action localization. IEEE Trans. Multimed. 26, 5705\u20135717 (2024)","journal-title":"IEEE Trans. Multimed."},{"key":"1511_CR78","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"},{"key":"1511_CR79","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"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01511-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01511-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01511-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T09:10:55Z","timestamp":1734340255000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01511-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,6]]},"references-count":79,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["1511"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01511-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,6]]},"assertion":[{"value":"26 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"334"}}