{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:50:23Z","timestamp":1761227423536,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819521005"},{"type":"electronic","value":"9789819521012"}],"license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"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\/978-981-95-2101-2_44","type":"book-chapter","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:27:02Z","timestamp":1761226022000},"page":"534-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Memory Reconciliation for\u00a0Online Action Detection"],"prefix":"10.1007","author":[{"given":"Wenze","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zimo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihong","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"An, J., Kang, H., Han, S.H., Yang, M.H., Kim, S.J.: Miniroad: minimal RNN framework for online action detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10341\u201310350 (2023)","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"44_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":"44_CR3","doi-asserted-by":"crossref","unstructured":"Cao, S., Luo, W., Wang, B., Zhang, W., Ma, L.: E2e-load: end-to-end long-form online action detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10422\u201310432 (2023)","DOI":"10.1109\/ICCV51070.2023.00956"},{"key":"44_CR4","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":"44_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Mittal, G., Yu, Y., Kong, Y., Chen, M.: Gatehub: gated history unit with background suppression for online action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 19925\u201319934 (2022)","DOI":"10.1109\/CVPR52688.2022.01930"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, F., Bertasius, G.: Tallformer: temporal action localization with a long-memory transformer. In: Proceedings of the European Conference on Computer Vision, pp. 503\u2013521. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19830-4_29"},{"key":"44_CR7","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"De\u00a0Geest, R., Gavves, E., Ghodrati, A., Li, Z., Snoek, C., Tuytelaars, T.: Online action detection. In: Proceedings of the European Conference on Computer Vision, pp. 269\u2013284 (2016)","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"De\u00a0Geest, R., Tuytelaars, T.: Modeling temporal structure with LSTM for online action detection. In: 2018 IEEE Winter Conference on Applications of Computer Vision, pp. 1549\u20131557. IEEE (2018)","DOI":"10.1109\/WACV.2018.00173"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Eun, H., Moon, J., Park, J., Jung, C., Kim, C.: Learning to discriminate information for online action detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 809\u2013818 (2020)","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: Red: reinforced encoder-decoder networks for action anticipation. arXiv preprint arXiv:1707.04818 (2017)","DOI":"10.5244\/C.31.92"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: Jadfer: exploring spatial-contextual interaction with joint attention dropping for facial expression recognition. IEEE Trans. Affect. Comput. (2024)","DOI":"10.1109\/TAFFC.2024.3454988"},{"issue":"11","key":"44_CR13","doi-asserted-by":"publisher","first-page":"18622","DOI":"10.1109\/JSEN.2024.3389674","volume":"24","author":"Y Gao","year":"2024","unstructured":"Gao, Y., Ren, W., Wang, Q., Chen, X., Wang, Z., Liu, H.: Snefer: stopping the negative effect of noisy labels adaptively in facial expression recognition. IEEE Sens. J. 24(11), 18622\u201318632 (2024)","journal-title":"IEEE Sens. J."},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Long short-term memory. In: Supervised Sequence Labelling with Recurrent Neural Networks, pp. 37\u201345 (2012)","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Guermal, M., Ali, A., Dai, R., Bremond, F.: Joadaa: joint online action detection and action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6889\u20136898 (2024)","DOI":"10.1109\/WACV57701.2024.00674"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, H., Ji, Q.: Bayesian evidential deep learning for online action detection. In: Proceedings of the European Conference on Computer Vision, pp. 283\u2013301 (2024)","DOI":"10.1007\/978-3-031-72640-8_16"},{"key":"44_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: The thumos challenge on action recognition for videos \u201cin the wild\u201d. Comput. Vis. Image Understand. 155, 1\u201323 (2017)","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"44_CR19","unstructured":"Ioffe, S.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 770\u2013778 (2015)"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Ji, H., Chen, B., Huang, W., Ren, W., Wang, Z., Liu, H.: Snippet-aware transformer with multiple action elements for skeleton-based action segmentation. IEEE Trans. Neural Netw. Learn. Syst. (2025)","DOI":"10.1109\/TNNLS.2025.3563025"},{"key":"44_CR21","doi-asserted-by":"crossref","unstructured":"Ji, H., Chen, B., Xu, X., Ren, W., Wang, Z., Liu, H.: Language-assisted skeleton action understanding for skeleton-based temporal action segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 400\u2013417. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72949-2_23"},{"issue":"2","key":"44_CR22","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1109\/TITS.2013.2280766","volume":"15","author":"CG Keller","year":"2013","unstructured":"Keller, C.G., Gavrila, D.M.: Will the pedestrian cross? A study on pedestrian path prediction. IEEE Trans. Intell. Transp. Syst. 15(2), 494\u2013506 (2013)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Kim, J., Misu, T., Chen, Y.T., Tawari, A., Canny, J.: Grounding human-to-vehicle advice for self-driving vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10591\u201310599 (2019)","DOI":"10.1109\/CVPR.2019.01084"},{"key":"44_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, T.T., Kawanishi, Y., Komamizu, T., Ide, I.: One-stage open-vocabulary temporal action detection leveraging temporal multi-scale and action label features. In: International Conference on Automatic Face and Gesture Recognition, pp. 1\u201310. IEEE (2024)","DOI":"10.1109\/FG59268.2024.10581896"},{"key":"44_CR25","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":"44_CR26","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":"44_CR27","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":"44_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"44_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, G., Huang, Y., Wang, L., Lu, T.: Memory-and-anticipation transformer for online action understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 13824\u201313835 (2023)","DOI":"10.1109\/ICCV51070.2023.01271"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of the European Conference on Computer Vision, pp. 20\u201336 (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"44_CR31","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Oadtr: online action detection with transformers. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7565\u20137575 (2021)","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Xu, M., Gao, M., Chen, Y.T., Davis, L.S., Crandall, D.J.: Temporal recurrent networks for online action detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5532\u20135541 (2019)","DOI":"10.1109\/ICCV.2019.00563"},{"key":"44_CR33","unstructured":"Xu, M., et al.: Long short-term transformer for online action detection. In: Advances in Neural Information Processing Systems, vol. 34, pp. 1086\u20131099 (2021)"},{"key":"44_CR34","doi-asserted-by":"crossref","unstructured":"Yang, L., Han, J., Zhang, D.: Colar: effective and efficient online action detection by consulting exemplars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3160\u20133169 (2022)","DOI":"10.1109\/CVPR52688.2022.00316"},{"key":"44_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Kr\u00e4henb\u00fchl, P.: Real-time online video detection with temporal smoothing transformers. In: Proceedings of the European Conference on Computer Vision, pp. 485\u2013502 (2022)","DOI":"10.1007\/978-3-031-19830-4_28"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2101-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T13:27:21Z","timestamp":1761226041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2101-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"ISBN":["9789819521005","9789819521012"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2101-2_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"24 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okayama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"6 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}