{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T22:24:36Z","timestamp":1743373476441,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377304"},{"type":"electronic","value":"9783030377311"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-37731-1_45","type":"book-chapter","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T06:02:51Z","timestamp":1577426571000},"page":"555-567","update-policy":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Action Co-localization in an Untrimmed Video by Graph Neural Networks"],"prefix":"10.1007","author":[{"given":"Changbo","family":"Zhai","sequence":"first","affiliation":[]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qilin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhanning","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Zhenxing","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"key":"45_CR1","unstructured":"Mexaction2. https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/mexculture.cnam.fr\/xwiki\/bin\/view\/Datasets\/Mex+ac-tion+dataset"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Ghanem, B., Fei-Fei, L., Niebles, J.C.: End-to-end, single-stream temporal action detection in untrimmed videos. In: BMVC (2017)","DOI":"10.5244\/C.31.93"},{"key":"45_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Duan, X., et al.: Joint spatio-temporal action localization in untrimmed videos with per-frame segmentation. In: ICIP (2018)","DOI":"10.1109\/ICIP.2018.8451692"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Gao, Z., et al.: ER3: a unified framework for event retrieval, recognition and recounting. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.227"},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Jojic, N., Niu, Z., Zheng, N., Hua, G.: Video imprint. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2866114"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Zhang, Q., Niu, Z., Zheng, N., Hua, G.: Video imprint segmentation for temporal action detection in untrimmed videos. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018328"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Niebles, J.C., Ghanem, B.: Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.211"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: Deep learning on spatio-temporal graphs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"45_CR10","unstructured":"Jiang, Y., et al.: Thumos challenge: action recognition with a large number of classes (2014)"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"45_CR12","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"issue":"2\u20133","key":"45_CR13","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Li, R., Tapaswi, M., Liao, R., Jia, J., Urtasun, R., Fidler, S.: Situation recognition with graph neural networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.448"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Shou, Z.: Single shot temporal action detection. In: ACM MM (2017)","DOI":"10.1145\/3123266.3123343"},{"issue":"12","key":"45_CR16","doi-asserted-by":"publisher","first-page":"5840","DOI":"10.1109\/TIP.2018.2859622","volume":"27","author":"Z Liu","year":"2018","unstructured":"Liu, Z., et al.: Joint video object discovery and segmentation by coupled dynamic Markov networks. IEEE Trans. Image Process. 27(12), 5840\u20135853 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Weakly supervised temporal action localization through contrast based evaluation networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00400"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Lv, X., Wang, L., Zhang, Q., Zheng, N., Hua, G.: Video object co-segmentation from noisy videos by a multi-level hypergraph model. In: ICIP (2018)","DOI":"10.1109\/ICIP.2018.8451806"},{"key":"45_CR19","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: The LEAR submission at Thumos 2014. In: ECCV THUMOS Workshop (2014)"},{"key":"45_CR20","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-030-01225-0_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Sujoy Paul","year":"2018","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: ECCV (2018)"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.C.: Learning human-object interactions by graph parsing neural networks. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"45_CR22","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"45_CR23","doi-asserted-by":"crossref","unstructured":"Richard, A., Gall, J.: Temporal action detection using a statistical language model. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.341"},{"key":"45_CR24","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.155"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.F.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"45_CR26","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NeurPIS (2014)"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"45_CR28","unstructured":"Tan, H., Wang, L., Zhang, Q., Gao, Z., Zheng, N., Hua, G.: Object affordances graph network for action recognition. In: BMVC (2019)"},{"key":"45_CR29","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"45_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.441"},{"issue":"10","key":"45_CR31","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1109\/TPAMI.2016.2612187","volume":"39","author":"L Wang","year":"2017","unstructured":"Wang, L., Hua, G., Sukthankar, R., Xue, J., Niu, Z., Zheng, N.: Video object discovery and co-segmentation with extremely weak supervision. IEEE Trans. Pattern Anal. Mach. Intell. 39(10), 2074\u20132088 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"45_CR32","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features. In: ECCV THUMOS Workshop (2014)"},{"key":"45_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X., Van Gool, L.: Actionness estimation using hybrid fully convolutional networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.296"},{"key":"45_CR34","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3d network for temporal activity detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Graph R-CNN for scene graph generation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"45_CR36","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: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.12234"},{"key":"45_CR37","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.337"},{"key":"45_CR38","doi-asserted-by":"crossref","unstructured":"Yuan, Z.H., Stroud, J.C., Lu, T., Deng, J.: Temporal action localization by structured maximal sums. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.342"},{"key":"45_CR39","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: ICCV (2017)","DOI":"10.1109\/ICCV.2017.317"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37731-1_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T11:38:26Z","timestamp":1665315506000},"score":1,"resource":{"primary":{"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/link.springer.com\/10.1007\/978-3-030-37731-1_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377304","9783030377311"],"references-count":39,"URL":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/https\/doi.org\/10.1007\/978-3-030-37731-1_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/summer-heart-0930.chufeiyun1688.workers.dev:443\/http\/www.mmm2020.kr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"171","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}