{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:18:31Z","timestamp":1743034711546,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463136"},{"type":"electronic","value":"9783031463143"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46314-3_4","type":"book-chapter","created":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:03:06Z","timestamp":1698472986000},"page":"47-58","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Guided Multi-feature Fusion for\u00a0Accurate Video Captioning"],"prefix":"10.1007","author":[{"given":"Yunjie","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoning","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenghua","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.,: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8739\u20138748 (2018)","DOI":"10.1109\/CVPR.2018.00911"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., Krishnamoorthy.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2712\u20132719 (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078(2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Xu, T., Wu, X.J., Kittler, J.: Non-negative subspace representation learning scheme for correlation filter based tracking. In: 2018 24th International Conference on Pattern Recognition, pp. 1888\u20131893 (2018)","DOI":"10.1109\/ICPR.2018.8546146"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., Bailey, J.: Symmetric cross entropy for robust learning with noisy labels. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 322\u2013330 (2019)","DOI":"10.1109\/ICCV.2019.00041"},{"key":"4_CR8","doi-asserted-by":"publisher","unstructured":"Kojima, A., Tamura, T., Fukunaga, K.: Natural language description of human activities from video images based on concept hierarchy of actions. Int. J. Comput. Vision 50, 171\u2013184 (2002). https:\/\/doi.org\/10.1023\/A:1020346032608","DOI":"10.1023\/A:1020346032608"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Venugopalan, S ., et al.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Hori, C., et al.: Attention-based multimodal fusion for video description. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4193\u20134202 (2017)","DOI":"10.1109\/ICCV.2017.450"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Aafaq, N., Akhtar, N., Liu, W., Gilani, S.Z., Mian, A.: Spatio-temporal dynamics and semantic attribute enriched visual encoding for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12487\u201312496 (2019)","DOI":"10.1109\/CVPR.2019.01277"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Wang, C., Tao, D.: Syntax-aware action targeting for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13096\u201313105 (2020)","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Pan, B., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10870\u201310879 (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"4_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107172","volume":"102","author":"T Xu","year":"2020","unstructured":"Xu, T., Feng, Z.H., Wu, X.J., Kittler, J.: An accelerated correlation filter tracker. Pattern Recogn. 102, 107172 (2020)","journal-title":"Pattern Recogn."},{"key":"4_CR17","unstructured":"Ging, S., Zolfaghari, M., Pirsiavash, H., Brox, T.: COOT: cooperative hierarchical transformer for video-text representation learning. In: Advances in Neural Information Processing Systems (2020)"},{"key":"4_CR18","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems (2021)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Xu, T., Feng, Z., Wu, X.J., Kittler, J.: Toward robust visual object tracking with independent target-agnostic detection and effective siamese cross-task interaction. IEEE Transactions on Image Processing, pp. 1541\u20131554 (2023)","DOI":"10.1109\/TIP.2023.3246800"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4584\u20134593 (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, J., Peng, Y.: Object-aware aggregation with bidirectional temporal graph for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8327\u20138336 (2019)","DOI":"10.1109\/CVPR.2019.00852"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Ye, H., Li, G., Qi, Y., Wang, S., Huang, Q., Yang, M.H.: Hierarchical modular network for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17939\u201317948 (2022)","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"4_CR23","doi-asserted-by":"publisher","unstructured":"Xu, T., Zhu, X.-F., Wu, X.-J.: Learning spatio-temporal discriminative model for affine subspace based visual object tracking. Visual Intell. 1(1) (2023). https:\/\/doi.org\/10.1007\/s44267-023-00002-1","DOI":"10.1007\/s44267-023-00002-1"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Liu, W.: Reconstruction network for video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7622\u20137631 (2018)","DOI":"10.1109\/CVPR.2018.00795"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","DOI":"10.1016\/j.neucom.2022.07.028"},{"issue":"5","key":"4_CR26","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.1007\/s11263-021-01435-1","volume":"129","author":"T Xu","year":"2021","unstructured":"Xu, T., Feng, Z., Wu, X.-J., Kittler, J.: Adaptive channel selection for robust visual object tracking with discriminative correlation filters. Int. J. Comput. Vision 129(5), 1359\u20131375 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01435-1","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46314-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:04:32Z","timestamp":1701111872000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46314-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463136","9783031463143"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46314-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","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":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","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":"166","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":"41% - 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":"3","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)"}}]}}