{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:49:39Z","timestamp":1742928579138,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985487"},{"type":"electronic","value":"9789819985494"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8549-4_33","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"395-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-depth Fusion Transformer and Batch Piecewise Loss for Visual Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Haochun","family":"Ou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunmei","family":"Qing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinglun","family":"Cen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangmin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"33_CR1","unstructured":"Wu, B., Xu, C., Dai, X., et al.: Visual transformers: Token-based image representation and processing for computer vision. arXiv preprint arXiv:2006.03677 (2020)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, USA, pp. 6881\u20136890. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"33_CR3","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., et al.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2018)"},{"key":"33_CR4","unstructured":"Tuli, S., Dasgupta, I., Grant, E., et al.: Are convolutional neural networks or transformers more like human vision? In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 43 (2021)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Luo, J.: Visual sentiment analysis by attending on local image regions. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 231\u2013237. AAAI Press, USA (2017)","DOI":"10.1609\/aaai.v31i1.10501"},{"issue":"9","key":"33_CR6","doi-asserted-by":"publisher","first-page":"2513","DOI":"10.1109\/TMM.2018.2803520","volume":"20","author":"J Yang","year":"2018","unstructured":"Yang, J., She, D., Sun, M., et al.: Visual sentiment prediction based on automatic discovery of affective regions. IEEE Trans. Multimedia 20(9), 2513\u20132525 (2018)","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"33_CR7","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.neucom.2018.12.053","volume":"333","author":"T Rao","year":"2019","unstructured":"Rao, T., Li, X., Zhang, H., et al.: Multi-level region-based convolutional neural network for image emotion classification. Neurocomputing 333(6), 429\u2013439 (2019)","journal-title":"Neurocomputing"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Yang, J., She, D., Lai, Y.K., et al.: Weakly supervised coupled networks for visual sentiment analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7584\u20137592. IEEE, USA (2018)","DOI":"10.1109\/CVPR.2018.00791"},{"key":"33_CR9","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.neucom.2018.05.104","volume":"312","author":"K Song","year":"2018","unstructured":"Song, K., Yao, T., Ling, Q., et al.: Boosting image sentiment analysis with visual attention. Neurocomputing 312, 218\u2013228 (2018)","journal-title":"Neurocomputing"},{"issue":"4","key":"33_CR10","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/s00530-020-00656-7","volume":"26","author":"A Yadav","year":"2020","unstructured":"Yadav, A., Vishwakarma, D.K.: A deep learning architecture of RA-DLNet for visual sentiment analysis. Multimedia Syst. 26(4), 431\u2013451 (2020)","journal-title":"Multimedia Syst."},{"issue":"3","key":"33_CR11","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1007\/s11063-019-10027-7","volume":"51","author":"L Wu","year":"2020","unstructured":"Wu, L., Qi, M., Jian, M., et al.: Visual sentiment analysis by combining global and local information. Neural. Process. Lett. 51(3), 2063\u20132075 (2020)","journal-title":"Neural. Process. Lett."},{"issue":"6","key":"33_CR12","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"33_CR13","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.3390\/s21062136","volume":"21","author":"H Ou","year":"2021","unstructured":"Ou, H., Qing, C., Xu, X., et al.: Multi-level context pyramid network for visual sentiment analysis. Sensors 21(6), 2136 (2021)","journal-title":"Sensors"},{"key":"33_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"33_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16\u00a0\u00d7\u00a016 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations, ICLR 2021 (2021)"},{"key":"33_CR16","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., et al.: Do vision transformers see like convolutional neural networks? In: Advances in Neural Information Processing Systems. MIT Press (2021)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022. IEEE, USA (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, USA, pp. 464\u2013468 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988. IEEE, USA (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations, ICLR, USA (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. IEEE, USA (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., et al.: Robust image sentiment analysis using progressively trained and domain transferred deep networks. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 381\u2013388. AAAI, USA (2015)","DOI":"10.1609\/aaai.v29i1.9179"},{"issue":"3","key":"33_CR23","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1007\/s11063-019-10033-9","volume":"51","author":"T Rao","year":"2020","unstructured":"Rao, T., Li, X., Xu, M.: Learning multi-level deep representations for image emotion classification. Neural. Process. Lett. 51(3), 2043\u20132061 (2020)","journal-title":"Neural. Process. Lett."},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, X., Li, L., Zhang, W., et al.: Dependency exploitation: a unified CNN-RNN approach for visual emotion recognition. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Australia, pp. 3595\u20133601 (2017)","DOI":"10.24963\/ijcai.2017\/503"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791. IEEE, USA (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, S., Jia, Z., Chen, H., et al.: PDANet: polarity-consistent deep attention network for fine-grained visual emotion regression. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 192\u2013201 (2019)","DOI":"10.1145\/3343031.3351062"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Xu, L., Wang, Z., Wu, B., et al.: MDAN: multi-level dependent attention network for visual emotion analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9479\u20139488 (2022)","DOI":"10.1109\/CVPR52688.2022.00926"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8549-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T20:07:29Z","timestamp":1730923649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8549-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985487","9789819985494"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8549-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}