{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:15:15Z","timestamp":1742930115877,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8620-6_16","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"231-245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ELEMO: Elements Focused Emotion Recognition for\u00a0Sticker Images"],"prefix":"10.1007","author":[{"given":"Min","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boda","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binghao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Ovsjanikov, M., Haydarov, K., Elhoseiny, M., Guibas, L.J.: Artemis: affective language for visual art. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11569\u201311579 (2021)","DOI":"10.1109\/CVPR46437.2021.01140"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Blaier, E., Malkiel, I., Wolf, L.: Caption enriched samples for improving hateful memes detection (2021). arXiv:2109.10649","DOI":"10.18653\/v1\/2021.emnlp-main.738"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Borth, D., Ji, R., Chen, T., Breuel, T., Chang, S.F.: Large-scale visual sentiment ontology and detectors using adjective noun pairs. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 223\u2013232 (2013)","DOI":"10.1145\/2502081.2502282"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Busso, C., Deng, Z., Yildirim, S., Bulut, M., Lee, C.M., Kazemzadeh, A., Lee, S., Neumann, U., Narayanan, S.: Analysis of emotion recognition using facial expressions, speech and multimodal information. In: Proceedings of the 6th International Conference on Multimodal Interfaces, pp. 205\u2013211 (2004)","DOI":"10.1145\/1027933.1027968"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Cai, Y., Cai, H., Wan, X.: Multi-modal sarcasm detection in twitter with hierarchical fusion model. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2506\u20132515 (2019)","DOI":"10.18653\/v1\/P19-1239"},{"key":"16_CR6","unstructured":"Chen, T., Borth, D., Darrell, T., Chang, S.F.: Deepsentibank: visual sentiment concept classification with deep convolutional neural networks (2014). arXiv:1410.8586"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"16_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2018). arXiv:1810.04805"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Firdaus, M., Chauhan, H., Ekbal, A., Bhattacharyya, P.: Meisd: a multimodal multi-label emotion, intensity and sentiment dialogue dataset for emotion recognition and sentiment analysis in conversations. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 4441\u20134453 (2020)","DOI":"10.18653\/v1\/2020.coling-main.393"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Firdaus, M., Madasu, A., Ekbal, A.: A unified framework for slot based response generation in a multimodal dialogue system. Multimed Tools Appl 83(4), 11643\u201311667 (2024)","DOI":"10.1007\/s11042-023-15915-8"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"He, J., Chen, J.N., Liu, S., Kortylewski, A., Yang, C., Bai, Y., Wang, C.: Transfg: a transformer architecture for fine-grained recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 852\u2013860 (2022)","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Hu, D., Wei, L., Huai, X.: Dialoguecrn: contextual reasoning networks for emotion recognition in conversations (2021). arXiv:2106.01978","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al.: Segment anything (2023). arXiv:2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Kumar, G.K., Nandakumar, K.: Hate-clipper: Multimodal hateful meme classification based on cross-modal interaction of clip features (2022). arXiv:2210.05916","DOI":"10.18653\/v1\/2022.nlp4pi-1.20"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, X., Yang, J.: Ser30k: a large-scale dataset for sticker emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 33\u201341 (2022)","DOI":"10.1145\/3503161.3548407"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Li, C., Yang, J., Su, H., Zhu, J., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection (2023). arXiv:2303.05499","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Lu, H., Guo, Z., Li, C., Yang, Y., He, H., Bao, S.: Towards building an open-domain dialogue system incorporated with internet memes. In: IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2023)","DOI":"10.1109\/TASLP.2023.3288413"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Machajdik, J., Hanbury, A.: Affective image classification using features inspired by psychology and art theory. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 83\u201392 (2010)","DOI":"10.1145\/1873951.1873965"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Patterson, G., Hays, J.: Sun attribute database: Discovering, annotating, and recognizing scene attributes. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2751\u20132758. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247998"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Pramanick, S., Sharma, S., Dimitrov, D., Akhtar, M.S., Nakov, P., Chakraborty, T.: Momenta: a multimodal framework for detecting harmful memes and their targets (2021). arXiv:2109.05184","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"16_CR21","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Rao, T., Li, X., Xu, M.: Learning multi-level deep representations for image emotion classification. Neural Process. Lett. 51, 2043\u20132061 (2020)","DOI":"10.1007\/s11063-019-10033-9"},{"key":"16_CR23","unstructured":"Ren, T., Liu, S., Zeng, A., Lin, J., Li, K., Cao, H., Chen, J., Huang, X., Chen, Y., Yan, F., et\u00a0al.: Grounded sam: assembling open-world models for diverse visual tasks (2024). arXiv:2401.14159"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Sun, Q., Wang, Y., Xu, C., Zheng, K., Yang, Y., Hu, H., Xu, F., Zhang, J., Geng, X., Jiang, D.: Multimodal dialogue response generation (2021). arXiv:2110.08515","DOI":"10.18653\/v1\/2022.acl-long.204"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pvt v2: improved baselines with pyramid vision transformer. Comput Vis Media 8(3), 415\u2013424 (2022)","DOI":"10.1007\/s41095-022-0274-8"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, J., Li, L., Wang, X., Gao, X.: A circular-structured representation for visual emotion distribution learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4237\u20134246 (2021)","DOI":"10.1109\/CVPR46437.2021.00422"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Yang, J., Yu, Y., Niu, D., Guo, W., Xu, Y.: Confede: Contrastive feature decomposition for multimodal sentiment analysis. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 7617\u20137630 (2023)","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Yang, J., She, D., Lai, Y.K., Rosin, P.L., Yang, M.H.: Weakly supervised coupled networks for visual sentiment analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7584\u20137592 (2018)","DOI":"10.1109\/CVPR.2018.00791"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Yang, J., She, D., Sun, M.: Joint image emotion classification and distribution learning via deep convolutional neural network. In: IJCAI, pp. 3266\u20133272 (2017)","DOI":"10.24963\/ijcai.2017\/456"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"You, Q., Luo, J., Jin, H., Yang, J.: Building a large scale dataset for image emotion recognition: the fine print and the benchmark. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a030 (2016)","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Yuan, M., Lv, N., Xie, Y., Lu, F., Zhan, K.: Clip-fg: selecting discriminative image patches by contrastive language-image pre-training for fine-grained image classification. In: 2023 IEEE International Conference on Image Processing (ICIP), pp. 560\u2013564. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10223197"},{"key":"16_CR33","unstructured":"Zhao, S., Ge, Y., Qi, Z., Song, L., Ding, X., Xie, Z., Shan, Y.: Sticker820k: empowering interactive retrieval with stickers (2023). arXiv:2306.06870"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, X., Li, L., Zhang, W., Rao, T., Xu, M., Huang, Q., Xu, D.: Dependency exploitation: a unified CNN-RNN approach for visual emotion recognition. In: IJCAI, pp. 3595\u20133601 (2017)","DOI":"10.24963\/ijcai.2017\/503"}],"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\/978-981-97-8620-6_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:18:39Z","timestamp":1736885919000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}