{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:39:18Z","timestamp":1742917158780,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755745"},{"type":"electronic","value":"9789819755752"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-5575-2_17","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:01:54Z","timestamp":1725184914000},"page":"243-253","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Representation and\u00a0Granularity Joint Alignment Framework for\u00a0Multimodal Sarcasm Detection on\u00a0Social Media"],"prefix":"10.1007","author":[{"given":"Jiapei","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fenghuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianhua","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Eke, C.I., Norman, A.A., Shuib, L., et al.: Sarcasm identification in textual data: systematic review, research challenges and open directions. Artif. Intell. Rev. 53, 4215\u20134258 (2020)","DOI":"10.1007\/s10462-019-09791-8"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Xu, N., Zeng, Z., Mao, W.: Reasoning with multimodal sarcastic tweets via modeling cross-modality contrast and semantic association. In: Proceedings of ACL, pp. 3777\u20133786 (2020)","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Tay, Y., Luu, A.T., Hui, S.C., Su, J.: Reasoning with sarcasm by reading in-between. In: Proceedings of ACL, pp. 1010\u20131020 (2018)","DOI":"10.18653\/v1\/P18-1093"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., Cai, H., Wan, X.: Multi-modal sarcasm detection in Twitter with hierarchical fusion model. In: Proceedings of ACL, Florence, Italy, pp. 2506\u20132515 (2019)","DOI":"10.18653\/v1\/P19-1239"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Pan, H., Lin, Z., Fu, P., Qi, Y., Wang, W.: Modeling intra and inter-modality incongruity for multi-modal sarcasm detection. In: Proceedings of EMNLP, pp. 1383\u20131392 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.124"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Liang, B., Lou, C., Li, X., Gui, L., Yang, M., Xu, R.: Multi-modal sarcasm detection with interactive in-modal and cross-modal graphs. In: Proceedings of ACMMM, pp. 4707\u20134715 (2021)","DOI":"10.1145\/3474085.3475190"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Liang, B., et al.: Multi-modal sarcasm detection via cross-modal graph convolutional network. In: Proceedings of ACL, Dublin, Ireland, pp. 1767\u20131777 (2022)","DOI":"10.18653\/v1\/2022.acl-long.124"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Revisiting multimodal representation in contrastive learning: from patch and token embeddings to finite discrete tokens. In: Proceedings of CVPR, pp. 15095\u201315104 (2023)","DOI":"10.1109\/CVPR52729.2023.01449"},{"key":"17_CR9","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: Proceedings of NeurIPS, pp. 9694\u20139705 (2021)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., Ding, C.: Learning granularity-unified representations for text-to-image person re-identification. In: Proceedings of ACMMM, pp. 5566\u20135574. ACM, Lisboa Portugal (2022)","DOI":"10.1145\/3503161.3548028"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"17_CR12","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of NIPS (2017)"},{"key":"17_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102132","volume":"103","author":"J Wang","year":"2024","unstructured":"Wang, J., Yang, Y., Jiang, Y., Ma, M., Xie, Z., Li, T.: Cross-modal incongruity aligning and collaborating for multi-modal sarcasm detection. Inf. Fusion 103, 102132 (2024)","journal-title":"Inf. Fusion"},{"key":"17_CR14","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of ICML, pp. 8748\u20138763 (2021)"},{"key":"17_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of ICLR (2021)"},{"key":"17_CR16","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, Minneapolis, Minnesota, pp. 4171\u20134186 (2019)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., Wang, W., Li, H.: Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement. In: Proceedings of EMNLP, Abu Dhabi, United Arab Emirates, pp. 4995\u20135006 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.333"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Wen, C., Jia, G., Yang, J.: DIP: dual incongruity perceiving network for sarcasm detection. In: Proceedings of CVPR, pp. 2540\u20132550 (2023)","DOI":"10.1109\/CVPR52729.2023.00250"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Jing, L., Song, X., Chen, X., Zhu, L., Nie, L.: Mutual-enhanced incongruity learning network for multi-modal sarcasm detection. In: Proceedings of AAAI, pp. 9507\u20139515 (2023)","DOI":"10.1609\/aaai.v37i8.26138"},{"key":"17_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of ICML, pp. 19730\u201319742 (2023)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5575-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:04:26Z","timestamp":1725185066000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5575-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755745","9789819755752"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5575-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gifu","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2024a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dasfaa2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}