{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:05:11Z","timestamp":1757624711929,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819500994"},{"type":"electronic","value":"9789819501007"}],"license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-0100-7_7","type":"book-chapter","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T04:37:20Z","timestamp":1755491840000},"page":"109-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid-Granularity Image-Music Retrieval Using Contrastive Learning Between Images and\u00a0Music"],"prefix":"10.1007","author":[{"given":"Xudong","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"7_CR1","unstructured":"Bai, J., et al.: Qwen-vl: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, X., Zhu, Z., Li, H., Li, Y., Zou, Y.: Ssvmr: saliency-based self-training for video-music retrieval. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096514"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Craswell, N.: Mean reciprocal rank. Encyclopedia of database systems, pp. 1703\u20131703 (2009)","DOI":"10.1007\/978-0-387-39940-9_488"},{"key":"7_CR4","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":"7_CR5","doi-asserted-by":"crossref","unstructured":"Doh, S., Lee, M., Jeong, D., Nam, J.: Enriching music descriptions with a finetuned-llm and metadata for text-to-music retrieval. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 826\u2013830. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446380"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Doh, S., Won, M., Choi, K., Nam, J.: Textless speech-to-music retrieval using emotion similarity. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095926"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Doh, S., Won, M., Choi, K., Nam, J.: Toward universal text-to-music retrieval. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10094670"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Dong, Z., Liu, X., Chen, B., Polak, P., Zhang, P.: Musechat: a conversational music recommendation system for videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12775\u201312785 (2024)","DOI":"10.1109\/CVPR52733.2024.01214"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Elizalde, B., Deshmukh, S., Al\u00a0Ismail, M., Wang, H.: Clap learning audio concepts from natural language supervision. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Hong, S., Im, W., Yang, H.S.: CBVMR: content-based video-music retrieval using soft intra-modal structure constraint. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp. 353\u2013361 (2018)","DOI":"10.1145\/3206025.3206046"},{"key":"7_CR12","unstructured":"Huang, Q., Jansen, A., Lee, J., Ganti, R., Li, J.Y., Ellis, D.P.: Mulan: a joint embedding of music audio and natural language. arXiv preprint arXiv:2208.12415 (2022)"},{"key":"7_CR13","unstructured":"Jain, T., Lennan, C., John, Z., Tran, D.: Imagededup (2019). https:\/\/github.com\/idealo\/imagededup"},{"key":"7_CR14","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Koutini, K., Schl\u00fcter, J., Eghbal-Zadeh, H., Widmer, G.: Efficient training of audio transformers with patchout. arXiv preprint arXiv:2110.05069 (2021)","DOI":"10.21437\/Interspeech.2022-227"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Lee, Y.S., Tseng, W.C., Wang, F.E., Sun, M.: Vmcml: video and music matching via cross-modality lifting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2060\u20132069 (2024)","DOI":"10.1109\/CVPRW63382.2024.00211"},{"key":"7_CR18","unstructured":"Lennan, C., Nguyen, H., Tran, D.: Image quality assessment (2018). https:\/\/github.com\/idealo\/image-quality-assessment"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C., Wu, H., Zhong, Y., Zhang, X., Wang, Y., Xie, W.: Intelligent grimm-open-ended visual storytelling via latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6190\u20136200 (2024)","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"7_CR21","unstructured":"Manco, I., Benetos, E., Quinton, E., Fazekas, G.: Contrastive audio-language learning for music. arXiv preprint arXiv:2208.12208 (2022)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Mao, T., Liu, S., Zhang, Y., Li, D., Shan, Y.: Unified pretraining target based video-music retrieval with music rhythm and video optical flow information. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7890\u20137894. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446029"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"McKee, D., Salamon, J., Sivic, J., Russell, B.: Language-guided music recommendation for video via prompt analogies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14784\u201314793 (2023)","DOI":"10.1109\/CVPR52729.2023.01420"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Nakatsuka, T., Hamasaki, M., Goto, M.: Content-based music-image retrieval using self-and cross-modal feature embedding memory. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2174\u20132184 (2023)","DOI":"10.1109\/WACV56688.2023.00221"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Park, J., Shin, H., Oh, C., Kim, H.Y.: \u201cis text-based music search enough to satisfy your needs?\u201d a new way to discover music with images. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, pp. 1\u201321 (2024)","DOI":"10.1145\/3613904.3642126"},{"key":"7_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Stewart, S., Avramidis, K., Feng, T., Narayanan, S.: Emotion-aligned contrastive learning between images and music. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8135\u20138139. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447276"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Stewart, S., KV, G., Lu, L., Fanelli, A.: Semi-supervised contrastive learning for controllable video-to-music retrieval. arXiv preprint arXiv:2412.05831 (2024)","DOI":"10.1109\/ICASSP49660.2025.10890382"},{"key":"7_CR29","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1109\/OJCS.2023.3300321","volume":"4","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Pan, Y., Yan, M., Su, Z., Luan, T.H.: A survey on ChatGPT: AI-generated contents, challenges, and solutions. IEEE Open J. Comput. Soc. 4, 280\u2013302 (2023)","journal-title":"IEEE Open J. Comput. Soc."},{"key":"7_CR30","unstructured":"Won, M., Salamon, J., Bryan, N.J., Mysore, G.J., Serra, X.: Emotion embedding spaces for matching music to stories. arXiv preprint arXiv:2111.13468 (2021)"},{"key":"7_CR31","doi-asserted-by":"publisher","first-page":"136378","DOI":"10.1109\/ACCESS.2019.2942073","volume":"7","author":"B Xing","year":"2019","unstructured":"Xing, B., Zhang, K., Zhang, L., Wu, X., Dou, J., Sun, S.: Image\u2013music synesthesia-aware learning based on emotional similarity recognition. IEEE Access 7, 136378\u2013136390 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2942073","journal-title":"IEEE Access"},{"key":"7_CR32","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/TMM.2021.3128254","volume":"25","author":"J Yi","year":"2021","unstructured":"Yi, J., Zhu, Y., Xie, J., Chen, Z.: Cross-modal variational auto-encoder for content-based micro-video background music recommendation. IEEE Trans. Multimedia 25, 515\u2013528 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"7_CR33","doi-asserted-by":"publisher","unstructured":"Yi, J., Zhu, Y., Xie, J., Chen, Z.: Cross-modal variational auto-encoder for content-based micro-video background music recommendation. IEEE Trans. Multimedia 25, 515\u2013528 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3128254","DOI":"10.1109\/TMM.2021.3128254"},{"key":"7_CR34","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310\u201312320. PMLR (2021)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, M., et al.: Weakly supervised contrastive learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10042\u201310051 (2021)","DOI":"10.1109\/ICCV48922.2021.00989"}],"container-title":["Lecture Notes in Computer Science","Computer Animation and Social Agents"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0100-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T15:17:08Z","timestamp":1757431028000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0100-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"ISBN":["9789819500994","9789819501007"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0100-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"19 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Animation and Social Agents","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"casa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/casa2025.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}