{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:00:45Z","timestamp":1754154045156,"version":"3.41.2"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819697939"},{"type":"electronic","value":"9789819697946"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-9794-6_35","type":"book-chapter","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T06:13:01Z","timestamp":1752473581000},"page":"419-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PB-CLIP: Enhancing CLIP's Compositional Reasoning with Pixel-level Image Hard Negatives and Balanced Multi-level Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Zimo","family":"Nie","sequence":"first","affiliation":[]},{"given":"Weina","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Haimei","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Zhiwei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Chaodong","family":"Tong","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"35_CR1","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5100\u20135111. ACL (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Ma\u00f1as, O., Rodriguez, P., Ahmadi, S., Nematzadeh, A., Goyal, Y., Agrawal, A.: MAPL: parameter-efficient adaptation of unimodal pre-trained models for vision-language few-shot prompting. arXiv preprint arXiv:2303.03230 (2023)","DOI":"10.18653\/v1\/2023.eacl-main.185"},{"key":"35_CR5","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936 (2022)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. In: arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"35_CR7","unstructured":"Zhang, H., et al.: TripletCLIP: enhancing vision-language models with triplet contrastive learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Structure-CLIP: towards scene graph knowledge to enhance multi-modal structured representations. In: AAAI Conference on Artificial Intelligence (AAAI) (2024)","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"35_CR9","unstructured":"Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 21798\u201321809 (2020)"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: MSKR: advancing multi-modal structured knowledge representation with synergistic hard negative samples. In: ACM International Conference on Information and Knowledge Management (CIKM) (2024)","DOI":"10.1145\/3627673.3679680"},{"key":"35_CR11","unstructured":"Jia, C., et al.: ALIGN: scaling up visual and vision-language representation learning with noisy text supervision. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Contrasting intra-modal and ranking cross-modal hard negatives to enhance visio-linguistic compositional understanding. arXiv preprint arXiv:2305.12097 (2023)","DOI":"10.1109\/CVPR52733.2024.01307"},{"key":"35_CR13","unstructured":"Mishra, R., Subramanyam, A.V.: Image synthesis with graph conditioning: CLIP-guided diffusion models for scene graphs. arXiv preprint arXiv:2401.14111 (2024)"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision (ECCV), pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5228\u20135238 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2017)","DOI":"10.1007\/s11263-016-0981-7"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9794-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T22:11:02Z","timestamp":1753308662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9794-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819697939","9789819697946"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9794-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}