{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:06Z","timestamp":1788894426488,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37044-0_37","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:18:39Z","timestamp":1788891519000},"page":"674-691","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Structured Visual Compositional Representations for\u00a0Weakly Supervised Referring Expression Comprehension"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1759-2941","authenticated-orcid":false,"given":"Lian","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7250-7407","authenticated-orcid":false,"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-7510","authenticated-orcid":false,"given":"Hamid","family":"Laga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7051-841X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0136-9603","authenticated-orcid":false,"given":"Dan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Akbari, H., et al.: Multi-level multimodal common semantic space for image-phrase grounding. In: Proceedings of the CVPR (2019)","DOI":"10.1109\/CVPR.2019.01276"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Chen, W., Xu, Z., Xu, R., Wu, S., Wong, H.S.: Task-aware cross-modal feature refinement transformer with large language models for visual grounding. In: Proceedings of the CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00372"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Dvin: dynamic visual routing network for weakly supervised referring expression comprehension. In: Proceedings of the CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01338"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: WeakMCN: Multi-task collaborative network for weakly supervised referring expression comprehension and segmentation. In: Proceedings of the CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00857"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Dai, M., Yang, L., Xu, Y., Feng, Z., Yang, W.: SimVG: a simple framework for visual grounding with decoupled multi-modal fusion. NeurIPS (2024)","DOI":"10.52202\/079017-3867"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Datta, S., et al.: Align2ground: weakly supervised phrase grounding guided by image-caption alignment. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.00269"},{"issue":"1","key":"37_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc.: Ser. B (Methodol.) 39(1), 1\u201322 (1977)","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TransVG: end-to-end visual grounding with transformers,. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, T., et al.: Contrastive learning for weakly supervised phrase grounding. In: Proceedings of the ECCV (2020)","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Jin, L., et al.: RefClip: a universal teacher for weakly supervised referring expression comprehension. In: Proceedings of the CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00263"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: Weakly supervised referring image segmentation with intra-chunk and inter-chunk consistency. In: Proceedings of the ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01999"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Proceedings of the ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, L., Yang, M.H.: Referring expression generation and comprehension via attributes. In: Proceedings of the ICCV (2017)","DOI":"10.1109\/ICCV.2017.520"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, L., Wang, S., Zha, Z.J., Meng, D., Huang, Q.: Adaptive reconstruction network for weakly supervised referring expression grounding. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.00270"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wan, B., Ma, L., He, X.: Relation-aware instance refinement for weakly supervised visual grounding. In: Proceedings of the CVPR, pp. 5612\u20135621 (2021)","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Luo, G., Zhou, Y., Sun, X., Cao, L., Wu, C., Deng, C., Ji, R.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: APL: anchor-based prompt learning for one-stage weakly supervised referring expression comprehension. In: Proceedings of the ECCV (2024)","DOI":"10.1007\/978-3-031-72624-8_12"},{"key":"37_CR18","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.neucom.2020.06.091","volume":"413","author":"F Lyu","year":"2020","unstructured":"Lyu, F., Feng, W., Wang, S.: VtgraphNet: learning weakly-supervised scene graph for complex visual grounding. Neurocomputing 413, 51\u201360 (2020)","journal-title":"Neurocomputing"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Ma, C., Jiang, Y., Wu, J., Yuan, Z., Qi, X.: Groma: localized visual tokenization for grounding multimodal large language models. In: Proceedings of the ECCV (2024)","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Proceedings of the ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"37_CR21","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024)"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Qiu, H., et al.: Spatial preference rewarding for MLLMS spatial understanding. In: Proceedings of the ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00075"},{"key":"37_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the ICML (2021)"},{"issue":"11","key":"37_CR25","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.1109\/TPAMI.2021.3058684","volume":"43","author":"M Sun","year":"2021","unstructured":"Sun, M., Xiao, J., Lim, E.G., Liu, S., Goulermas, J.Y.: Discriminative triad matching and reconstruction for weakly referring expression grounding. IEEE TPAMI 43(11), 4189\u20134195 (2021)","journal-title":"IEEE TPAMI"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Teney, D., Liu, L., van Den\u00a0Hengel, A.: Graph-structured representations for visual question answering. In: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.344"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: Proceedings of the CVPR (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Referencing where to focus: improving visual grounding with referential query. NeurIPS (2024)","DOI":"10.52202\/079017-1502"},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Xiao, F., Sigal, L., Lee, Y.J.: Weakly-supervised visual grounding of phrases with linguistic structures. In: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.558"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Xiao, L., Yang, X., Peng, F., Wang, Y., Xu, C.: Oneref: unified one-tower expression grounding and segmentation with mask referring modeling. NeurIPS, (2024)","DOI":"10.52202\/079017-4438"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: Proceedings of the CVPR (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., Lu, J., Lee, S., Batra, D., Parikh, D.: Graph R-CNN for scene graph generation. In: Proceedings of the ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth anything v2. In: Proceedings of the NeurIPS (2024)","DOI":"10.52202\/079017-0688"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: Proceedings of the CVPR (2019)","DOI":"10.1109\/CVPR.2019.00427"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the ICCV (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Graph-structured referring expression reasoning in the wild. In: Proceedings of the CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"37_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yuhao, L., Lin, J., Hancke, G.P., Lau, R.W.: Boosting weakly supervised referring image segmentation via progressive comprehension. In: Proceedings of the NeurIPS (2024)","DOI":"10.52202\/079017-2958"},{"key":"37_CR38","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: MattNet: modular attention network for referring expression comprehension. In: Proceedings of the CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"37_CR39","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Proceedings of the ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"37_CR40","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: Proceedings of the CVPR (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"37_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: OMG-LLaVA: bridging image-level, object-level, pixel-level reasoning and understanding. NeurIPS (2024)","DOI":"10.52202\/079017-2291"},{"key":"37_CR42","unstructured":"Zhang, Z., Zhao, Z., Lin, Z., He, X.: Counterfactual contrastive learning for weakly-supervised vision-language grounding. NeurIPS (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37044-0_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:18:48Z","timestamp":1788891528000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}