{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:04:49Z","timestamp":1789254289243,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375551","type":"print"},{"value":"9783032375568","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\/978-3-032-37556-8_10","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:15:48Z","timestamp":1789251348000},"page":"173-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CFM: Language-Aligned Concept Foundation Model for\u00a0Vision"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0521-8466","authenticated-orcid":false,"given":"Kai","family":"Wittenmayer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8896-7619","authenticated-orcid":false,"given":"Sukrut","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0424-7812","authenticated-orcid":false,"given":"Amin","family":"Parchami-Araghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-5237","authenticated-orcid":false,"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6459-5053","authenticated-orcid":false,"given":"Jonas","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Benou, I., Raviv, T.R.: Show and tell: visually explainable deep neural nets via spatially-aware concept bottleneck models. In: CVPR, pp. 30063\u201330072 (2025)","DOI":"10.1109\/CVPR52734.2025.02798"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Bhalla, U., Oesterling, A., Srinivas, S., Calmon, F.P., Lakkaraju, H.: Interpreting CLIP with sparse linear concept embeddings (SpLiCE). In: NeurIPS (2024)","DOI":"10.52202\/079017-2678"},{"key":"10_CR3","unstructured":"Bricken, T., et al.: Towards Monosemanticity: decomposing language models with dictionary learning. Transformer Circuits Thread (2023)"},{"key":"10_CR4","unstructured":"Bussmann, B., Leask, P., Nanda, N.: BatchTopK sparse autoencoders. arXiv preprint arXiv:2412.06410 (2024)"},{"key":"10_CR5","unstructured":"Bussmann, B., Nabeshima, N., Karvonen, A., Nanda, N.: Learning multi-level features with matryoshka sparse autoencoders. In: ICML (2025)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: COCO-stuff: thing and stuff classes in context. In: CVPR, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Cha, J., Mun, J., Roh, B.: Learning to generate text-grounded mask for open-world semantic segmentation from only image-text pairs. In: CVPR, pp. 11165\u201311174 (2023)","DOI":"10.1109\/CVPR52729.2023.01074"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: CVPR, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"10_CR10","unstructured":"Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: NeurIPS, vol.\u00a032 (2019)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Exploring open-vocabulary semantic segmentation from CLIP vision encoder distillation only. In: ICCV, pp. 699\u2013710 (2023)","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: CVPR, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"10_CR15","unstructured":"Cunningham, H., Ewart, A., Riggs, L., Huben, R., Sharkey, L.: Sparse autoencoders find highly interpretable features in language models. In: ICLR (2024)"},{"key":"10_CR16","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: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR17","unstructured":"Dong, H., Li, J., Wu, B., Wang, J., Zhang, Y., Guo, H.: Benchmarking and improving detail image caption. arXiv preprint arXiv:2405.19092 (2024)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Donnelly, J., Barnett, A.J., Chen, C.: Deformable ProtoPNet: an interpretable image classifier using deformable prototypes. In: CVPR, pp. 10265\u201310275 (2022)","DOI":"10.1109\/CVPR52688.2022.01002"},{"key":"10_CR19","unstructured":"Everingham, M., Winn, J.: The PASCAL visual object classes challenge 2012 (VOC2012) development kit. Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep 8(5), 2\u20135 (2011)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Fel, T., et al.: CRAFT: concept recursive activation FacTorization for Explainability. In: CVPR, pp. 2711\u20132721 (2023)","DOI":"10.1109\/CVPR52729.2023.00266"},{"key":"10_CR21","unstructured":"Gao, L., et al.: Scaling and evaluating sparse autoencoders. In: ICLR (2025)"},{"key":"10_CR22","unstructured":"Ghorbani, A., Wexler, J., Zou, J.Y., Kim, B.: Towards automatic concept-based explanations. In: NeurIPS, vol. 32 (2019)"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"He, J., et al.: PartImageNet: a large, high-quality dataset of parts. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13668, pp. 128\u2013145. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_8","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"10_CR24","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: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Q., Song, J., Hu, J., Zhang, H., Wang, Y., Song, M.: On the concept trustworthiness in concept bottleneck models. In: AAAI, pp. 21161\u201321168 (2024)","DOI":"10.1609\/aaai.v38i19.30109"},{"key":"10_CR26","unstructured":"Ilharco, G., et al.: OpenCLIP (2021)"},{"key":"10_CR27","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"key":"10_CR28","doi-asserted-by":"publisher","unstructured":"Karazija, L., Laina, I., Vedaldi, A., Rupprecht, C.: Diffusion models for open-vocabulary segmentation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15063, pp. 299\u2013317. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72652-1_18(2024)","DOI":"10.1007\/978-3-031-72652-1_18"},{"key":"10_CR29","unstructured":"Koh, P.W., et al.: Concept Bottleneck Models. In: ICML, pp. 5338\u20135348 (2020)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Kowal, M., Wildes, R.P., Derpanis, K.G.: Visual Concept Connectome (VCC): open world concept discovery and their interlayer connections in deep models. In: CVPR, pp. 10895\u201310905 (2024)","DOI":"10.1109\/CVPR52733.2024.01036"},{"key":"10_CR31","unstructured":"Li, B., et al.: LLaVA-OneVision: easy visual task transfer. TMLR (2025)"},{"key":"10_CR32","unstructured":"Lim, H., Choi, J., Choo, J., Schneider, S.: Sparse autoencoders reveal selective remapping of visual concepts during adaptation. In: ICLR (2025)"},{"key":"10_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"10_CR36","unstructured":"Luo, H., Bao, J., Wu, Y., He, X., Li, T.: SegCLIP: patch aggregation with learnable centers for open-vocabulary semantic segmentation. In: ICML, pp. 23033\u201323044 (2023)"},{"key":"10_CR37","unstructured":"Menon, S., Vondrick, C.: Visual classification via description from large language models. In: ICLR. (2023)"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: CVPR, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Nauta, M., Schl\u00f6tterer, J., Van Keulen, M., Seifert, C.: PIP-Net: Patch-based Intuitive Prototypes for Interpretable Image Classification. In: CVPR, pp. 2744\u20132753 (2023)","DOI":"10.1109\/CVPR52729.2023.00269"},{"key":"10_CR40","unstructured":"Oikarinen, T., Das, S., Nguyen, L.M., Weng, T.W.: Label-free concept bottleneck models. In: ICLR (2023)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"O\u2019Mahony, L., Andrearczyk, V., M\u00fcller, H., Graziani, M.: Disentangling neuron representations with concept vectors. In: CVPRW, pp. 3769\u20133774 (2023)","DOI":"10.1109\/CVPRW59228.2023.00390"},{"key":"10_CR42","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. TMLR (2024)"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Pach, M., Karthik, S., Bouniot, Q., Belongie, S., Akata, Z.: Sparse autoencoders learn monosemantic features in vision-language models. In: NeurIPS (2025)","DOI":"10.52202\/085713-3202"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Panousis, K.P., Ienco, D., Marcos, D.: Sparse linear concept discovery models. In: ICCVW, pp. 2767\u20132771 (2023)","DOI":"10.1109\/ICCVW60793.2023.00292"},{"key":"10_CR45","doi-asserted-by":"crossref","unstructured":"Panousis, K.P., Ienco, D., Marcos, D.: Coarse-to-fine concept bottleneck models. In: NeurIPS, vol. 37, pp. 105171\u2013105199 (2024)","DOI":"10.52202\/079017-3340"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Parchami-Araghi, A., Rao, S., Fischer, J., Schiele, B.: FaCT: faithful concept traces for explaining neural network decisions. In: NeurIPS (2025)","DOI":"10.52202\/085713-4083"},{"key":"10_CR47","unstructured":"Pham, N., Jesslen, A., Schiele, B., Kortylewski, A., Fischer, J.: Interpretable 3D neural object volumes for robust conceptual reasoning. In: ICLR (2026)"},{"key":"10_CR48","unstructured":"Prasse, K., Knab, P., Marton, S., Bartelt, C., Keuper, M.: DCBM: data-efficient visual concept bottleneck models. In: ICML (2025)"},{"key":"10_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"10_CR50","doi-asserted-by":"crossref","unstructured":"Rajamanoharan, S., et al.: Improving sparse decomposition of language model activations with gated sparse autoencoders. In: NeurIPS (2024)","DOI":"10.52202\/079017-0024"},{"key":"10_CR51","unstructured":"Rajamanoharan, S., et al.: Jumping ahead: improving reconstruction fidelity with JumpReLU sparse autoencoders. arXiv preprint arXiv:2407.14435 (2024)"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., McKinzie, B., Ravi, S., Yang, Y., Toshev, A., Shlens, J.: Perceptual grouping in contrastive vision-language models. In: ICCV, pp. 5571\u20135584 (2023)","DOI":"10.1109\/ICCV51070.2023.00513"},{"key":"10_CR53","doi-asserted-by":"publisher","unstructured":"Rao, S., Mahajan, S., B\u00f6hle, M., Schiele, B.: Discover-then-name: task-agnostic concept bottlenecks via automated concept discovery. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15135, pp. 444\u2013461. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72980-5_26","DOI":"10.1007\/978-3-031-72980-5_26"},{"key":"10_CR54","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"10_CR55","doi-asserted-by":"crossref","unstructured":"Rewatbowornwong, P., Chatthee, N., Chuangsuwanich, E., Suwajanakorn, S.: Zero-guidance segmentation using zero segment labels. In: ICCV, pp. 1162\u20131172 (2023)","DOI":"10.1109\/ICCV51070.2023.00113"},{"issue":"3","key":"10_CR56","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"10_CR57","doi-asserted-by":"crossref","unstructured":"Shin, G., Xie, W., Albanie, S.: ReCo: retrieve and co-segment for zero-shot transfer. In: NeurIPS, vol. 35, pp. 33754\u201333767 (2022)","DOI":"10.52202\/068431-2446"},{"key":"10_CR58","unstructured":"Singh, A., et\u00a0al.: OpenAI GPT-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"10_CR59","unstructured":"Sun, A., Yuan, Y., Ma, P., Wang, S.: Eliminating information leakage in hard concept bottleneck models with supervised, hierarchical concept learning. arXiv preprint arXiv:2402.05945 (2024)"},{"key":"10_CR60","unstructured":"Team, G., et al.: Gemma 2: improving open language models at a practical size. arXiv preprint arXiv:2408.00118 (2024)"},{"key":"10_CR61","unstructured":"Tschannen, M., et al.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"10_CR62","unstructured":"Wimmer, T., et al.: AnyUp: universal feature upsampling. In: ICLR (2026)"},{"key":"10_CR63","doi-asserted-by":"crossref","unstructured":"Wysocza\u0144ska, M., Ramamonjisoa, M., Trzci\u0144ski, T., Sim\u00e9oni, O.: CLIP-DIY: CLIP dense inference yields open-vocabulary semantic segmentation for-free. In: WACV, pp. 1403\u20131413 (2024)","DOI":"10.1109\/WACV57701.2024.00143"},{"key":"10_CR64","doi-asserted-by":"publisher","unstructured":"Wysocza\u0144ska, M., Sim\u00e9oni, O., Ramamonjisoa, M., Bursuc, A., Trzci\u0144ski, T., P\u00e9rez, P.: CLIP-DINOiser: teaching CLIP a Few DINO tricks for open-vocabulary semantic segmentation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15119, pp. 320\u2013337. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73030-6_18","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"10_CR65","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: CVPR, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"10_CR66","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Learning open-vocabulary semantic segmentation models from natural language supervision. In: CVPR, pp. 2935\u20132944 (2023)","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"10_CR67","unstructured":"Xue, M., et al.: ProtoPFormer: concentrating on prototypical parts in vision transformers for interpretable image recognition. In: IJCAI (2022)"},{"key":"10_CR68","doi-asserted-by":"crossref","unstructured":"Yang, Y., Panagopoulou, A., Zhou, S., Jin, D., Callison-Burch, C., Yatskar, M.: Language in a bottle: language model guided concept bottlenecks for interpretable image classification. In: CVPR, pp. 19187\u201319197 (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"10_CR69","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. TMLR (2022)"},{"key":"10_CR70","unstructured":"Yuksekgonul, M., Wang, M., Zou, J.: Post-hoc concept bottleneck models. In: ICLR (2023)"},{"key":"10_CR71","unstructured":"Zaigrajew, V., Baniecki, H., Biecek, P.: Interpreting CLIP with hierarchical sparse autoencoders. In: ICML (2025)"},{"key":"10_CR72","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: ICCV, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"10_CR73","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. In: ICLR (2026)"},{"key":"10_CR74","doi-asserted-by":"publisher","unstructured":"Zheng, K., et al.: DreamLIP: language-image pre-training with long captions. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15076, pp. 73\u201390. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72649-1_5","DOI":"10.1007\/978-3-031-72649-1_5"},{"key":"10_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE TPAMI (2017)","DOI":"10.1167\/17.10.296"},{"issue":"3","key":"10_CR76","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20k dataset. IJCV 127(3), 302\u2013321 (2019)","journal-title":"IJCV"},{"key":"10_CR77","doi-asserted-by":"publisher","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from CLIP. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 696\u2013712. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_40","DOI":"10.1007\/978-3-031-19815-1_40"}],"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\/978-3-032-37556-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:15:58Z","timestamp":1789251358000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37556-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375551","9783032375568"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37556-8_10","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":"13 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"}}]}}