{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:45:29Z","timestamp":1777657529805,"version":"3.51.4"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729195","type":"print"},{"value":"9783031729201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-72920-1_12","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:02:57Z","timestamp":1727683377000},"page":"203-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["SegIC: Unleashing the\u00a0Emergent Correspondence for\u00a0In-Context Segmentation"],"prefix":"10.1007","author":[{"given":"Lingchen","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyi","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengduo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose M.","family":"Alvarez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Bai, Y., et al.: Sequential modeling enables scalable learning for large vision models. arXiv preprint arXiv:2312.00785 (2023)","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"12_CR2","unstructured":"Bala\u017eevi\u0107, I., Steiner, D., Parthasarathy, N., Arandjelovi\u0107, R., H\u00e9naff, O.J.: Towards in-context scene understanding. arXiv preprint arXiv:2306.01667 (2023)"},{"key":"12_CR3","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. In: ICLR (2021)"},{"key":"12_CR4","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.: Visual prompting via image inpainting. In: NeurIPS (2022)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: ECCV (2006)","DOI":"10.1007\/11744023_32"},{"key":"12_CR6","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"12_CR8","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":"12_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"12_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"12_CR12","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: NeurIPS (2021)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: long-term video object segmentation with an Atkinson-Shiffrin memory model. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"12_CR14","unstructured":"Cho, S., Hong, S., Kim, S.: CATs++: boosting cost aggregation with convolutions and transformers. TPAMI (2022)"},{"key":"12_CR15","unstructured":"Gu, X., et\u00a0al.: DataSeg: taming a universal multi-dataset multi-task segmentation model. arXiv preprint arXiv:2306.01736 (2023)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Hong, S., Cho, S., Nam, J., Lin, S., Kim, S.: Cost aggregation with 4D convolutional swin transformer for few-shot segmentation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"12_CR21","unstructured":"Ilharco, G., et al.: Openclip (2021)"},{"key":"12_CR22","unstructured":"Iqbal, E., Safarov, S., Bang, S.: MSANet: multi-similarity and attention guidance for boosting few-shot segmentation. arXiv preprint arXiv:2206.09667 (2022)"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: OneFormer: one transformer to rule universal image segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"12_CR24","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Johnander, J., Danelljan, M., Brissman, E., Khan, F.S., Felsberg, M.: A generative appearance model for end-to-end video object segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00916"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, J., Cho, M.: TransforMatcher: match-to-match attention for semantic correspondence. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00850"},{"key":"12_CR27","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Wu, Y., He, K., Girshick, R.: PointRend: image segmentation as rendering. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"12_CR29","unstructured":"Kossen, J., Rainforth, T., Gal, Y.: In-context learning in large language models learns label relationships but is not conventional learning. arXiv preprint arXiv:2307.12375 (2023)"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Lee, J.Y., DeGol, J., Fragoso, V., Sinha, S.N.: Patchmatch-based neighborhood consensus for semantic correspondence. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01295"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask DINO: towards a unified transformer-based framework for object detection and segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Li, H., et\u00a0al.: Uni-perceiver v2: a generalist model for large-scale vision and vision-language tasks. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00264"},{"key":"12_CR33","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: NeurIPS (2021)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, Y.P., Tai, Y.W., Tang, C.K.: FSS-1000: a 1000-class dataset for few-shot segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: SWEM: towards real-time video object segmentation with sequential weighted expectation-maximization. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00142"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"12_CR38","unstructured":"Liu, Y., Zhu, M., Li, H., Chen, H., Wang, X., Shen, C.: Matcher: segment anything with one shot using all-purpose feature matching. arXiv preprint arXiv:2305.13310 (2023)"},{"key":"12_CR39","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":"12_CR40","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"12_CR41","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: Detection hub: unifying object detection datasets via query adaptation on language embedding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01097"},{"key":"12_CR44","unstructured":"Meng, L., et al.: Learning from rich semantics and coarse locations for long-tailed object detection. In: NeurIPS (2023)"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. In: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"12_CR46","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Spair-71k: a large-scale benchmark for semantic correspondence. arXiv preprint arXiv:1908.10543 (2019)"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Todorovic, S.: Feature weighting and boosting for few-shot segmentation. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00071"},{"key":"12_CR48","unstructured":"Nguyen, Q.H., Vu, T.T., Tran, A.T., Nguyen, K.: Dataset diffusion: diffusion-based synthetic data generation for pixel-level semantic segmentation. In: NeurIPS (2023)"},{"key":"12_CR49","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"12_CR50","unstructured":"Ouyang, L., et\u00a0al.: Training language models to follow instructions with human feedback. In: NeurIPS (2022)"},{"key":"12_CR51","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van\u00a0Gool, L.: The 2017 Davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"12_CR52","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"12_CR53","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI Blog (2018)"},{"key":"12_CR54","unstructured":"Radford, A., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI Blog (2019)"},{"key":"12_CR55","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR57","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge\u00a0Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Qu\u00e9bec City, QC, Canada, 14 September, Proceedings 3 (2017)"},{"key":"12_CR58","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"12_CR59","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. arXiv preprint arXiv:2306.03881 (2023)"},{"key":"12_CR60","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Wang, X., Jabri, A., Efros, A.A.: Learning correspondence from the cycle-consistency of time. In: CVPR, pp. 2566\u20132576 (2019)","DOI":"10.1109\/CVPR.2019.00267"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. In: Painter (2023)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: SegGPT: towards segmenting everything in context. In: CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"12_CR64","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"12_CR65","unstructured":"Xie, S.M., Raghunathan, A., Liang, P., Ma, T.: An explanation of in-context learning as implicit Bayesian inference. In: ICLR (2021)"},{"key":"12_CR66","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"12_CR67","unstructured":"Xu, N., et al.: YouTube-VOS: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"12_CR68","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: CVPR, pp. 15325\u201315336 (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"12_CR69","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"12_CR70","unstructured":"Zhang, J.W., Sun, Y., Yang, Y., Chen, W.: Feature-proxy transformer for few-shot segmentation. In: Advances in Neural Information Processing Systems (2022)"},{"key":"12_CR71","unstructured":"Zhang, R., et al.: Personalize segment anything model with one shot. arXiv preprint arXiv:2305.03048 (2023)"},{"key":"12_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. IJCV (2019)","DOI":"10.1007\/s11263-018-1140-0"},{"key":"12_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Simple multi-dataset detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"12_CR74","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"12_CR75","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. In: NeurIPS (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72920-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:53:40Z","timestamp":1732830820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72920-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729195","9783031729201"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72920-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}