{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:56:20Z","timestamp":1783184180390,"version":"3.54.6"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728891","type":"print"},{"value":"9783031728907","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-3-031-72890-7_8","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:45:46Z","timestamp":1733514346000},"page":"121-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Finding NeMo: Negative-Mined Mosaic Augmentation for\u00a0Referring Image Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3035-2591","authenticated-orcid":false,"given":"Seongsu","family":"Ha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6661-4437","authenticated-orcid":false,"given":"Chaeyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7931-5648","authenticated-orcid":false,"given":"Donghwa","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7643-1024","authenticated-orcid":false,"given":"Junho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8718-0004","authenticated-orcid":false,"given":"Sangho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0786-8086","authenticated-orcid":false,"given":"Joonseok","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"issue":"3","key":"8_CR1","doi-asserted-by":"publisher","first-page":"4419","DOI":"10.1007\/s11042-022-13413-x","volume":"82","author":"M Bellver","year":"2023","unstructured":"Bellver, M., Ventura, C., Silberer, C., Kazakos, I., Torres, J., Giro-i Nieto, X.: A closer look at referring expressions for video object segmentation. Multimedia Tools and Applications 82(3), 4419\u20134438 (2023)","journal-title":"Multimedia Tools and Applications"},{"key":"8_CR2","unstructured":"Blattmann, A., Rombach, R., Oktay, K., M\u00fcller, J., Ommer, B.: Retrieval-augmented diffusion models. In: NeurIPS (2022)"},{"key":"8_CR3","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: Optimal speed and accuracy of object detection. arXiv:2004.10934 (2020)"},{"key":"8_CR4","unstructured":"Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., Van Den\u00a0Driessche, G.B., Lespiau, J.B., Damoc, B., Clark, A., et\u00a0al.: Improving language models by retrieving from trillions of tokens. In: ICML (2022)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Jia, S., Lo, Y.C., Chen, H.T., Liu, T.L.: See-through-text grouping for referring image segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00755"},{"key":"8_CR6","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587 (2017)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Hu, H., Chen, X., Verga, P., Cohen, W.W.: MuRAG: Multimodal retrieval-augmented generator for open question answering over images and text. In: EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"8_CR8","unstructured":"Chen, W., Hu, H., Saharia, C., Cohen, W.W.: Re-Imagen: Retrieval-augmented text-to-image generator. arXiv:2209.14491 (2022)"},{"key":"8_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Cui, Y., Srinivas, A., Qian, R., Lin, T.Y., Cubuk, E.D., Le, Q.V., Zoph, B.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"8_CR12","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: ICML (2020)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Hao, X., Zhu, Y., Appalaraju, S., Zhang, A., Zhang, W., Li, B., Li, M.: MixGen: A new multi-modal data augmentation. In: WACV (2023)","DOI":"10.1109\/WACVW58289.2023.00042"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Z., Feng, G., Sun, J., Zhang, L., Lu, H.: Bi-directional relationship inferring network for referring image segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00448"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Huang, S., Hui, T., Liu, S., Li, G., Wei, Y., Han, J., Liu, L., Li, B.: Referring image segmentation via cross-modal progressive comprehension. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Hui, T., Liu, S., Huang, S., Li, G., Yu, S., Zhang, F., Han, J.: Linguistic structure guided context modeling for referring image segmentation. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Jing, Y., Kong, T., Wang, W., Wang, L., Li, L., Tan, T.: Locate then segment: A strong pipeline for referring image segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: Referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"8_CR21","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., Lewis, M.: Generalization through memorization: Nearest neighbor language models. arXiv:1911.00172 (2019)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Kim, N., Kim, D., Lan, C., Zeng, W., Kwak, S.: Restr: Convolution-free referring image segmentation using transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"8_CR23","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.J., Shamma, D.A., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR24","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.t., Rockt\u00e4schel, T., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. NeurIPS (2020)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Li, M., Xu, R., Wang, S., Zhou, L., Lin, X., Zhu, C., Zeng, M., Ji, H., Chang, S.F.: Clip-event: Connecting text and images with event structures. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01593"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Li, R., Li, K., Kuo, Y.C., Shu, M., Qi, X., Shen, X., Jia, J.: Referring image segmentation via recurrent refinement networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00602"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: Generalized referring expression segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.143"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Son, K., Yang, J., Liu, C., Gao, J., Lee, Y.J., Li, C.: Learning customized visual models with retrieval-augmented knowledge. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01454"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Liu, J., Ding, H., Cai, Z., Zhang, Y., Satzoda, R.K., Mahadevan, V., Manmatha, R.: PolyFormer: Referring image segmentation as sequential polygon generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Liu, W., Zhou, P., Zhao, Z., Wang, Z., Ju, Q., Deng, H., Wang, P.: K-BERT: Enabling language representation with knowledge graph. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Long, A., Yin, W., Ajanthan, T., Nguyen, V., Purkait, P., Garg, R., Blair, A., Shen, C., van\u00a0den Hengel, A.: Retrieval augmented classification for long-tail visual recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00683"},{"key":"8_CR34","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Margffoy-Tuay, E., P\u00e9rez, J.C., Botero, E., Arbel\u00e1ez, P.: Dynamic multimodal instance segmentation guided by natural language queries. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_39"},{"key":"8_CR37","unstructured":"Norelli, A., Fumero, M., Maiorca, V., Moschella, L., Rodola, E., Locatello, F.: ASIF: Coupled data turns unimodal models to multimodal without training. In: NeurIPS (2023)"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Peters, M.E., Neumann, M., Logan\u00a0IV, R.L., Schwartz, R., Joshi, V., Singh, S., Smith, N.A.: Knowledge enhanced contextual word representations. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1005"},{"key":"8_CR39","unstructured":"Shen, S., Li, C., Hu, X., Xie, Y., Yang, J., Zhang, P., Gan, Z., Wang, L., Yuan, L., Liu, C., et\u00a0al.: K-LITE: Learning transferable visual models with external knowledge. In: NeurIPS (2022)"},{"key":"8_CR40","unstructured":"Sheynin, S., Ashual, O., Polyak, A., Singer, U., Gafni, O., Nachmani, E., Taigman, Y.: KNN-diffusion: Image generation via large-scale retrieval. In: ICLR (2023)"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Shi, H., Li, H., Meng, F., Wu, Q.: Key-word-aware network for referring expression image segmentation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01231-1_3"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Shi, C., Yang, S.: Contrastive grouping with transformer for referring image segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, Y., Li, Q., Tao, X., Guo, Y., Gong, M., Liu, T.: CRIS: Clip-driven referring image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Wu, C., Lin, Z., Cohen, S., Bui, T., Maji, S.: PhraseCut: Language-based image segmentation in the wild. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, X., Li, X., Ding, H., Tong, Y., Tao, D.: Towards robust referring image segmentation. IEEE Transactions on Image Processing (2024)","DOI":"10.1109\/TIP.2024.3371348"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Xie, C.W., Sun, S., Xiong, X., Zheng, Y., Zhao, D., Zhou, J.: RA-CLIP: Retrieval augmented contrastive language-image pre-training. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: Language-aware vision transformer for referring image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"8_CR48","unstructured":"Yasunaga, M., Aghajanyan, A., Shi, W., James, R., Leskovec, J., Liang, P., Lewis, M., Zettlemoyer, L., Yih, W.t.: Retrieval-augmented multimodal language modeling. arXiv:2211.12561 (2023)"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Yu, L., Lin, Z., Shen, X., Yang, J., Lu, X., Bansal, M., Berg, T.L.: MAttNet: Modular attention network for referring expression comprehension. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhu, C., Fang, Y., Yu, D., Wang, S., Xu, Y., Zeng, M., Jiang, M.: Dict-BERT: Enhancing language model pre-training with dictionary. In: ACL (2021)","DOI":"10.18653\/v1\/2022.findings-acl.150"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: Regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv:1710.09412 (2017)","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. arXiv:2303.02153 (2023)","DOI":"10.1109\/ICCV51070.2023.00527"}],"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\/978-3-031-72890-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:04:26Z","timestamp":1733515466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72890-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9783031728891","9783031728907"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72890-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 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"}}]}}