{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T16:01:33Z","timestamp":1772121693013,"version":"3.50.1"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919060","type":"print"},{"value":"9783031919077","type":"electronic"}],"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\/978-3-031-91907-7_5","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T11:45:19Z","timestamp":1748346319000},"page":"71-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["RoCOCO: Robustness Benchmark of\u00a0MS-COCO to\u00a0Stress-Test Image-Text Matching Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5679-3718","authenticated-orcid":false,"given":"Seulki","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0223-2400","authenticated-orcid":false,"given":"Daeho","family":"Um","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0270-4251","authenticated-orcid":false,"given":"Hajung","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4533-2610","authenticated-orcid":false,"given":"Sanghyuk","family":"Chun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0417-8450","authenticated-orcid":false,"given":"Sangdoo","family":"Yun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"5_CR1","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. arXiv preprint arXiv:2204.14198 (2022)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Alzantot, M., Sharma, Y., Elgohary, A., Ho, B.J., Srivastava, M., Chang, K.W.: Generating natural language adversarial examples. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018)","DOI":"10.18653\/v1\/D18-1316"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"5_CR4","unstructured":"Belinkov, Y., Bisk, Y.: Synthetic and natural noise both break neural machine translation. In: International Conference on Learning Representations (2018)"},{"key":"5_CR5","unstructured":"Biggio, B., Nelson, B., Laskov, P.: Poisoning attacks against support vector machines. In: Proceedings of the 29th International Conference on International Conference on Machine Learning (2012)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Boucher, N., Shumailov, I., Anderson, R., Papernot, N.: Bad characters: imperceptible NLP attacks. In: 2022 IEEE Symposium on Security and Privacy (SP) (2022)","DOI":"10.1109\/SP46214.2022.9833641"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Byun, J., Hwang, T., Fu, J., Moon, T.: GRIT-VLP: grouped mini-batch sampling for efficient vision and language pre-training. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel (2022)","DOI":"10.1007\/978-3-031-19800-7_23"},{"key":"5_CR8","unstructured":"Carlini, N., Terzis, A.: Poisoning and backdooring contrastive learning. In: International Conference on Learning Representations (2022)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Adversarial examples are not easily detected: bypassing ten detection methods. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security (2017)","DOI":"10.1145\/3128572.3140444"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., Wang, C.: Learning the best pooling strategy for visual semantic embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"5_CR11","unstructured":"Chen, X., Liu, C., Li, B., Lu, K., Song, D.: Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 (2017)"},{"key":"5_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, M., et\u00a0al.: Vista: vision and scene text aggregation for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder\u2013decoder approaches. In: 8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2014 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Chun, S., Kim, W., Park, S., Chang, M., Oh, S.J.: ECCV caption: correcting false negatives by collecting machine-and-human-verified image-caption associations for MS-COCO. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part VIII (2022)","DOI":"10.1007\/978-3-031-20074-8_1"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Chun, S., Oh, S.J., de\u00a0Rezende, R.S., Kalantidis, Y., Larlus, D.: Probabilistic embeddings for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Croce, F., Hein, M.: Sparse and imperceivable adversarial attacks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00482"},{"key":"5_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (2019)"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"5_CR20","unstructured":"Dong, X., Luu, A.T., Ji, R., Liu, H.: Towards robustness against natural language word substitutions. In: International Conference on Learning Representations (2021)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Ebrahimi, J., Rao, A., Lowd, D., Dou, D.: HotFlip: white-box adversarial examples for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2018)","DOI":"10.18653\/v1\/P18-2006"},{"key":"5_CR22","unstructured":"Frome, A., et al.: DeViSE: a deep visual-semantic embedding model. Adv. Neural Inf. Process. Syst. (2013)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Gal, R., Patashnik, O., Maron, H., Bermano, A.H., Chechik, G., Cohen-Or, D.: StyleGAN-NADA: CLIP-guided domain adaptation of image generators. ACM TOG (2022)","DOI":"10.1145\/3528223.3530164"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Galatolo, F.A., Cimino, M.G., Vaglini, G.: Generating images from caption and vice versa via clip-guided generative latent space search. arXiv preprint arXiv:2102.01645 (2021)","DOI":"10.5220\/0010503701660174"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Garg, S., Ramakrishnan, G.: BAE: BERT-based adversarial examples for text classification. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.498"},{"key":"5_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-030-58589-1_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Gokhale","year":"2020","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: VQA-LOL: visual question answering under the lens of logic. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 379\u2013396. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_23"},{"key":"5_CR27","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"5_CR28","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"5_CR29","unstructured":"Gu, T., Dolan-Gavitt, B., Garg, S.: BadNets: identifying vulnerabilities in the machine learning model supply chain. arXiv preprint arXiv:1708.06733 (2017)"},{"key":"5_CR30","unstructured":"Guo, C., Gardner, J., You, Y., Wilson, A.G., Weinberger, K.: Simple black-box adversarial attacks. In: Proceedings of the 36th International Conference on Machine Learning (2019)"},{"key":"5_CR31","unstructured":"Gupta, T., Marten, R., Kembhavi, A., Hoiem, D.: GRIT: general robust image task benchmark. arXiv preprint arXiv:2204.13653 (2022)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et\u00a0al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"5_CR33","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2019)"},{"key":"5_CR34","unstructured":"Hendrycks, D., Mazeika, M., Wilson, D., Gimpel, K.: Using trusted data to train deep networks on labels corrupted by severe noise. In: Advances in Neural Information Processing Systems (2018)"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Hu, P., Peng, X., Zhu, H., Zhen, L., Lin, J.: Learning cross-modal retrieval with noisy labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Iyyer, M., Wieting, J., Gimpel, K., Zettlemoyer, L.: Adversarial example generation with syntactically controlled paraphrase networks. In: Proceedings of NAACL-HLT (2018)","DOI":"10.18653\/v1\/N18-1170"},{"key":"5_CR38","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning (2021)"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Jia, R., Raghunathan, A., G\u00f6ksel, K., Liang, P.: Certified robustness to adversarial word substitutions. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)","DOI":"10.18653\/v1\/D19-1423"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Kim, D., Kim, N., Kwak, S.: Improving cross-modal retrieval with set of diverse embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"5_CR42","unstructured":"Kim, W., Son, B., Kim, I.: VILT: vision-and-language transformer without convolution or region supervision. In: Proceedings of the 38th International Conference on Machine Learning. PMLR (2021)"},{"key":"5_CR43","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Li, D., et al.: Contextualized perturbation for textual adversarial attack. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2021)","DOI":"10.18653\/v1\/2021.naacl-main.400"},{"key":"5_CR46","unstructured":"Li, D., Li, J., Hoi, S.: BLIP-diffusion: pre-trained subject representation for controllable text-to-image generation and editing. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Li, J., Ji, R., Liu, H., Hong, X., Gao, Y., Tian, Q.: Universal perturbation attack against image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4899\u20134908 (2019)","DOI":"10.1109\/ICCV.2019.00500"},{"key":"5_CR48","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"5_CR49","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning. PMLR (2022)"},{"key":"5_CR50","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. Adv. Neural Inf. Process. Syst. (2021)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"5_CR52","unstructured":"Li, L., Gan, Z., Liu, J.: A closer look at the robustness of vision-and-language pre-trained models. arXiv preprint arXiv:2012.08673 (2020)"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Li, L., Lei, J., Gan, Z., Liu, J.: Adversarial VQA: a new benchmark for evaluating the robustness of VQA models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00205"},{"key":"5_CR54","doi-asserted-by":"crossref","unstructured":"Li, L., Ma, R., Guo, Q., Xue, X., Qiu, X.: BERT-attack: adversarial attack against BERT using BERT. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"5_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"5_CR56","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":"5_CR57","doi-asserted-by":"crossref","unstructured":"Lu, H., Fei, N., Huo, Y., Gao, Y., Lu, Z., Wen, J.R.: COTS: collaborative two-stream vision-language pre-training model for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15692\u201315701 (2022)","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Parekh, Z., Baldridge, J., Cer, D., Waters, A., Yang, Y.: Crisscrossed captions: extended intramodal and intermodal semantic similarity judgments for MS-COCO. arXiv preprint arXiv:2004.15020 (2020)","DOI":"10.18653\/v1\/2021.eacl-main.249"},{"key":"5_CR59","doi-asserted-by":"crossref","unstructured":"Park, D.H., Darrell, T., Rohrbach, A.: Robust change captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00472"},{"key":"5_CR60","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"5_CR62","unstructured":"Prabhu, V., Yenamandra, S., Chattopadhyay, P., Hoffman, J.: LANCE: stress-testing visual models by generating language-guided counterfactual images. arXiv preprint arXiv:2305.19164 (2023)"},{"key":"5_CR63","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR (2021)"},{"key":"5_CR64","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"5_CR65","doi-asserted-by":"crossref","unstructured":"Ren, S., Deng, Y., He, K., Che, W.: Generating natural language adversarial examples through probability weighted word saliency. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1103"},{"key":"5_CR66","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR67","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. (2022)"},{"key":"5_CR68","doi-asserted-by":"crossref","unstructured":"Shah, M., Chen, X., Rohrbach, M., Parikh, D.: Cycle-consistency for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00681"},{"key":"5_CR69","unstructured":"Sheng, S., et al.: Human-adversarial visual question answering. Adv. Neural Inf. Process. Syst. (2021)"},{"key":"5_CR70","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: CLIPort: what and where pathways for robotic manipulation. In: Conference on Robot Learning. PMLR (2022)"},{"key":"5_CR71","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"5_CR72","unstructured":"Steinhardt, J., Koh, P.W.W., Liang, P.S.: Certified defenses for data poisoning attacks. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"5_CR73","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"5_CR74","doi-asserted-by":"crossref","unstructured":"Wallace, E., Zhao, T., Feng, S., Singh, S.: Concealed data poisoning attacks on NLP models. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2021)","DOI":"10.18653\/v1\/2021.naacl-main.13"},{"key":"5_CR75","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: CODER: coupled diversity-sensitive momentum contrastive learning for image-text retrieval. In: European Conference on Computer Vision (2022)","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"5_CR76","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58586-0_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhang, Y., Ji, Z., Pang, Y., Ma, L.: Consensus-aware visual-semantic embedding for image-text matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_2"},{"key":"5_CR77","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Wasserstein coupled graph learning for cross-modal retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00183"},{"key":"5_CR78","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":"5_CR79","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? In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"5_CR80","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: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"5_CR81","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"},{"key":"5_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, P., Goyal, Y., Summers-Stay, D., Batra, D., Parikh, D.: Yin and yang: balancing and answering binary visual questions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.542"},{"key":"5_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00553"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91907-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T08:29:38Z","timestamp":1754555378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91907-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919060","9783031919077"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91907-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}