{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:06:13Z","timestamp":1789041973951,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370914","type":"print"},{"value":"9783032370921","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\/978-3-032-37092-1_31","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:07:27Z","timestamp":1789038447000},"page":"552-570","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Why Can\u2019t I Open My Drawer? Mitigating Object-Driven Shortcuts in\u00a0Zero-Shot Compositional Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7792-2374","authenticated-orcid":false,"given":"Geo","family":"Ahn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4356-7616","authenticated-orcid":false,"given":"Inwoong","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7252-5525","authenticated-orcid":false,"given":"Taeoh","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9637-4909","authenticated-orcid":false,"given":"Minho","family":"Shim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-146X","authenticated-orcid":false,"given":"Dongyoon","family":"Wee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7043-0610","authenticated-orcid":false,"given":"Jinwoo","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00522"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Bae, K., Ahn, G., Kim, Y., Choi, J.: DEVIAS: learning disentangled video representations of action and scene for holistic video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73113-6_25"},{"key":"31_CR3","unstructured":"Bahng, H., Chun, S., Yun, S., Choo, J., Oh, S.J.: Learning de-biased representations with biased representations. In: ICML (2020)"},{"key":"31_CR4","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chatterjee, D., Sener, F., Ma, S., Yao, A.: Opening the vocabulary of egocentric actions. Adv. Neural Inform. Process. Syst. (2023)","DOI":"10.52202\/075280-1440"},{"key":"31_CR6","unstructured":"Choi, J., Gao, C., Messou, J.C., Huang, J.B.: Why can\u2019t i dance in the mall? Learning to mitigate scene bias in action recognition. Adv. Neural Inform. Process. Syst. (2019)"},{"key":"31_CR7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. IJCV 130, 33\u201355 (2022)","journal-title":"IJCV"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Diba, A., et al.: Large scale holistic video understanding. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58558-7_35"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Ding, S., et al.: Motion-aware contrastive video representation learning via foreground-background merging. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"31_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"31_CR11","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: ICLR (2018)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"31_CR13","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"31_CR14","unstructured":"Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., Madry, A.: Adversarial examples are not bugs, they are features. NeurIPS (2019)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, D., Jing, H., Ma, Y., Zheng, N.: Beyond image classification: a video benchmark and dual-branch hybrid discrimination framework for compositional zero-shot learning. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00921"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Jung, H., Bak, J.H., Jeong, Y., Lee, G., Ahn, J., Kim, E.S.: Zero-shot compositional video learning with coding rate reduction. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01907"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, J., Park, S., Sohn, K.: Hierarchical visual primitive experts for compositional zero-shot learning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00522"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Unmasked teacher: towards training-efficient video foundation models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: C2C: component-to-composition learning for zero-shot compositional action recognition. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72920-1_21"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Vasconcelos, N.: Resound: towards action recognition without representation bias. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, Z., Chen, H., Yao, L.: Context-based and diversity-driven specificity in compositional zero-shot learning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01612"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1516"},{"key":"31_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111452","volume":"163","author":"Y Liu","year":"2025","unstructured":"Liu, Y., et al.: Knowledge-driven compositional action recognition. Pattern Recogn. 163, 111452 (2025)","journal-title":"Pattern Recogn."},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Luo, Z., Ghosh, S., Guillory, D., Kato, K., Darrell, T., Xu, H.: Disentangled action recognition with knowledge bases. In: North American Chapter of the Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.naacl-main.41"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Ma, Y., Xu, G., Sun, X., Yan, M., Zhang, J., Ji, R.: X-CLIP: end-to-end multi-grained contrastive learning for video-text retrieval. In: ACM MM (2022)","DOI":"10.1145\/3503161.3547910"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Open world compositional zero-shot learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Materzynska, J., Xiao, T., Herzig, R., Xu, H., Wang, X., Darrell, T.: Something-else: compositional action recognition with spatial-temporal interaction networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Misra, I., Gupta, A., Hebert, M.: From red wine to red tomato: composition with context. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.129"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Naeem, M.F., Xian, Y., Tombari, F., Akata, Z.: Learning graph embeddings for compositional zero-shot learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"31_CR30","unstructured":"Nam, J., Cha, H., Ahn, S., Lee, J., Shin, J.: Learning from failure: de-biasing classifier from biased classifier. NeurIPS (2020)"},{"key":"31_CR31","unstructured":"Nayak, N.V., Yu, P., Bach, S.: Learning to compose soft prompts for compositional zero-shot learning. In: ICLR (2023)"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Purushwalkam, S., Nickel, M., Gupta, A., Ranzato, M.: Task-driven modular networks for zero-shot compositional learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00369"},{"key":"31_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Saini, N., Pham, K., Shrivastava, A.: Disentangling visual embeddings for attributes and objects. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01329"},{"key":"31_CR35","unstructured":"Scimeca, L., Oh, S.J., Chun, S., Poli, M., Yun, S.: Which shortcut cues will DNNs choose? A study from the parameter-space perspective. In: ICLR (2022)"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Zha, S., Yan, Z., Goswami, V., Feiszli, M., Torresani, L.: Only time can tell: discovering temporal data for temporal modeling. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00058"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Mahajan, D., Grauman, K., Lee, Y.J., Feiszli, M., Ghadiyaram, D.: Don\u2019t judge an object by its context: learning to overcome contextual bias. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01108"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Sun, P., Wu, B., Li, X., Li, W., Duan, L., Gan, C.: Counterfactual debiasing inference for compositional action recognition. In: ACM MM (2021)","DOI":"10.1145\/3474085.3475472"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Removing the background by adding the background: towards background robust self-supervised video representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Internvideo2: scaling video foundation models for multimodal video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Wu, P., et al.: A conditional probability framework for compositional zero-shot learning. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00350"},{"key":"31_CR42","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: AIM: adapting image models for efficient video understanding. In: ICLR (2023)"},{"key":"31_CR43","doi-asserted-by":"crossref","unstructured":"Ye, G., Li, L., Li, K., Xiao, J., Chen, L.: Zero-shot compositional action recognition with neural logic constraints. In: ACM MM (2025)","DOI":"10.1145\/3746027.3755134"},{"key":"31_CR44","unstructured":"Yun, S., Kim, J., Han, D., Song, H., Ha, J.W., Shin, J.: Time is matter: temporal self-supervision for video transformers. In: ICML (2022)"},{"issue":"2","key":"31_CR45","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1109\/TPAMI.2024.3487222","volume":"47","author":"T Zhang","year":"2024","unstructured":"Zhang, T., Liang, K., Du, R., Chen, W., Ma, Z.: Disentangling before composing: learning invariant disentangled features for compositional zero-shot learning. TPAMI 47(2), 1132\u20131147 (2024)","journal-title":"TPAMI"},{"key":"31_CR46","unstructured":"Zhao, L., et al.: VideoPrism: a commercial-grade video foundation model. In: ICML (2024)"}],"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\/978-3-032-37092-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:07:42Z","timestamp":1789038462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37092-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370914","9783032370921"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37092-1_31","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":"11 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"}}]}}