{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:14Z","timestamp":1777657454278,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726606","type":"print"},{"value":"9783031726613","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-72661-3_8","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T07:48:48Z","timestamp":1732607328000},"page":"132-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["HYDRA: A Hyper Agent for\u00a0Dynamic Compositional Visual Reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9709-1305","authenticated-orcid":false,"given":"Fucai","family":"Ke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7978-0860","authenticated-orcid":false,"given":"Zhixi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8903-5175","authenticated-orcid":false,"given":"Simindokht","family":"Jahangard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9578-819X","authenticated-orcid":false,"given":"Weiqing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9922-1214","authenticated-orcid":false,"given":"Pari Delir","family":"Haghighi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8659-8773","authenticated-orcid":false,"given":"Hamid","family":"Rezatofighi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"8_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR2","unstructured":"Amizadeh, S., Palangi, H., Polozov, A., Huang, Y., Koishida, K.: Neuro-symbolic visual reasoning: disentangling. In: International Conference on Machine Learning, pp. 279\u2013290. PMLR (2020)"},{"key":"8_CR3","unstructured":"Bai, Y., et al.: Constitutional AI: harmlessness from AI feedback. arXiv preprint arXiv:2212.08073 (2022)"},{"key":"8_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR5","doi-asserted-by":"publisher","unstructured":"Bugliarello, E., Sartran, L., Agrawal, A., Hendricks, L.A., Nematzadeh, A.: Measuring progress in fine-grained vision-and-language understanding. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada, pp. 1559\u20131582. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.87. https:\/\/aclanthology.org\/2023.acl-long.87","DOI":"10.18653\/v1\/2023.acl-long.87"},{"issue":"240","key":"8_CR6","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR7","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14953\u201314962 (2023)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"8_CR9","unstructured":"Han, J., et al.: Imagebind-LLM: multi-modality instruction tuning. arXiv preprint arXiv:2309.03905 (2023)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Heigold, G., et al.: Video owl-VIT: temporally-consistent open-world localization in video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13802\u201313811 (2023)","DOI":"10.1109\/ICCV51070.2023.01269"},{"key":"8_CR11","unstructured":"Hsieh, C.Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: Sugarcrepe: fixing hackable benchmarks for vision-language compositionality. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Visual program distillation: Distilling tools and programmatic reasoning into vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9590\u20139601 (2024)","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"8_CR13","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In: International Conference on Machine Learning, pp. 9118\u20139147. PMLR (2022)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"8_CR15","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. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 5583\u20135594. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/kim21k.html"},{"key":"8_CR16","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199\u201322213 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR17","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726 (2023)"},{"key":"8_CR18","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the 40th International Conference on Machine Learning, ICML 2023. JMLR.org (2023)"},{"key":"8_CR19","unstructured":"Li, L., et al.: $$\\text{M}^3$$it: a large-scale dataset towards multi-modal multilingual instruction tuning. arXiv preprint arXiv:2306.04387 (2023)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"8_CR22","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR23","unstructured":"Lu, P., et al.: Chameleon: plug-and-play compositional reasoning with large language models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019). https:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Marino_OK-VQA_A_Visual_Question_Answering_Benchmark_Requiring_External_Knowledge_CVPR_2019_paper.html","DOI":"10.1109\/CVPR.2019.00331"},{"key":"8_CR25","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR26","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"8_CR27","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR28","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol.\u00a032. Curran Associates, Inc. (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/bdbca288fee7f92f2bfa9f7012727740-Abstract.html"},{"key":"8_CR29","unstructured":"Peng, Z., et al.: Grounding multimodal large language models to the world. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=lLmqxkfSIw"},{"issue":"8","key":"8_CR30","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"issue":"3","key":"8_CR31","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR32","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-031-20074-8_9","volume-title":"European Conference on Computer Vision","author":"D Schwenk","year":"2022","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-OKVQA: a benchmark for visual question answering using world knowledge. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13668, pp. 146\u2013162. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_9"},{"key":"8_CR33","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: Hugginggpt: solving AI tasks with chatgpt and its friends in hugging face. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR34","unstructured":"Stani\u0107, A., Caelles, S., Tschannen, M.: Towards truly zero-shot compositional visual reasoning with LLMs as programmers. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=WYGiqSVstK"},{"key":"8_CR35","unstructured":"Su, Y., Lan, T., Li, H., Xu, J., Wang, Y., Cai, D.: Pandagpt: one model to instruction-follow them all. arXiv preprint arXiv:2305.16355 (2023)"},{"key":"8_CR36","doi-asserted-by":"publisher","unstructured":"Subramanian, S., Merrill, W., Darrell, T., Gardner, M., Singh, S., Rohrbach, A.: ReCLIP: a strong zero-shot baseline for referring expression comprehension. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5198\u20135215 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.357","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Sur\u2019is, D., Menon, S., Vondrick, C.: Vipergpt: visual inference via python execution for reasoning. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11854\u201311864 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257505358","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"8_CR38","doi-asserted-by":"publisher","unstructured":"Tiong, A.M.H., Li, J., Li, B., Savarese, S., Hoi, S.C.: Plug-and-play VQA: zero-shot VQA by conjoining large pretrained models with zero training. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 951\u2013967 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.67","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"key":"8_CR39","unstructured":"Villalobos, P., Sevilla, J., Heim, L., Besiroglu, T., Hobbhahn, M., Ho, A.: Will we run out of data? An analysis of the limits of scaling datasets in machine learning. arXiv preprint arXiv:2211.04325 (2022)"},{"key":"8_CR40","unstructured":"Wang, W., et al.: Visionllm: large language model is also an open-ended decoder for vision-centric tasks. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR41","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatgpt: talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)"},{"key":"8_CR42","unstructured":"Wu, S., Fei, H., Qu, L., Ji, W., Chua, T.S.: Next-GPT: any-to-any multimodal LLM. arXiv preprint arXiv:2309.05519 (2023)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3081\u20133089 (2022)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"8_CR44","unstructured":"Yang, Z., et al.: MM-react: prompting chatgpt for multimodal reasoning and action. arXiv preprint arXiv:2303.11381 (2023)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"You, H., et al.: Idealgpt: iteratively decomposing vision and language reasoning via large language models. arXiv preprint arXiv:2305.14985 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"8_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"8_CR47","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 (2022)"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"8_CR49","unstructured":"Zeng, Y., Zhang, X., Li, H.: Multi-grained vision language pre-training: aligning texts with visual concepts. In: International Conference on Machine Learning, pp. 25994\u201326009. PMLR (2022)"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"8_CR51","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (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\/978-3-031-72661-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:17:32Z","timestamp":1732609052000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72661-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031726606","9783031726613"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72661-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 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"}}]}}