{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:11:21Z","timestamp":1788851481813,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370945","type":"print"},{"value":"9783032370952","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\/978-3-032-37095-2_33","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:04:46Z","timestamp":1788851086000},"page":"608-626","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Video-Oasis: Rethinking Evaluation of\u00a0Video Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2204-6109","authenticated-orcid":false,"given":"Geuntaek","family":"Lim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0310-8718","authenticated-orcid":false,"given":"Sungjune","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2109-0862","authenticated-orcid":false,"given":"Jaeyun","family":"Lee","sequence":"additional","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\/0000-0003-0359-146X","authenticated-orcid":false,"given":"Dongyoon","family":"Wee","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\/0000-0002-9970-0132","authenticated-orcid":false,"given":"Yukyung","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"33_CR1","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"33_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"33_CR3","unstructured":"Chen, B., et\u00a0al.: VideoChat-M1: collaborative policy planning for video understanding via multi-agent reinforcement learning. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2026)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: LVAgent: long video understanding by multi-round dynamical collaboration of MLLM agents. In: Proceedings of the International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.01882"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: Eagle 2.5: boosting long-context post-training for frontier vision-language models. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-3047"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Scaling RL to long videos. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-5753"},{"key":"33_CR7","unstructured":"Cheng, J., Ge, Y., Wang, T., Ge, Y., Liao, J., Shan, Y.: Video-Holmes: can MLLM think like holmes for complex video reasoning? arXiv preprint arXiv:2505.21374 (2025)"},{"key":"33_CR8","unstructured":"Chu, T., et al.: SFT memorizes, RL generalizes: a comparative study of foundation model post-training. In: Proceedings of the International Conference on Machine Learning (2025)"},{"key":"33_CR9","unstructured":"Cores, D., Dorkenwald, M., Mucientes, M., Snoek, C.G., Asano, Y.M.: Lost in time: a new temporal benchmark for videoLLMs. In: Proceedings of the British Machine Vision Conference (2025)"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Fan, S., Cui, J., Guo, M.H., Yang, S.: Tool-augmented spatiotemporal reasoning for streamlining video question answering task. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-4305"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-R1: reinforcing video reasoning in MLLMs. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-3310"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Fu, C., et\u00a0al.: Video-MME: the first-ever comprehensive evaluation benchmark of multi-modal LLMs in video analysis. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"33_CR13","unstructured":"Google DeepMind, Comanici, G., Bieber, E., et\u00a0al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Han, S., et al.: VideoEspresso: a large-scale chain-of-thought dataset for fine-grained video reasoning via core frame selection. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.02438"},{"key":"33_CR15","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: MVBench: a comprehensive multi-modal video understanding benchmark. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., Ishida, K., Yamazaki, S., Ji, X., Liu, J.: KFS-Bench: comprehensive evaluation of key frame sampling in long video understanding. In: Proceedings of the Winter Conference on Applications of Computer Vision (2026)","DOI":"10.1109\/WACV61042.2026.00547"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLaVA: learning united visual representation by alignment before projection. In: Proceedings of the Empirical Methods in Natural Language Processing (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"33_CR19","unstructured":"Liu, S., et\u00a0al.: VideoAuto-R1: video auto reasoning via thinking once, answering twice. arXiv preprint arXiv:2601.05175 (2026)"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: DrVideo: document retrieval based long video understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.01764"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. In: Proceedings of the Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2004"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Nagrani, A., et al.: MINERVA: Evaluating complex video reasoning. In: Proceedings of the International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.02222"},{"key":"33_CR23","unstructured":"OpenAI: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"33_CR24","unstructured":"OpenAI: OpenAI o3 and o4-mini system card. https:\/\/cdn.openai.com\/pdf\/2221c875-02dc-4789-800b-e7758f3722c1\/o3-and-o4-mini-system-card.pdf (2025)"},{"key":"33_CR25","unstructured":"OpenAI: GPT-5 system card. arXiv preprint arXiv:2601.03267 (2026)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Plizzari, C., Tonioni, A., Xian, Y., Kulshrestha, A., Tombari, F.: Omnia de EgoTempo: benchmarking temporal understanding of multi-modal LLMs in egocentric videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.02247"},{"key":"33_CR27","unstructured":"Qi, Y., et al.: VCR-Bench: a comprehensive evaluation framework for video chain-of-thought reasoning. arXiv preprint arXiv:2504.07956 (2025)"},{"key":"33_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning (2021)"},{"key":"33_CR29","unstructured":"Shen, X., et al.: LongVU: spatiotemporal adaptive compression for long video-language understanding. In: Proceedings of the International Conference on Machine Learning (2025)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Shen, X., Zhang, W., Chen, J., Elhoseiny, M.: Vgent: graph-based retrieval-reasoning-augmented generation for long video understanding. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-3372"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Shu, Y., et al.: Video-XL: extra-long vision language model for hour-scale video understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"33_CR32","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"33_CR33","unstructured":"Swetha, S., et al.: ImplicitQA: going beyond frames towards implicit video reasoning. arXiv preprint arXiv:2506.21742 (2025)"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Tang, X., Qiu, J., Xie, L., Tian, Y., Jiao, J., Ye, Q.: Adaptive keyframe sampling for long video understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: LVBench: an extreme long video understanding benchmark. In: Proceedings of the International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"33_CR36","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: InternVideo2: scaling foundation models for multimodal video understanding. In: Proceedings of the European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: VideoTree: adaptive tree-based video representation for LLM reasoning on long videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3272\u20133283 (2025)","DOI":"10.1109\/CVPR52734.2025.00311"},{"key":"33_CR39","doi-asserted-by":"crossref","unstructured":"Wu, H., Li, D., Chen, B., Li, J.: LongVideoBench: a benchmark for long-context interleaved video-language understanding. In: Proceedings of the Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-0907"},{"key":"33_CR40","unstructured":"Xu, Y., Li, X., Yang, Y., Meng, D., Huang, R., Wang, L.: CareBench: a fine-grained benchmark for video captioning and retrieval. In: Proceedings of the International Conference on Learning Representations (2026)"},{"key":"33_CR41","unstructured":"Xue, Z., et al.: AdavideoRAG: Omni-contextual adaptive retrieval-augmented efficient long video understanding. In: Proceedings of the Neural Information Processing Systems (2025)"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Xun, S., et al.: RTV-Bench: benchmarking MLLM continuous perception, understanding and reasoning through real-time video. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-0600"},{"key":"33_CR43","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"33_CR44","unstructured":"Yang, S., et al.: Towards spatial supersensing in video. In: Proceedings of the International Conference on Learning Representations (2026)"},{"key":"33_CR45","unstructured":"Yeo, W., Kim, K., Yoon, J., Hwang, S.J.: WorldMM: dynamic multimodal memory agent for long video reasoning. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2026)"},{"key":"33_CR46","unstructured":"Yin, X., Peng, X., Li, X., Xiong, Z., Lu, Y.: Hierarchical long video understanding with audiovisual entity cohesion and agentic search. arXiv preprint arXiv:2601.13719 (2026)"},{"key":"33_CR47","unstructured":"Yue, Y., et al.: Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? In: Proceedings of the Neural Information Processing Systems (2025)"},{"key":"33_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zhang, P., Dong, X., Zang, Y., Wang, J.: Long-CLIP: unlocking the long-text capability of clip. In: Proceedings of the European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Deep video discovery: agentic search with tool use for long-form video understanding. In: Proceedings of the Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-3005"},{"key":"33_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: MLVU: benchmarking multi-task long video understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.01278"},{"key":"33_CR51","unstructured":"Zhu, J.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models (2025). arXiv preprint arXiv:2504.10479"},{"key":"33_CR52","unstructured":"Zhu, K., et al.: MMR-v: what\u2019s left unsaid? A benchmark for multimodal deep reasoning in videos. In: Proceedings of the International Conference on Learning Representations (2026)"},{"key":"33_CR53","doi-asserted-by":"crossref","unstructured":"Zohar, O., et\u00a0al.: Apollo: an exploration of video understanding in large multimodal models. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.01760"}],"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\/978-3-032-37095-2_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T07:04:57Z","timestamp":1788851097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37095-2_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370945","9783032370952"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37095-2_33","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":"9 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"}}]}}