{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:11:52Z","timestamp":1789074712410,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368454","type":"print"},{"value":"9783032368461","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\/978-3-032-36846-1_5","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:02:34Z","timestamp":1789074154000},"page":"73-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evidence-Backed Video Question Answering"],"prefix":"10.1007","author":[{"given":"Shijie","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiming","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"5_CR1","unstructured":"Ahmad, G.S., et al.: VideoMolmo: Spatio-temporal grounding meets pointing. arXiv preprint arXiv:2506.05336 (2025)"},{"key":"5_CR2","unstructured":"An, X., et al.: LLaVA-OneVision-1.5: Fully open framework for democratized multimodal training. arXiv preprint arXiv:2509.23661 (2025)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Athar, A., Deng, X., Chen, L.C.: ViCaS: a dataset for combining holistic and pixel-level video understanding using captions with grounded segmentation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01772"},{"key":"5_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report (2025). https:\/\/arxiv.org\/abs\/2502.13923. Accessed 26 June 2026"},{"key":"5_CR5","doi-asserted-by":"publisher","first-page":"6833","DOI":"10.52202\/079017-0219","volume":"37","author":"Z Bai","year":"2024","unstructured":"Bai, Z., et al.: One token to seg them all: language instructed reasoning segmentation in videos. Adv. Neural. Inf. Process. Syst. 37, 6833\u20136859 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR6","unstructured":"Carion, N., et al.: SAM 3: segment anything with concepts (2025). https:\/\/arxiv.org\/abs\/2511.16719. Accessed 26 June 2026"},{"key":"5_CR7","unstructured":"Chen, G., et al.: CG-Bench: clue-grounded question answering benchmark for long video understanding. arXiv preprint arXiv:2412.12075 (2024)"},{"key":"5_CR8","unstructured":"Cheng, Z., Hu, J., Liu, Z., Si, C., Li, W., Gong, S.: V-STaR: benchmarking Video-LLMs on video spatio-temporal reasoning (2025). https:\/\/arxiv.org\/abs\/2503.11495. Accessed 26 June 2026"},{"key":"5_CR9","unstructured":"Comanici, G., et\u00a0al.: Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities (2025). https:\/\/arxiv.org\/abs\/2507.06261. Accessed 26 June 2026"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Deng, A., et al.: Motion-grounded video reasoning: understanding and perceiving motion at pixel level. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8625\u20138636 (2025)","DOI":"10.1109\/CVPR52734.2025.00806"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., He, S., Jiang, X., Loy, C.C.: MeViS: a large-scale benchmark for video segmentation with motion expressions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2694\u20132703 (2023)","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-R1: reinforcing video reasoning in MLLMs. arXiv preprint arXiv:2503.21776 (2025)","DOI":"10.52202\/085713-3310"},{"key":"5_CR13","unstructured":"Gong, S., Zhang, L., Zhuge, Y., Jia, X., Zhang, P., Lu, H.: Reinforcing video reasoning segmentation to think before it segments. arXiv preprint arXiv:2508.11538 (2025)"},{"key":"5_CR14","unstructured":"Grauman, K.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Y., Liu, J., Li, M., Tang, X., Chen, X., Zhao, B.: VTG-LLM: integrating timestamp knowledge into video LLMs for enhanced video temporal grounding. arXiv preprint arXiv:2405.13382 (2024)","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"5_CR16","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, pp. 26181\u201326191 (2025)","DOI":"10.1109\/CVPR52734.2025.02438"},{"key":"5_CR17","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, X., Chen, H., Song, Z., Zhu, W.: VTimeLLM: empower LLM to grasp video moments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14271\u201314280 (2024)","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"5_CR19","unstructured":"Jin, W., Kim, S., Lee, J., Kim, S.: InterRVOS: interaction-aware referring video object segmentation. arXiv preprint arXiv:2506.02356 (2025)"},{"key":"5_CR20","doi-asserted-by":"publisher","unstructured":"Lei, J., Yu, L., Berg, T., Bansal, M.: TVQA+: spatio-temporal grounding for video question answering. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 8211\u20138225 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.730","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: MVBench: a comprehensive multi-modal video understanding benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22195\u201322206 (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"5_CR22","unstructured":"Li, X., et al.: VideoChat-R1: enhancing spatio-temporal perception via reinforcement fine-tuning. arXiv preprint arXiv:2504.06958 (2025)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Xiao, J., Feng, C., Wang, X., Chua, T.S.: Discovering spatio-temporal rationales for video question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13869\u201313878 (2023)","DOI":"10.1109\/ICCV51070.2023.01275"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Liang, S., Zhong, Y., Hu, Z.Y., Tao, Y., Wang, L.: Fine-grained spatiotemporal grounding on egocentric videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9385\u20139395 (2025)","DOI":"10.1109\/ICCV51701.2025.00876"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Lin, L., Yu, X., Pang, Z., Wang, Y.X.: GLUS: global-local reasoning unified into a single large language model for video segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8658\u20138667 (2025)","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"5_CR26","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":"5_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: UniPixel: unified object referring and segmentation for pixel-level visual reasoning. In: Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-4203"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Lu, Y., Song, Y., Wang, W., Torresani, L., Nagarajan, T.: VITED: video temporal evidence distillation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8501\u20138511 (2025)","DOI":"10.1109\/CVPR52734.2025.00795"},{"key":"5_CR29","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: VideoGPT+: Integrating image and video encoders for enhanced video understanding. arXiv preprint arXiv:2406.09418 (2024)"},{"key":"5_CR30","unstructured":"Meng, J., et\u00a0al.: Open-o3 Video: Grounded video reasoning with explicit spatio-temporal evidence. arXiv preprint arXiv:2510.20579 (2025)"},{"key":"5_CR31","unstructured":"Munasinghe, S., et al.: VideoGLaMM: A large multimodal model for pixel-level visual grounding in videos. ArXiv (2024). https:\/\/arxiv.org\/abs\/2411.04923. Accessed 26 June 2026"},{"key":"5_CR32","unstructured":"OpenAI: GPT-4o system card (2024). https:\/\/arxiv.org\/abs\/2410.21276. Accessed 26 June 2026"},{"key":"5_CR33","unstructured":"OpenAI: OpenAI o3 model (2024). https:\/\/platform.openai.com\/docs\/models\/o3. Accessed 14 Nov. 2025"},{"key":"5_CR34","doi-asserted-by":"publisher","first-page":"42748","DOI":"10.52202\/075280-1852","volume":"36","author":"V Patraucean","year":"2023","unstructured":"Patraucean, V., et al.: Perception test: a diagnostic benchmark for multimodal video models. Adv. Neural. Inf. Process. Syst. 36, 42748\u201342761 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR35","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"5_CR36","unstructured":"Qian, L., et al.: Momentor: advancing video large language model with fine-grained temporal reasoning. arXiv preprint arXiv:2402.11435 (2024)"},{"key":"5_CR37","unstructured":"Qwen Team: Qwen3-VL: sharper vision, deeper thought, broader action (2025). https:\/\/qwen.ai\/blog?id=99f0335c4ad9ff6153e517418d48535ab6d8afef. Accessed 13 Nov. 2025"},{"key":"5_CR38","unstructured":"Ravi, N., et\u00a0al.: SAM 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Seo, S., Lee, J.Y., Han, B.: URVOS: unified referring video object segmentation network with a large-scale benchmark. In: European Conference on Computer Vision, pp. 208\u2013223. Springer (2020)","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zhang, H., Ding, H., Zhang, T., Ma, X., Jiang, Y.G.: SAMA: towards multi-turn referential grounded video chat with large language models. arXiv preprint arXiv:2505.18812 (2025)","DOI":"10.52202\/085713-1568"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Towards open-vocabulary video instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4057\u20134066 (2023)","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"5_CR42","unstructured":"Wang, J., et\u00a0al.: VGR: visual grounded reasoning. arXiv preprint arXiv:2506.11991 (2025)"},{"key":"5_CR43","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Time-R1: post-training large vision language model for temporal video grounding. arXiv preprint arXiv:2503.13377 (2025)","DOI":"10.52202\/085713-2793"},{"key":"5_CR45","doi-asserted-by":"publisher","unstructured":"Wang, Y., Wang, Y., Chen, K., Zhao, D.: STAIR: spatial-temporal reasoning with auditable intermediate results for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38(17), pp. 19215\u201319223 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i17.29890","DOI":"10.1609\/aaai.v38i17.29890"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yoon, J., Yu, S., Islam, M.M., Bertasius, G., Bansal, M.: Video-RTS: rethinking reinforcement learning and test-time scaling for efficient and enhanced video reasoning. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 28114\u201328128 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1428"},{"key":"5_CR47","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR48","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., Gan, C.: Star: a benchmark for situated reasoning in real-world videos. In: NeurIPS (2021)"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Number it: Temporal grounding videos like flipping manga. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13754\u201313765 (2025)","DOI":"10.1109\/CVPR52734.2025.01284"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: NeXT-QA: next phase of question-answering to explaining temporal actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9777\u20139786 (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Li, Y., Chua, T.S.: Can i trust your answer? Visually grounded video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13204\u201313214 (2024)","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Yan, C., et al.: VISA: reasoning video object segmentation via large language models. In: European Conference on Computer Vision, pp. 98\u2013115. Springer (2024)","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"5_CR53","unstructured":"Yi, K., et al.: CLEVRER: collision events for video representation and reasoning. In: ICLR (2020)"},{"key":"5_CR54","unstructured":"You, Z., Wu, Z.: Seg-R1: Segmentation can be surprisingly simple with reinforcement learning. arXiv preprint arXiv:2506.22624 (2025)"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Sa2VA: marrying SAM 2 with LLaVA for dense grounded understanding of images and videos. arXiv preprint arXiv:2501.04001 (2025)","DOI":"10.1109\/TPAMI.2026.3720379"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et\u00a0al.: VideoRefer suite: advancing spatial-temporal object understanding with video LLM. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18970\u201318980 (2025)","DOI":"10.1109\/CVPR52734.2025.01767"},{"key":"5_CR57","unstructured":"Zhang, B.: VideoLLaMA 3: frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106 (2025)"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, H., et al.: STRefer: empowering video LLMs with space-time referring and reasoning via synthetic instruction data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4289\u20134300 (2025)","DOI":"10.1109\/ICCVW69036.2025.00451"}],"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\/978-3-032-36846-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:02:43Z","timestamp":1789074163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36846-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368454","9783032368461"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36846-1_5","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"}}]}}