{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:03:55Z","timestamp":1789319035219,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368386","type":"print"},{"value":"9783032368393","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\/978-3-032-36839-3_32","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:29:05Z","timestamp":1789316945000},"page":"588-606","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reasoning with\u00a0Memory: A Temporal Granularity-Adaptive Framework for\u00a0Training-Free Long Video Understanding"],"prefix":"10.1007","author":[{"given":"Linghao","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiankun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyuan","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pujin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicheng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"32_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"32_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"32_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"32_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv e-prints pp. arXiv\u20132502 (2025)"},{"key":"32_CR5","unstructured":"Chen, Y., et\u00a0al.: Longvila: Scaling long-context visual language models for long videos. arXiv preprint arXiv:2408.10188 (2024)"},{"key":"32_CR6","unstructured":"Cheng, Z., et\u00a0al.: VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs. arXiv preprint arXiv:2406.07476 (2024)"},{"key":"32_CR7","unstructured":"Fei, J., Li, D., Deng, Z., Wang, Z., Liu, G., Wang, H.: Video-CCAM: Enhancing video-language understanding with causal cross-attention masks for short and long videos. arXiv preprint arXiv:2408.14023 (2024)"},{"key":"32_CR8","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":"32_CR9","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"32_CR10","unstructured":"Ghazanfari, S., Croce, F., Flammarion, N., Krishnamurthy, P., Khorrami, F., Garg, S.: Chain-of-frames: Advancing video understanding in multimodal LLMs via frame-aware reasoning. arXiv preprint arXiv:2506.00318 (2025)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Guo, W., et al.: Logic-in-frames: Dynamic keyframe search via visual semantic-logical verification for long video understanding. arXiv preprint arXiv:2503.13139 (2025)","DOI":"10.52202\/085713-4145"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Hu, K., et al: M-LLM based video frame selection for efficient video understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13702\u201313712 (2025)","DOI":"10.1109\/CVPR52734.2025.01279"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, W., Cao, X., Yuan, L.: Chat-uniVi: Unified visual representation empowers large language models with image and video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13700\u201313710 (2024)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"32_CR14","unstructured":"Li, B., et\u00a0al.: Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"32_CR15","unstructured":"Li, C., et al.: Frameoracle: Learning what to see and how much to see in videos. arXiv preprint arXiv:2510.03584 (2025)"},{"issue":"10","key":"32_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9","volume":"68","author":"K Li","year":"2025","unstructured":"Li, K.: Videochat: chat-centric video understanding. SCIENCE CHINA Inf. Sci. 68(10), 200102 (2025)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"32_CR17","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":"32_CR18","unstructured":"Li, X., et al.: Videochat-r1: Enhancing spatio-temporal perception via reinforcement fine-tuning. arXiv preprint arXiv:2504.06958 (2025)"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: Llama-vid: An image is worth 2 tokens in large language models. In: European Conference on Computer Vision, pp. 323\u2013340. Springer (2024)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"32_CR20","unstructured":"Liang, H., et al.: Keyvideollm: Towards large-scale video keyframe selection. arXiv preprint arXiv:2407.03104 (2024)"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLaVa: Learning united visual representation by alignment before projection. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 5971\u20135984 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"32_CR22","unstructured":"Liu, H., et al.: Llavanext: Improved reasoning, OCR, and world knowledge (2024)"},{"key":"32_CR23","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhao, C., Xu, T., Ghanem, B.: Bolt: Boost large vision-language model without training for long-form video understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3318\u20133327 (2025)","DOI":"10.1109\/CVPR52734.2025.00315"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: Video-ChatGPT: Towards detailed video understanding via large vision and language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12585\u201312602 (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"32_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: Timechat: A time-sensitive multimodal large language model for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14313\u201314323 (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"32_CR28","unstructured":"Shen, X., et al.: LongVU: Spatiotemporal adaptive compression for long video-language understanding. arXiv preprint arXiv:2410.17434 (2024)"},{"key":"32_CR29","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, pp. 26160\u201326169 (2025)","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Song, B., Peng, J., Zhang, Y., Chen, G., Yang, F., Guo, J.: KTV: Keyframes and key tokens selection for efficient training-free video LLMs. arXiv preprint arXiv:2602.03615 (2026)","DOI":"10.1609\/aaai.v40i11.37862"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Song, E., , et\u00a0al.: MovieChat: From dense token to sparse memory for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18221\u201318232 (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Sun, H., et al.: MDP3: A training-free approach for list-wise frame selection in video-LLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 24090\u201324101 (2025)","DOI":"10.1109\/ICCV51701.2025.02233"},{"key":"32_CR33","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, pp. 29118\u201329128 (2025)","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"32_CR34","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: LVBench: An extreme long video understanding benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22958\u201322967 (2025)","DOI":"10.1109\/ICCV51701.2025.02131"},{"key":"32_CR36","unstructured":"Wang, Y., et\u00a0al.: Internvid: A large-scale video-text dataset for multimodal understanding and generation. arXiv preprint arXiv:2307.06942 (2023)"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Internvideo2: Scaling foundation models for multimodal video understanding. In: European Conference on Computer Vision, pp. 396\u2013416. Springer (2024)","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"32_CR38","doi-asserted-by":"publisher","first-page":"28828","DOI":"10.52202\/079017-0907","volume":"37","author":"H Wu","year":"2024","unstructured":"Wu, H., Li, D., Chen, B., Li, J.: Longvideobench: a benchmark for long-context interleaved video-language understanding. Adv. Neural. Inf. Process. Syst. 37, 28828\u201328857 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Generative frame sampler for long video understanding. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 17900\u201317917 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.921"},{"key":"32_CR40","doi-asserted-by":"publisher","first-page":"76749","DOI":"10.52202\/075280-3354","volume":"36","author":"S Yu","year":"2023","unstructured":"Yu, S., Cho, J., Yadav, P., Bansal, M.: Self-chained image-language model for video localization and question answering. Adv. Neural. Inf. Process. Syst. 36, 76749\u201376771 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR41","unstructured":"Yu, S., et\u00a0al.: Frame-voyager: Learning to query frames for video large language models. arXiv preprint arXiv:2410.03226 (2024)"},{"key":"32_CR42","unstructured":"Zhang, B., et\u00a0al.: Videollama 3: Frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106 (2025)"},{"key":"32_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: A simple LLM framework for long-range video question-answering. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 21715\u201321737 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wan, Z., Hu, L., Lin, S., Wu, S., Shan, S.: Collaboratively self-supervised video representation learning for action recognition. IEEE Trans. Inf. Forensics Secur. (2025)","DOI":"10.1109\/TIFS.2025.3531772"},{"key":"32_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wan, Z., Nie, S., Li, C., Shan, S., Chen, X.: BIMM: Brain inspired masked modeling for video representation learning. In: IEEE Transactions on Circuits and Systems for Video Technology, (2026)","DOI":"10.1109\/TCSVT.2026.3683701"},{"key":"32_CR46","unstructured":"Zhang, P., et al.: Long context transfer from language to vision. arXiv preprint arXiv:2406.16852 (2024)"},{"key":"32_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yang, J., Yin, J., Luo, Z., Luan, J.: Q-frame: Query-aware frame selection and multi-resolution adaptation for video-LLMs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22056\u201322065 (2025)","DOI":"10.1109\/ICCV51701.2025.02048"},{"key":"32_CR48","unstructured":"Zhang, Y., et al.: LLaVa-video: Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"32_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, Y., Wang, T., Rao, F., Yang, Y., Zhu, L.: Flexselect: Flexible token selection for efficient long video understanding, (2025). arXiv:2506.00993 arXiv preprint","DOI":"10.52202\/085713-3435"},{"key":"32_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, M., Yu, Y., Wang, X., Yang, L., Niu, D.: Search-map-search: a frame selection paradigm for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10627\u201310636 (2023)","DOI":"10.1109\/CVPR52729.2023.01024"},{"key":"32_CR51","unstructured":"Zhou, J., et al.: M: A comprehensive benchmark for multi-task long video understanding. arXiv preprint (2024)"},{"key":"32_CR52","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)"},{"key":"32_CR53","unstructured":"Zhu, Z., et al.: Focus: Efficient keyframe selection for long video understanding. arXiv preprint arXiv:2510.27280 (2025)"}],"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\/978-3-032-36839-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:29:14Z","timestamp":1789316954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36839-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368386","9783032368393"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36839-3_32","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":"14 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"}}]}}