{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:09:23Z","timestamp":1789373363667,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372543","type":"print"},{"value":"9783032372550","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\/978-3-032-37255-0_33","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:00:54Z","timestamp":1789372854000},"page":"605-623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CurveStream: Boosting Streaming Video Understanding in\u00a0MLLMs via\u00a0Curvature-Aware Hierarchical Visual Memory Management"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5703-7580","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6008-5789","authenticated-orcid":false,"given":"Xudong","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-3956","authenticated-orcid":false,"given":"Jianjian","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6998-780X","authenticated-orcid":false,"given":"Kangcong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"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 al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: VideoLLM-online: online video large language model for streaming video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18407\u201318418 (2024)","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"33_CR4","unstructured":"Chen, X., Tao, K., Shao, K., Wang, H.: StreamingTOM: Streaming token compression for efficient video understanding. arXiv preprint arXiv:2510.18269 (2025)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: StreamKV: Streaming video question-answering with segment-based KV cache retrieval and compression. arXiv preprint arXiv:2511.07278 (2025)","DOI":"10.1609\/aaai.v40i4.37305"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"33_CR7","unstructured":"Cheng, Z., et al.: VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs. arXiv preprint arXiv:2406.07476 (2024). https:\/\/arxiv.org\/abs\/2406.07476"},{"key":"33_CR8","unstructured":"Cho, J., Lee, J., Hayat, M., Hwang, K., Porikli, F., Choi, S.: FLoC: Facility location-based efficient visual token compression for long video understanding. arXiv preprint arXiv:2511.00141 (2025)"},{"key":"33_CR9","unstructured":"Di, S., et\u00a0al.: Streaming video question-answering with in-context video KV-cache retrieval. In: ICLR (2025)"},{"key":"33_CR10","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":"33_CR11","doi-asserted-by":"crossref","unstructured":"Gao, H., Bao, Y., Tu, X., Zhong, B., Yue, L., Zhang, M.: APVR: Hour-level long video understanding with adaptive pivot visual information retrieval. arXiv preprint arXiv:2506.04953 (2025)","DOI":"10.1609\/aaai.v40i6.42406"},{"key":"33_CR12","unstructured":"Guan, Y., et al.: Video streaming thinking: VideoLLMs can watch and think simultaneously. arXiv preprint arXiv:2603.12262 (2026)"},{"key":"33_CR13","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":"33_CR14","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"33_CR15","unstructured":"Jiang, T., et al.: Imagine before you predict: Interleaved latent visual reasoning for video event prediction. arXiv preprint arXiv:2606.05769 (2026)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Kim, M., Shim, K., Choi, J., Chang, S.: InfiniPot-V: memory-constrained KV cache compression for streaming video understanding. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=hFxOZjHyTg","DOI":"10.52202\/085713-4639"},{"key":"33_CR17","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"33_CR18","unstructured":"Li, J., Li, B., Li, J., Lu, Y.: Divide, then ground: adapting frame selection to query types for long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11369\u201311380 (2026)"},{"key":"33_CR19","unstructured":"Li, K., Ye, P., Zhang, L., Wang, C., Qin, H., Chen, T.: FreshMem: Brain-inspired frequency-space hybrid memory for streaming video understanding. arXiv preprint arXiv:2602.01683 (2026)"},{"issue":"10","key":"33_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9","volume":"68","author":"K Li","year":"2025","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. Sci. China Inf. Sci. 68(10), 200102 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"33_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":"33_CR22","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":"33_CR23","unstructured":"Lin, J., et al.: StreamingBench: Assessing the gap for MLLMs to achieve streaming video understanding. arXiv preprint arXiv:2411.03628 (2024)"},{"key":"33_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":"33_CR25","first-page":"102751","volume":"38","author":"Y Lu","year":"2026","unstructured":"Lu, Y., Wang, T., Rao, F., Yang, Y., Zhu, L., et al.: FlexSelect: flexible token selection for efficient long video understanding. Adv. Neural. Inf. Process. Syst. 38, 102751\u2013102777 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR26","doi-asserted-by":"publisher","first-page":"46212","DOI":"10.52202\/075280-2004","volume":"36","author":"K Mangalam","year":"2023","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. Adv. Neural. Inf. Process. Syst. 36, 46212\u201346244 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Niu, J., et al.: OVO-Bench: how far is your video-LLMs from real-world online video understanding? In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18902\u201318913 (2025)","DOI":"10.1109\/CVPR52734.2025.01761"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Dispider: enabling video LLMs with active real-time interaction via disentangled perception, decision, and reaction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24045\u201324055 (2025)","DOI":"10.1109\/CVPR52734.2025.02239"},{"key":"33_CR29","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":"33_CR30","unstructured":"Team, G., et\u00a0al.: Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024). https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Tu, C., et al.: FAVOR-Bench: A comprehensive benchmark for fine-grained video motion understanding. arXiv preprint arXiv:2503.14935 (2025)","DOI":"10.52202\/085713-4791"},{"key":"33_CR32","unstructured":"Wang, L., et al.: Think while watching: Online streaming segment-level memory for multi-turn video reasoning in multimodal large language models. arXiv preprint arXiv:2603.11896 (2026)"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Wang, M., Chen, S., Kersting, K., Tresp, V., Ma, Y.: METok: multi-stage event-based token compression for efficient long video understanding. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 18881\u201318895 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.954"},{"key":"33_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":"33_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Song, Y., Xie, C., Liu, Y., Zheng, Z.: VideoLLaMB: long streaming video understanding with recurrent memory bridges. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 24170\u201324181 (2025)","DOI":"10.1109\/ICCV51701.2025.02240"},{"key":"33_CR36","unstructured":"Xiong, H., et al.: Streaming video understanding and multi-round interaction with memory-enhanced knowledge. arXiv preprint arXiv:2501.13468 (2025)"},{"key":"33_CR37","unstructured":"Xu, R., et al.: StreamingVLM: Real-time understanding for infinite video streams. arXiv preprint arXiv:2510.09608 (2025)"},{"key":"33_CR38","unstructured":"Yang, S., et\u00a0al.: Cambrian-S: towards spatial supersensing in video. In: The Fourteenth International Conference on Learning Representations (2025)"},{"key":"33_CR39","unstructured":"Yang, Y., et al.: StreamMem: Query-agnostic KV cache memory for streaming video understanding. arXiv preprint arXiv:2508.15717 (2025)"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Yao, L., et\u00a0al.: TimeChat-online: 80% visual tokens are naturally redundant in streaming videos. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 10807\u201310816 (2025)","DOI":"10.1145\/3746027.3754839"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Ye, J., et al.: Re-thinking temporal search for long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8579\u20138591 (2025)","DOI":"10.1109\/CVPR52734.2025.00802"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Ye, S., et al.: Venus: An efficient edge memory-and-retrieval system for VLM-based online video understanding. arXiv preprint arXiv:2512.07344 (2025)","DOI":"10.1109\/INFOCOM59046.2026.11571630"},{"key":"33_CR43","unstructured":"Yuan, H., et al.: Memory-enhanced retrieval augmentation for long video understanding. arXiv preprint arXiv:2503.09149 (2025)"},{"key":"33_CR44","doi-asserted-by":"crossref","unstructured":"Zeng, X., et\u00a0al.: StreamForest: Efficient online video understanding with persistent event memory. arXiv preprint arXiv:2509.24871 (2025)","DOI":"10.52202\/085713-2547"},{"key":"33_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Tang, Y., Liu, Y., Feng, J., Jin, X.: Flash-VStream: efficient real-time understanding for long video streams. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21059\u201321069 (2025)","DOI":"10.1109\/ICCV51701.2025.01957"},{"key":"33_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yang, S., Fu, J., Ng, S.K., Qiu, X.: HERMES: KV cache as hierarchical memory for efficient streaming video understanding (2026). https:\/\/arxiv.org\/abs\/2601.14724","DOI":"10.18653\/v1\/2026.acl-long.381"},{"key":"33_CR47","unstructured":"Zhang, X., et al.: GPT-4V(ision) as a generalist evaluator for vision-language tasks. arXiv preprint arXiv:2311.01361 (2023)"},{"key":"33_CR48","unstructured":"Zhang, Y., et al.: LLaVA-Next: A strong zero-shot video understanding model (2024). https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"33_CR49","unstructured":"Zhang, Y., et al.: LLaVA-Video: Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"33_CR50","doi-asserted-by":"crossref","unstructured":"Zuo, J., et al.: VideoLucy: Deep memory backtracking for long video understanding. arXiv preprint arXiv:2510.12422 (2025)","DOI":"10.52202\/085713-0864"}],"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\/978-3-032-37255-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:01:22Z","timestamp":1789372882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37255-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372543","9783032372550"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37255-0_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":"15 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"}}]}}