{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:01:47Z","timestamp":1789718507835,"version":"4.0.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","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\/978-3-032-37174-4_26","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:04:01Z","timestamp":1789715041000},"page":"437-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["H$$^2$$SVC: Head-Aware Heterogeneous Streaming Video Cache for Online Video Understanding"],"prefix":"10.1007","author":[{"given":"Han","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junni","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Ainslie, J., Lee-Thorp, J., De Jong, M., Zemlyanskiy, Y., Lebr\u00f3n, F., Sanghai, S.: GQA: training generalized multi-query transformer models from multi-head checkpoints. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 4895\u20134901 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"26_CR2","unstructured":"Bai, S., et al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"26_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":"26_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":"26_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"},{"issue":"12","key":"26_CR6","doi-asserted-by":"publisher","first-page":"220101","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen, Z., et al.: How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites. SCIENCE CHINA Inf. Sci. 67(12), 220101 (2024)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"26_CR7","unstructured":"Cheng, Z., et al.: VideoLLaMA 2: advancing spatial-temporal modeling and audio understanding in video-LLMs. arXiv preprint arXiv:2406.07476 (2024)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: FlashAttention: fast and memory-efficient exact attention with io-awareness. In: Advances in Neural Information Processing Systems, vol. 35, pp. 16344\u201316359 (2022)","DOI":"10.52202\/068431-1189"},{"key":"26_CR9","unstructured":"Di, S., et al.: Streaming video question-answering with in-context video KV-cache retrieval. arXiv preprint arXiv:2503.00540 (2025)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Fu, C., et al.: 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":"26_CR11","unstructured":"Hu, S., et al.: MiniCPM: unveiling the potential of small language models with scalable training strategies. arXiv preprint arXiv:2404.06395 (2024)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Kim, M., Shim, K., Choi, J., Chang, S.: InfiniPot-V: memory-constrained KV cache compression for streaming video understanding. arXiv preprint arXiv:2506.15745 (2025)","DOI":"10.52202\/085713-4639"},{"key":"26_CR13","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"26_CR14","unstructured":"Li, H., et al.: OneCAT: decoder-only auto-regressive model for unified understanding and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 30235\u201330245 (2026)"},{"issue":"10","key":"26_CR15","doi-asserted-by":"publisher","first-page":"200102","DOI":"10.1007\/s11432-024-4321-9","volume":"68","author":"K Li","year":"2025","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. SCIENCE CHINA Inf. Sci. 68(10), 200102 (2025)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: SnapKV: LLM knows what you are looking for before generation. In: Advances in Neural Information Processing Systems, vol. 37, pp. 22947\u201322970 (2024)","DOI":"10.52202\/079017-0722"},{"key":"26_CR17","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":"26_CR18","unstructured":"Lin, J., et al.: StreamingBench: assessing the gap for MLLMs to achieve streaming video understanding. arXiv preprint arXiv:2411.03628 (2024)"},{"key":"26_CR19","unstructured":"Liu, A.: DeepSeek-V3.2: pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556 (2025)"},{"key":"26_CR20","unstructured":"Liu, J., et al.: Kangaroo: a powerful video-language model supporting long-context video input. arXiv preprint arXiv:2408.15542 (2024)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. In: Advances in Neural Information Processing Systems, vol. 36, pp. 46212\u201346244 (2023)","DOI":"10.52202\/075280-2004"},{"key":"26_CR22","unstructured":"Ning, Z., Liu, G., Jin, Q., Ding, W., Guo, M., Zhao, J.: LiveVLM: efficient online video understanding via streaming-oriented KV cache and retrieval. arXiv preprint arXiv:2505.15269 (2025)"},{"key":"26_CR23","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":"26_CR24","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":"26_CR25","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":"26_CR26","doi-asserted-by":"crossref","unstructured":"Song, E., et al.: 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":"26_CR27","doi-asserted-by":"publisher","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"26_CR28","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"26_CR29","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)"},{"key":"26_CR30","unstructured":"Xu, R., et al.: StreamingVLM: real-time understanding for infinite video streams. arXiv preprint arXiv:2510.09608 (2025)"},{"key":"26_CR31","unstructured":"Yang, Y., et al.: StreamMem: query-agnostic KV cache memory for streaming video understanding. arXiv preprint arXiv:2508.15717 (2025)"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: 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":"26_CR33","doi-asserted-by":"crossref","unstructured":"Zeng, X., et al.: StreamForest: efficient online video understanding with persistent event memory. arXiv preprint arXiv:2509.24871 (2025)","DOI":"10.52202\/085713-2547"},{"key":"26_CR34","unstructured":"Zhang, C., et al.: Efficient context scaling with LongCat zigzag attention (2026)"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Flash-VStream: memory-based real-time understanding for long video streams. arXiv preprint arXiv:2406.08085 (2024)","DOI":"10.1109\/ICCV51701.2025.01957"},{"key":"26_CR36","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. arXiv preprint arXiv:2601.14724 (2026)","DOI":"10.18653\/v1\/2026.acl-long.381"},{"key":"26_CR37","unstructured":"Zhang, P., et al: Long context transfer from language to vision. arXiv preprint arXiv:2406.16852 (2024)"},{"key":"26_CR38","unstructured":"Zhang, Y., et al.: LLaVA-Video: video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: H2o: heavy-hitter oracle for efficient generative inference of large language models. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34661\u201334710 (2023)","DOI":"10.52202\/075280-1506"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: MLVU: benchmarking multi-task long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13691\u201313701 (2025)","DOI":"10.1109\/CVPR52734.2025.01278"}],"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\/978-3-032-37174-4_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:04:19Z","timestamp":1789715059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_26","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":"19 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"}}]}}