{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:03:58Z","timestamp":1789319038880,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375919","type":"print"},{"value":"9783032375926","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\/978-3-032-37592-6_4","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:47:15Z","timestamp":1789318035000},"page":"57-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GuideMe: Multi-domain Task Guidance and\u00a0Intervention in\u00a0Streaming Video"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5763-0172","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0469-4463","authenticated-orcid":false,"given":"Jinpeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5855-3810","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0550-4788","authenticated-orcid":false,"given":"Yuhao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0825-8658","authenticated-orcid":false,"given":"Huankang","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1699-6286","authenticated-orcid":false,"given":"Xudong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0948-9901","authenticated-orcid":false,"given":"Yang","family":"Bo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2388-3542","authenticated-orcid":false,"given":"Gerhard","family":"Hancke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2115-8491","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8957-8129","authenticated-orcid":false,"given":"Rynson W. H.","family":"Lau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"4_CR1","unstructured":"Bai, S., et al.: Qwen3-vl technical report (2025). https:\/\/arxiv.org\/abs\/2511.21631"},{"key":"4_CR2","unstructured":"Bai, S., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"4_CR3","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bao, Y., et al.: Can foundation models watch, talk and guide you step by step to make a cake? In: EMNLP, pp. 12325\u201312341 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.824"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Ben-Shabat, Y., et al.: The ikea ASM dataset: understanding people assembling furniture through actions, objects and pose. In: WACV, pp. 847\u2013859 (2021)","DOI":"10.1109\/WACV48630.2021.00089"},{"key":"4_CR6","unstructured":"ByteDance: Doubao-seed-1.6 (2025). Volcengine ARK Platform"},{"key":"4_CR7","unstructured":"ByteDance: Doubao-seed-1.8 (2026). Volcengine ARK Platform"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Videollm-online: online video large language model for streaming video. In: CVPR, pp. 18407\u201318418 (2024)","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"issue":"11","key":"4_CR11","doi-asserted-by":"publisher","first-page":"4125","DOI":"10.1109\/TPAMI.2020.2991965","volume":"43","author":"D Damen","year":"2020","unstructured":"Damen, D., et al.: The epic-kitchens dataset: collection, challenges and baselines. IEEE TPAMI 43(11), 4125\u20134141 (2020)","journal-title":"IEEE TPAMI"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: Streammind: unlocking full frame rate streaming video dialogue through event-gated cognition. In: ICCV, pp. 13448\u201313459 (2025)","DOI":"10.1109\/ICCV51701.2025.01249"},{"key":"4_CR13","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: CVPR, pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Fu, L., et al.: Ocrbench v2: an improved benchmark for evaluating large multimodal models on visual text localization and reasoning (2024)","DOI":"10.52202\/085713-3253"},{"key":"4_CR15","unstructured":"Google DeepMind: Gemini 3 pro model card (2025). Google DeepMind Model Cards"},{"key":"4_CR16","unstructured":"Google DeepMind: Gemini 3.1 pro model card (2026). Google DeepMind Model Cards"},{"key":"4_CR17","unstructured":"Grauman, K., et\u00a0al.: Ego4d: around the world in 3,000 hours of egocentric video. In: CVPR, pp. 18995\u201319012 (2022)"},{"key":"4_CR18","unstructured":"Grauman, K., et al.: Ego-exo4d: understanding skilled human activity from first-and third-person perspectives, pp. 19383\u201319400. CVPR (2024)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Y., et\u00a0al.: Egoexolearn: a dataset for bridging asynchronous ego-and exo-centric view of procedural activities in real world. In: CVPR, pp. 22072\u201322086 (2024)","DOI":"10.1109\/CVPR52733.2024.02084"},{"key":"4_CR20","unstructured":"Hurst, A., et alpt-4o system card. arXiv preprint hyperimagehttp:\/\/arxiv.org\/abs\/2410.21276arXiv:2410.21276 (2024)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Jang, Y., Sullivan, B., Ludwig, C., Gilchrist, I., Damen, D., Mayol-Cuevas, W.: Epic-tent: An egocentric video dataset for camping tent assembly. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00547"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Lee, S.P., Lu, Z., Zhang, Z., Hoai, M., Elhamifar, E.: Error detection in egocentric procedural task videos. In: CVPR, pp. 18655\u201318666 (2024)","DOI":"10.1109\/CVPR52733.2024.01765"},{"key":"4_CR23","unstructured":"Lin, J., Fang, Z., Chen, C., Wan, Z., Luo, F., Li, P., Liu, Y., Sun, M.: Streamingbench: Assessing the gap for mllms to achieve streaming video understanding. arXiv preprint arXiv:2411.03628 (2024)"},{"key":"4_CR24","unstructured":"Lin, Y., et al.: Hippomm: hippocampal-inspired multimodal memory for long audiovisual event understanding. In: CVPR, pp. 5968\u20135977 (2026)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Referring image segmentation using text supervision. In: ICCV, pp. 22124\u201322134 (2023)","DOI":"10.1109\/ICCV51070.2023.02022"},{"key":"4_CR26","unstructured":"Liu, F., Liu, Y., Xu, K., Hancke, G.P., Lau, R.W.: Gensplat: bridging the generalization gap in 3dgs language comprehension. In: CVPR, pp. 5221\u20135231 (2026)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Liu, F., Liu, Y., Xu, K., Ye, S., Hancke, G.P., Lau, R.W.: Language-guided salient object ranking. In: CVPR, pp. 29803\u201329813 (2025)","DOI":"10.1109\/CVPR52734.2025.02774"},{"key":"4_CR28","unstructured":"Long, L., et al.: Seeing, listening, remembering, and reasoning: a multimodal agent with long-term memory. In: ICLR (2026)"},{"key":"4_CR29","unstructured":"Lu, X., et\u00a0al.: Aura: always-on understanding and real-time assistance via video streams. arXiv preprint arXiv:2604.04184 (2026)"},{"key":"4_CR30","unstructured":"Lu, X., et\u00a0al.: Phostream: benchmarking real-world streaming for omnimodal assistants in mobile scenarios. In: ICML (2026)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: Docvqa: a dataset for VQA on document images. In: WACV, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Niu, J., et al.: Ovo-bench: how far is your video-llms from real-world online video understanding? In: CVPR, pp. 18902\u201318913 (2025)","DOI":"10.1109\/CVPR52734.2025.01761"},{"key":"4_CR34","first-page":"75853","volume":"37","author":"S Panchal","year":"2024","unstructured":"Panchal, S., et al.: What to say and when to say it: live fitness coaching as a testbed for situated interaction. NeurIPS 37, 75853\u201375882 (2024)","journal-title":"NeurIPS"},{"key":"4_CR35","first-page":"135626","volume":"37","author":"R Peddi","year":"2024","unstructured":"Peddi, R., et al.: Captaincook4d: a dataset for understanding errors in procedural activities. NeurIPS 37, 135626\u2013135679 (2024)","journal-title":"NeurIPS"},{"key":"4_CR36","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":"4_CR37","doi-asserted-by":"crossref","unstructured":"Sener, F., et al.: Assembly101: a large-scale multi-view video dataset for understanding procedural activities. In: CVPR, pp. 21096\u201321106 (2022)","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"4_CR38","unstructured":"Singh, A., et\u00a0al.: Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"4_CR39","unstructured":"Sun, P., et\u00a0al.: Spacevista: all-scale visual spatial reasoning from mm to km. In: ICML (2026)"},{"key":"4_CR40","unstructured":"Sun, P., et al.: X-stream: exploring mllms as multiplexers for multi-stream understanding. In: ECCV (2026)"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Coin: a large-scale dataset for comprehensive instructional video analysis. In: CVPR, pp. 1207\u20131216 (2019)","DOI":"10.1109\/CVPR.2019.00130"},{"key":"4_CR42","unstructured":"Team, Q.: Qwen3.5: Accelerating productivity with native multimodal agents (2026). https:\/\/qwen.ai\/blog?id=qwen3.5"},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Streambridge: Turning your offline video large language model into a proactive streaming assistant. arXiv preprint arXiv:2505.05467 (2025)","DOI":"10.52202\/085713-4406"},{"key":"4_CR44","first-page":"95095","volume":"37","author":"K Wang","year":"2024","unstructured":"Wang, K., et al.: Measuring multimodal mathematical reasoning with math-vision dataset. NeurIPS 37, 95095\u201395169 (2024)","journal-title":"NeurIPS"},{"key":"4_CR45","unstructured":"Wang, W., et al.: Internvl3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: Holoassist: an egocentric human interaction dataset for interactive ai assistants in the real world. In: ICCV, pp. 20270\u201320281 (2023)","DOI":"10.1109\/ICCV51070.2023.01854"},{"key":"4_CR47","unstructured":"Wang, Y., et al.: Mmduet2: Enhancing proactive interaction of video mllms with multi-turn reinforcement learning. arXiv preprint arXiv:2512.06810 (2025)"},{"key":"4_CR48","unstructured":"Wang, Y., Meng, X., Wang, Y., Zhang, H., Zhao, D.: Proactivevideoqa: a comprehensive benchmark evaluating proactive interactions in video large language models. arXiv preprint arXiv:2507.09313 (2025)"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, Y., Chen, B., Wu, T., Zhao, D., Zheng, Z.: Omnimmi: a comprehensive multi-modal interaction benchmark in streaming video contexts. In: CVPR, pp. 18925\u201318935 (2025)","DOI":"10.1109\/CVPR52734.2025.01763"},{"key":"4_CR50","unstructured":"Wu, Z., et\u00a0al.: Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"4_CR51","unstructured":"Xu, J., et al.: Qwen3-omni technical report (2025). https:\/\/arxiv.org\/abs\/2509.17765"},{"key":"4_CR52","unstructured":"Xu, R., et al.: Streamingvlm: Real-time understanding for infinite video streams. arXiv preprint arXiv:2510.09608 (2025)"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Yang, J., et\u00a0al.: Egolife: towards egocentric life assistant. In: CVPR, pp. 28885\u201328900 (2025)","DOI":"10.1109\/CVPR52734.2025.02690"},{"key":"4_CR54","unstructured":"Yang, Z., et al.: Svbench: A benchmark with temporal multi-turn dialogues for streaming video understanding. arXiv preprint arXiv:2502.10810 (2025)"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Livestar: Live streaming assistant for real-world online video understanding. arXiv preprint arXiv:2511.05299 (2025)","DOI":"10.52202\/085713-1050"},{"key":"4_CR56","unstructured":"Yu, T., et\u00a0al.: Minicpm-v 4.5: Cooking efficient mllms via architecture, data, and training recipe. arXiv preprint arXiv:2509.18154 (2025)"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Activitynet-qa: a dataset for understanding complex web videos via question answering. In: AAAI, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, R., et\u00a0al.: Mathverse: does your multi-modal LLM truly see the diagrams in visual math problems? In: ECCV, pp. 169\u2013186. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"4_CR59","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. NeurIPS 36, 46595\u201346623 (2023)","journal-title":"NeurIPS"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: AAAI, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12342"}],"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\/978-3-032-37592-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:47:26Z","timestamp":1789318046000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37592-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375919","9783032375926"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37592-6_4","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"}}]}}