{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:12Z","timestamp":1774419432571,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890678","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Find Details in Long Videos: Tower-of-Thoughts and Self-Retrieval Augmented Generation for Video Understanding"],"prefix":"10.1109","author":[{"given":"Tong","family":"Yue","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingrui","family":"Xiao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dafeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Samsung Research China - Beijing (SRC-B)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref2","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models[C]","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref3","first-page":"36","article-title":"Visual instruction tuning[J]","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models[J]","author":"Zhu","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref8","article-title":"Llama: Open and efficient foundation language models[J]","author":"Touvron","year":"2023"},{"issue":"3","key":"ref9","first-page":"6","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality[J]","volume":"2","author":"Chiang","year":"2023"},{"issue":"2024","key":"ref10","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Aligning large multi-modal model with robust instruction tuning[J]","author":"Liu","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref15","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training[J]"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners[J]","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision[C]","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref19","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models[J]","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref21","first-page":"28","article-title":"Deep visual analogy-making[J]","author":"Reed","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"A survey of hallucination in large foundation models","author":"Rawte","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref24","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models[J]","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Internvideo: General video foundation models via generative and discriminative learning[J]","author":"Wang","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref27","article-title":"Vista-llama: Reliable video narrator via equal distance to visual tokens[J]","author":"Ma","year":"2023"},{"key":"ref28","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning[J]","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Self-chained image-language model for video localization and question answering[J]","volume":"36","author":"Yu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_18"},{"key":"ref32","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref35","article-title":"Star: A benchmark for situated reasoning in real-world videos[J]","author":"Wu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref39","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge[J]"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref41","article-title":"Gpt-4 technical report[J]","author":"Achiam","year":"2023"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890678.pdf?arnumber=10890678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:51Z","timestamp":1774416171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890678","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}