{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T22:05:36Z","timestamp":1770933936829,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2059"],"award-info":[{"award-number":["U22B2059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62276083"],"award-info":[{"award-number":["62276083"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019356","name":"5G Application Innovation Joint Research Institute\u2019s Project","doi-asserted-by":"publisher","award":["A003"],"award-info":[{"award-number":["A003"]}],"id":[{"id":"10.13039\/501100019356","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3609803","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:35:46Z","timestamp":1758044146000},"page":"1754-1765","source":"Crossref","is-referenced-by-count":0,"title":["APSam: An Aggregating-Then-Pruning Sampler for Question-Conditional Denoising"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5747-6187","authenticated-orcid":false,"given":"Jiafeng","family":"Liang","sequence":"first","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"}]},{"given":"Shixin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"}]},{"given":"Wei","family":"Tang","sequence":"additional","affiliation":[{"name":"State Grid Anhui Electric Power Research Institute, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4937-6784","authenticated-orcid":false,"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"resides, Shanghai, China"}]},{"given":"Zekun","family":"Wang","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7163-9560","authenticated-orcid":false,"given":"Xun","family":"Mao","sequence":"additional","affiliation":[{"name":"State Grid Anhui Electric Power Research Institute, Hefei, China"}]},{"given":"Kai","family":"Lv","sequence":"additional","affiliation":[{"name":"State Grid Anhui Electric Power Research Institute, Hefei, China"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2543-5604","authenticated-orcid":false,"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref2","first-page":"76749","article-title":"Self-chained image-language model for video localization and question answering","volume-title":"Proc. NeurIPS","author":"Yu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.556"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3527032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287201"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3475510"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref9","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"issue":"3","key":"ref10","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref11","article-title":"AGQA 2.0: An updated benchmark for compositional spatio-temporal reasoning","author":"Grunde-McLaughlin","year":"2022","journal-title":"arXiv:2204.06105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref13","first-page":"1","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3490665"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076556"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00680"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19922"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.442"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref28","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00117"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612577"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3546312"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612345"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.66"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.608"},{"key":"ref38","first-page":"1","article-title":"SmartTrim: Adaptive tokens and attention pruning for efficient vision-language models","volume-title":"Proc. LREC\/COLING","author":"Wang"},{"key":"ref39","article-title":"Efficient prompting via dynamic in-context learning","author":"Zhou","year":"2023","journal-title":"arXiv:2305.11170"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3434626"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref43","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. ICLR","author":"Jang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref48","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref51","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref56","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"ref58","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref60","first-page":"28828","article-title":"LongVideoBench: A benchmark for long-context interleaved video-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Wu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11164879.pdf?arnumber=11164879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:49Z","timestamp":1770930169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3609803","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}