{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:02:24Z","timestamp":1783180944383,"version":"3.54.6"},"reference-count":97,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01532","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16503-16513","source":"Crossref","is-referenced-by-count":1,"title":["Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation"],"prefix":"10.1109","author":[{"given":"Junyu","family":"Xie","sequence":"first","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengda","family":"Han","sequence":"additional","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max","family":"Bain","sequence":"additional","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arsha","family":"Nagrani","sequence":"additional","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eshika","family":"Khandelwal","sequence":"additional","affiliation":[{"name":"IIIT,CVIT,Hyderabad"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidi","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[{"name":"University of Oxford,Visual Geometry Group"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Guidelines for audio describers"},{"key":"ref2","volume-title":"Audiovault"},{"key":"ref3","volume-title":"Pyscenedetect"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref7","article-title":"Condensed movies: Story based retrieval with contextual embeddings","author":"Bain","year":"2020","journal-title":"ACCV"},{"key":"ref8","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw54120.2021.00357"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00215"},{"key":"ref11","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"Chen","year":"2011","journal-title":"A C L"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00832"},{"key":"ref13","article-title":"Timemarker: A versatile video-llm for long and short video understanding with superior temporal localization ability","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Panda-70m: Captioning 70 m videos with multiple cross-modality teachers","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13111-8"},{"key":"ref16","article-title":"LLM-AD: Large language model based audio description system","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00030"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01267"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447306"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"ref22","article-title":"Trace: Temporal grounding video llm via causal event modeling","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01815"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01255"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01720"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref27","article-title":"Thread-safe: Towards recognizing human actions across shot boundaries","author":"Hoai","year":"2014","journal-title":"ACCV"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.29"},{"key":"ref33","article-title":"Multi-modal dense video captioning","volume-title":"CVPR Workshops on Multimodal Learning","author":"Iashin","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01723"},{"key":"ref35","article-title":"Space-time correspondence as a contrastive random walk","author":"Jabri","year":"2020","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092143"},{"key":"ref37","article-title":"Film Directing Shot by Shot: Visualizing from Concept to Screen","volume-title":"Michael Wiese Productions","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12194174"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.360"},{"key":"ref44","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02928-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3048482"},{"key":"ref48","article-title":"The llama 3 herd of models","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref50","volume-title":"How to Read a Film: Movies, Media, and Beyond. OUP","author":"Monaco","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00675"},{"key":"ref52","volume-title":"the Blink of an Eye: A Perspective on Film Editing","author":"Murch","year":"2021"},{"key":"ref53","article-title":"Gpt-4 technical report","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref55","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_39"},{"key":"ref57","article-title":"Matchdiffusion: Training-free generation of match-cuts","author":"Pardo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"It\u2019s just another day: Unique video captioning by discriminative prompting","author":"Perrett","year":"2024","journal-title":"ACCV"},{"key":"ref59","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024","journal-title":"ICML"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00900"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_2"},{"key":"ref63","article-title":"Temporal and contextual transformer for multi-camera editing of tv shows","volume-title":"Proceedings of the CVEU Workshop at ICCV","author":"Rao","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3604321.3604334"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00794"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/2683483.2683490"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11101570"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00784"},{"key":"ref73","article-title":"Groundedvideollm: Sharpening fine-grained temporal grounding in video large language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref75","article-title":"Qwen2vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445347"},{"key":"ref79","article-title":"Hawkeye: Training video-text llms for grounding text in videos","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01769"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01284"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_5"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.63317\/4s5pfq3wxzuq"},{"key":"ref87","year":"2023","journal-title":"Videoblip"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01295"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref91","article-title":"Bertscore: Evaluating text generation with bert","year":"2020","journal-title":"ICLR"},{"key":"ref92","article-title":"Representation learning of next shot selection for vlog editing","volume-title":"Proceedings of the CVEU Workshop at ICCV","author":"Zhang","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_2"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444363.pdf?arnumber=11444363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:34Z","timestamp":1777529494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01532","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}