{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T21:31:32Z","timestamp":1781127092180,"version":"3.54.1"},"reference-count":105,"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\/iccv51701.2025.01801","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19373-19385","source":"Crossref","is-referenced-by-count":1,"title":["AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation"],"prefix":"10.1109","author":[{"given":"Moayed","family":"Haji-Ali","sequence":"first","affiliation":[{"name":"Rice University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Willi","family":"Menapace","sequence":"additional","affiliation":[{"name":"Snap Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aliaksandr","family":"Siarohin","sequence":"additional","affiliation":[{"name":"Snap Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Skorokhodov","sequence":"additional","affiliation":[{"name":"Snap Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alper","family":"Canberk","sequence":"additional","affiliation":[{"name":"Snap Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwot Sin","family":"Lee","sequence":"additional","affiliation":[{"name":"Snap Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vicente","family":"Ordonez","sequence":"additional","affiliation":[{"name":"Rice University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Tulyakov","sequence":"additional","affiliation":[{"name":"Snap Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"7523","article-title":"Vidstyleode: Disentangled video editing via stylegan and neuralodes","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Haji Ali","year":"2023"},{"key":"ref2","article-title":"Label-efficient semantic segmentation with diffusion models","author":"Baranchuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Sonicdiffusion: Audio-driven image generation and editing with pretrained diffusion models","author":"Can Biner","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv:2311.15127"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","article-title":"The mtg-jamendo dataset for automatic music tagging","volume-title":"Machine Learning for Music Discovery Workshop, ICML (ICML 2019)","author":"Bogdanov","year":"2019"},{"key":"ref7","article-title":"Video generation models as world simulators","volume":"1","author":"Brooks","year":"2024","journal-title":"OpenAI Blog"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_16"},{"key":"ref9","author":"Chen","year":"2024","journal-title":"Semantically consistent video-to-audio generation using multimodal language large model"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref11","first-page":"5178","article-title":"Beats: audio pre-training with acoustic tokenizers","volume-title":"ICML","author":"Chen","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01749"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01749"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02691"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888085"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_1"},{"key":"ref19","article-title":"FMA: A dataset for music analysis","volume-title":"18th International Society for Music Information Retrieval Conference (ISMIR)","author":"Defferrard","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref22","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref23","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"ICML","author":"Evans","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref26","article-title":"Gotta hear them all: Sound source aware vision to audio generation","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02632-y"},{"key":"ref28","article-title":"Discriminator-guided cooperative diffusion for joint audio and video generation","author":"Hayakawa","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0363"},{"key":"ref30","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NIPS","author":"Heusel","year":"2017"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2022"},{"key":"ref32","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888189"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096198"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref36","article-title":"A simple but strong baseline for sounding video generation: Effective adaptation of audio and video diffusion models for joint generation","author":"Ishii","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00719"},{"key":"ref38","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref40","article-title":"A versatile diffusion transformer with mixture of noise levels for audiovisual generation","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Kong","year":"2020"},{"key":"ref42","author":"Kushwaha","year":"2024","journal-title":"Vintage: Joint video and text conditioning for holistic audio generation. arXiv preprint arXiv:2412.10768"},{"key":"ref43","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"International Society for Music Information Retrieval Conference","author":"Law","year":"2009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3597477"},{"key":"ref45","article-title":"Aadiff: Audio-aligned video synthesis with text-toimage diffusion","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref47","article-title":"T2v-turbo-v2: Enhancing video generation model posttraining through data, reward, and conditional guidance design","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2410.05677"},{"key":"ref48","article-title":"Learn to dance with aist++: Music conditioned 3d dance generation","author":"Li","year":"2021","journal-title":"arXiv"},{"key":"ref49","article-title":"Muvi: Video-to-music generation with semantic alignment and rhythmic synchronization","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0960-4_8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00120"},{"key":"ref52","author":"Lipman","year":"2022","journal-title":"Flow matching for generative modeling. arXiv preprint arXiv:2210.02747"},{"key":"ref53","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"ICML","author":"Liu","year":"2023"},{"key":"ref54","article-title":"Plumbley","author":"Liu","year":"2023","journal-title":"AudioLDM 2: Learning holistic audio generation with self-supervised pretraining. arXiv preprint arXiv:2308.05734"},{"key":"ref55","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2057"},{"key":"ref57","article-title":"Diff-foley: Synchronized video-to-audio synthesis with latent diffusion models","volume-title":"NeurIPS, 36","author":"Luo","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref59","article-title":"The song describer dataset: a corpus of audio captions for music-and-language evaluation","volume-title":"Machine Learning for Audio Workshop at NeurIPS 2023","author":"Manco","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680612"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP58920.2024.10734721"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_15"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref67","article-title":"Movie Gen: A Cast of Media Foundation Models","author":"Polyak","year":"2024","journal-title":"arXiv"},{"key":"ref68","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref69","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2022","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00483"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890132"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref73","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref75","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref77","article-title":"From vision to audio and beyond: A unified model for audio-visual representation and generation","author":"Su","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680889"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626164"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888656"},{"key":"ref81","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref82","article-title":"One rank at a time: Cascading error dynamics in sequential learning","author":"Alizadeh Vandchali","year":"2025","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890587"},{"key":"ref84","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"International Conference on Learning Representations","author":"Villegas","year":"2022"},{"key":"ref85","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023","journal-title":"arXiv preprint arXiv:2312.15821"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref87","article-title":"Av-dit: Efficient audio-visual diffusion transformer for joint audio and video generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681027"},{"key":"ref89","article-title":"Frieren: Efficient video-to-audio generation with rectified flow matching","author":"Wang","year":"2024","journal-title":"arXiv e-prints, pages arXiv-2406"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref91","first-page":"26866","article-title":"Sonicvisionlm: Playing sound with vision language models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xie","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref93","article-title":"Demystifying clip data","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref95","article-title":"Draw an audio: Leveraging multi-instruction for video-toaudio synthesis","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-93806-1_16"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"ref98","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2408.06072"},{"key":"ref99","first-page":"6639","article-title":"Diverse and aligned audio-tovideo generation via text-to-video model adaptation","volume-title":"AAAI","author":"Yariv","year":"2024"},{"key":"ref100","article-title":"Momu-diffusion: On learning long-term motion-music synchronization and correspondence","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"You","year":"2024"},{"key":"ref101","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_1"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02649-3"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"ref105","article-title":"Allegro: Open the black box of commercial-level video generation model","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"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\/11445166.pdf?arnumber=11445166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:15Z","timestamp":1777529655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":105,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01801","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}