{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:14Z","timestamp":1777865354920,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.02185","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23541-23550","source":"Crossref","is-referenced-by-count":0,"title":["SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization"],"prefix":"10.1109","author":[{"given":"Zhentao","family":"Tan","sequence":"first","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Xue","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Jia","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wencai","family":"Ye","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoyun","family":"Shi","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjie","family":"Sun","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjin","family":"Wu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Chen","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"ICLR","year":"2023"},{"key":"ref2","article-title":"Omnitokenizer: A joint image-video tokenizer for visual generation","volume-title":"NeurIPS","year":"2024"},{"key":"ref3","article-title":"Larp: Tokenizing videos with a learned autoregressive generative prior","volume-title":"ICLR Oral","year":"2025"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","article-title":"A short note about kinetics600","author":"Carreira","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"issue":"240","key":"ref9","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"JMLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL","author":"Devlin","year":"2018"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref15","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref17","first-page":"22185","article-title":"Video-lavit: Unified videolanguage pre-training with decoupled visual-motional tokenization","volume-title":"ICML","author":"Jin","year":"2024"},{"key":"ref18","article-title":"Unified language-vision pretraining in 11 m with dynamic discrete visual tokenization","volume-title":"ICLR","author":"Jin","year":"2024"},{"key":"ref19","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arxiv preprint arxiv"},{"key":"ref20","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma","year":"2013"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arxiv preprint arxiv"},{"key":"ref22","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"ICLR","author":"Kipf","year":"2016"},{"key":"ref23","article-title":"Few shot activity recognition using variational inference","author":"Kumar","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref25","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref26","article-title":"Video-llava: Learning united visual representation by alignment before projection","volume-title":"EMNLP","author":"Lin","year":"2023"},{"key":"ref27","article-title":"Language quantized autoencoders: Towards unsupervised text-image alignment","volume-title":"NeurIPS","volume":"36","author":"Liu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00243"},{"issue":"8","key":"ref29","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref31","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref34","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref35","article-title":"Generative pretraining in multimodality","volume-title":"ICLR","author":"Sun","year":"2024"},{"key":"ref36","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref37","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"NeurIPS","volume":"34","author":"Tsimpoukelli","year":"2021"},{"key":"ref38","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref39","article-title":"Neural discrete representation learning","volume-title":"NeurIPS","volume":"30","author":"Van Den Oord","year":"2017"},{"key":"ref40","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani","year":"2017"},{"key":"ref41","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"ICLR","author":"Villegas","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01724"},{"key":"ref43","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","volume-title":"ECCV","author":"Wang","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01281"},{"key":"ref45","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02192"},{"key":"ref47","article-title":"Vector-quantized image modeling with improved vqgan","volume-title":"ICLR","author":"Yu","year":"2022"},{"key":"ref48","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume-title":"ICLR","author":"Yu","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref50","article-title":"Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms","volume-title":"NeurIPS","volume":"36","author":"Yu","year":"2023"},{"key":"ref51","article-title":"An image is worth 32 tokens for reconstruction and generation","volume-title":"NeurIPS","author":"Yu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00741"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02554"}],"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\/11445414.pdf?arnumber=11445414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:28Z","timestamp":1777529968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02185","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}