{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:47Z","timestamp":1777888667547,"version":"3.51.4"},"reference-count":50,"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\/iccv51701.2025.02276","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24549-24559","source":"Crossref","is-referenced-by-count":0,"title":["B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens"],"prefix":"10.1109","author":[{"given":"Zhuqiang","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Sydney,NSW,Australia,2006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney,NSW,Australia,2006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengwei","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney,NSW,Australia,2006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihui","family":"Wang","sequence":"additional","affiliation":[{"name":"International School of Information Science and Engineering, Dalian University of Technology,Dalian,China,116081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices,WA,USA,98007"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney,NSW,Australia,2006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Science, Edith Cowan University,WA,Australia,6027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref4","article-title":"Token Merging: Your ViT But Faster","volume-title":"ICLR","author":"Bolya","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref6","article-title":"VideoLLaMA 2: Advancing SpatialTemporal Modeling and Audio Understanding in VideoLLMs","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"An Image is Worth 16 16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"The LLaMA 3 Herd of Models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298698"},{"key":"ref10","article-title":"MME:A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","author":"Fu","year":"2024","journal-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref13","first-page":"6904","article-title":"Making the V in VQA Matter: Elevating the Eole of Image Understanding in Visual Question Answering","volume-title":"CVPR","author":"Goyal","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref15","article-title":"Vision-based freezing of gait detection with anatomic patch based representation","volume-title":"ACCV","author":"Hu","year":"2018"},{"key":"ref16","first-page":"6700","article-title":"GQA: A New Dataset for Real-World Visual Eeasoning and Compositional Question Answering","volume-title":"CVPR","author":"Hudson","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref19","article-title":"Seed-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref26","article-title":"Visual Instruction Tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref28","first-page":"2507","article-title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29332"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3796716"},{"key":"ref31","first-page":"46212","article-title":"Egoschema: A Diagnostic Benchmark for Bery Long-Form Video Language Understanding","author":"Mangalam","year":"2023","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","author":"P\u0103tr\u0103ucean","year":"2023","journal-title":"NeurIPS"},{"key":"ref33","first-page":"8748","article-title":"Learning Transferable Visual Models from Natural Language Supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref34","article-title":"Llava-prumerge: Adaptive Token Reduction for Efficient Large Multimodal Models","author":"Shang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref37","article-title":"LLaMA 2: Open Foundation and Fine-tuned Chat Models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"[cls] token tells everything needed for training-free efficient mllms","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"VisionLLM: Large Language Model is Also An Open-ended Decoder for Vision-Centric Tasks","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref42","article-title":"Qwen2 Technical Report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Evaluating Object Hallucination in Large Vision-Language Models","volume-title":"EMNLP","author":"Zhou Jinpeng Wang Wayne Xin Zhao Yifan Li","year":"2023"},{"key":"ref44","article-title":"Surgicalpartsam: Part-to-whole collaborative prompting for surgical instrument segmentation","author":"Yue","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref46","author":"Zhang","year":"2024","journal-title":"LLaVA- NeXT: A Strong Zero-shot Video Understanding Model"},{"key":"ref47","article-title":"Needle In A Video Haystack: A Scalable Synthetic Framework for Benchmarking Video MLLMs","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103551"},{"key":"ref49","article-title":"Languagebind: Extending Video-Language Pretraining to N-modality by Language-Based Semantic Alignment","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"A closer look at the cls token for cross-domain few-shot learning","author":"Zou","year":"2024","journal-title":"NeurIPS"}],"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\/11444838.pdf?arnumber=11444838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:09Z","timestamp":1777611249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02276","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}