{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:14:49Z","timestamp":1781018089979,"version":"3.54.1"},"reference-count":151,"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\/iccv51701.2025.01958","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21070-21084","source":"Crossref","is-referenced-by-count":1,"title":["V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding"],"prefix":"10.1109","author":[{"given":"Junqi","family":"Ge","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintao","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinguo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xizhou","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"114","article-title":"Keyformer: Kv cache reduction through key tokens selection for efficient generative inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Adnan","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"An image is worth 16 x 16words: Transformers for image recognition at scale","author":"Alexey","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","volume-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024"},{"key":"ref6","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Deepseek llm: Scaling opensource language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"@bloc97","year":"2023","journal-title":"Ntk-aware scaled rope"},{"key":"ref12","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Burtsev. Scaling transformer to 1 m tokens and beyond with rmt","author":"Bulatov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Internlm2 technical report","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref16","article-title":"Extending context window of large language models via positional interpolation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Longlora: Efficient fine-tuning of long-context large language models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"ref22","article-title":"Mobility vla: Multimodal instruction navigation with long-context vlms and topological graphs","author":"Lewis Chiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Rethinking attention with performers","author":"Choromanski","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Mobilevlm v2: Faster and stronger baseline for vision language model","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref29","author":"DeepSeek-AI","year":"2025","journal-title":"Deepseekr1: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref30","first-page":"7480","article-title":"Scaling vision transformers to 22 billion pa-rameters","volume-title":"International Conference on Machine Learning","author":"Dehghani","year":"2023"},{"key":"ref31","article-title":"Longnet: Scaling transformers to 1,000,000,000 tokens","author":"Ding","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Longrope: Extending llm context window beyond 2 million tokens","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","author":"Doan","year":"2024","journal-title":"Vintern-1b: An efficient multimodal large language model for vietnamese"},{"key":"ref34","article-title":"Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Internlm-xcomposer24khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4 k hd","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref37","article-title":"Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal 11 ms in video analysis","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Tc-llava: Rethinking the transfer from image to video understanding with temporal considerations","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00067-6"},{"key":"ref40","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Infinity-mm: Scaling multimodal performance with large-scale and high-quality instruction data","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Lm-infinite: Simple on-the-fly length generalization for large language models","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.99"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.581"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.321"},{"key":"ref50","first-page":"6700","article-title":"Gqa: A new dataset for real-world visual reasoning and compositional question answering","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Drew","year":"2019"},{"key":"ref51","volume-title":"Introducing hpt: A family of leading multimodal llms","year":"2024"},{"key":"ref52","article-title":"Mantis: Interleaved multiimage instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Rethinking positional encoding in language pre-training","author":"Ke","year":"2020","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref55","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.266"},{"key":"ref57","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref59","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref65","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref66","article-title":"World model on million-length video and language with ringattention","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.252"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3537759"},{"key":"ref69","article-title":"Thus spake long-context large language model","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref71","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref73","article-title":"Feast your eyes: Mixture-ofresolution adaptation for multimodal large language models","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Are we falling in a middleintelligence trap? an analysis and mitigation of the reversal curse","author":"Lv","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Kosmos-2.5: A multimodal literate model","author":"Lv","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Vista-llama: Reliable video narrator via equal distance to visual tokens","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref79","article-title":"Mm1: Methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Landmark attention: Random-access infinite context length for transformers","author":"Mohtashami","year":"2023","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"OpenAI","year":"2023","journal-title":"Hello gpt-4o"},{"key":"ref82","volume-title":"Gpt-4v(ision) system card","year":"2023"},{"issue":"5","key":"ref83","article-title":"R OpenAI","volume":"2","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref84","article-title":"OpenGVLab","year":"2024","journal-title":"Needle in a multimodal haystack"},{"key":"ref85","article-title":"Yarn: Efficient context window extension of large language models","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref86","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref87","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","author":"Press","year":"2021","journal-title":"arXiv preprint"},{"key":"ref88","article-title":"Blockwise selfattention for long document understanding","author":"Qiu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref89","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref90","first-page":"1","article-title":"Liu. Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref91","first-page":"22470","article-title":"Combiner: Full attention transformer with sparse computation cost","volume":"34","author":"Ren","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref92","article-title":"Selfattention with relative position representations","author":"Shaw","year":"2018","journal-title":"arXiv preprint"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02436"},{"key":"ref94","article-title":"Milebench: Benchmarking mllms in long context","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref95","volume-title":"Step-1v: A hundred billion parameter multimodal large model","year":"2024"},{"key":"ref96","volume-title":"Rectified rotary position embeddings","author":"Su","year":"2023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"issue":"7","key":"ref99","article-title":"Moss: Training conversational language models from synthetic data","volume":"3","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.816"},{"issue":"6","key":"ref101","article-title":"Alpaca: A strong, replicable instructionfollowing model","volume":"3","author":"Taori","year":"2023","journal-title":"Stanford Center for Research on Foundation Models"},{"key":"ref102","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref103","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref104","article-title":"InternLM Team","year":"2023","journal-title":"Internlm: A multilingual language model with progressively enhanced capabilities"},{"key":"ref105","article-title":"Mm-interleaved: Interleaved image-text generative modeling via multi-modal feature synchronizer","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref107","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref108","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref109","article-title":"Focused transformer: Contrastive training for context scaling","volume":"36","author":"Tworkowski","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref110","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref111","article-title":"On position embeddings in bert","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2020"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.166"},{"key":"ref113","article-title":"To see is to believe: Prompting gpt-4v for better visual instruction tuning","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref114","article-title":"Enhancing zero-shot counting via language-guided exemplar learning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref115","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref116","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref117","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref118","article-title":"Augmenting language models with long-term memory","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref119","article-title":"Needle in a multimodal haystack","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref120","article-title":"Longllava: Scaling multi-modal 11 ms to 1000 images efficiently via hybrid architecture","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref124","article-title":"Skywork: A more open bilingual foundation model","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref125","article-title":"Videorope: What makes for good video rotary position embedding","author":"Wei","year":"2025","journal-title":"arXiv preprint"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"ref127","article-title":"Training-free exponential extension of sliding window context with cascading kv cache","author":"Willette","year":"2024","journal-title":"arXiv preprint"},{"key":"ref128","article-title":"Memorizing transformers","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref129","volume-title":"X.a. Grok-1.5 vision preview","year":"2024"},{"key":"ref130","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref131","article-title":"Retrieval meets long context large language models","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref132","article-title":"Longvila: Scaling long-context visual language models for long videos","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref133","article-title":"mt5: A massively multilingual pre-trained text-totext transformer","author":"Xue","year":"2020","journal-title":"arXiv preprint"},{"key":"ref134","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref135","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref136","article-title":"CLEVRER: collision events for video representation and reasoning","author":"Yi","year":"2020","journal-title":"ICLR"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref138","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref140","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref141","article-title":"Retrieve anything to augment large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref142","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref143","article-title":"Long context compression with activation beacon","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref144","article-title":"Long context transfer from language to vision","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref145","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref146","article-title":"Extending llms\u2019 context window with 100 samples","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref147","article-title":"Longskywork: A training recipe for efficiently extending context length in large language models","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref149","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref150","article-title":"Pose: Efficient context window extension of 11 ms via positional skip-wise training","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref151","article-title":"Multimodal c4: An open, billion-scale corpus of images interleaved with text","volume":"36","author":"Zhu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11445919.pdf?arnumber=11445919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:55Z","timestamp":1777611835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":151,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01958","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}