{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T21:14:48Z","timestamp":1783458888553,"version":"3.55.0"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005130","name":"Giant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021160","name":"Chinese Academy of Sciences Shanghai Institute of Microsystem and Information Technology","doi-asserted-by":"publisher","award":["6142804230104"],"award-info":[{"award-number":["6142804230104"]}],"id":[{"id":"10.13039\/501100021160","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.jvcir.2026.104887","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:40:33Z","timestamp":1782924033000},"page":"104887","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["OCC-MLLM-V2: Joint understanding and generation for occluded objects via multi-modal token learning"],"prefix":"10.1016","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0164-1953","authenticated-orcid":false,"given":"Chaoyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingdong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9752-1524","authenticated-orcid":false,"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijie","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianpo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8855-8628","authenticated-orcid":false,"given":"Xinhan","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104887_b1","series-title":"Gpt-4 technical report","author":"OpenAI","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104887_b2","series-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Google","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b3","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TCSVT.2021.3067449","article-title":"Task-adaptive attention for image captioning","volume":"32","author":"Yan","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104887_b4","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1109\/TPAMI.2020.2975798","article-title":"Deep multi-view enhancement hashing for image retrieval","volume":"43","author":"Yan","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104887_b5","doi-asserted-by":"crossref","unstructured":"Z. Zhang, L. Li, G. Cong, H. Yin, Y. Gao, C. Yan, A.v.d. Hengel, Y. Qi, From speaker to dubber: movie dubbing with prosody and duration consistency learning, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 7523\u20137532.","DOI":"10.1145\/3664647.3680777"},{"key":"10.1016\/j.jvcir.2026.104887_b6","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2025.1585386","article-title":"Focus: Object-centric world models for robotic manipulation","volume":"19","author":"Ferraro","year":"2025","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.jvcir.2026.104887_b7","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1007\/s11633-025-1542-8","article-title":"A survey of embodied learning for object-centric robotic manipulation","volume":"22","author":"Zheng","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.jvcir.2026.104887_b8","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2024.1398703","article-title":"Remote intelligent perception system for multi-object detection","volume":"18","author":"Alazeb","year":"2024","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.jvcir.2026.104887_b9","doi-asserted-by":"crossref","first-page":"2250","DOI":"10.3390\/electronics13122250","article-title":"An advanced approach to object detection and tracking in robotics and autonomous vehicles using yolov8 and lidar data fusion","volume":"13","author":"Dai","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.jvcir.2026.104887_b10","series-title":"2024 5th International Conference on Advancements in Computational Sciences","first-page":"1","article-title":"Dynamic adoptive gaussian mixture model for multi-object detection over natural scenes","author":"Ahmed","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b11","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"361","article-title":"Contactpose: A dataset of grasps with object contact and hand pose","author":"Brahmbhatt","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104887_b12","doi-asserted-by":"crossref","unstructured":"Z. Cao, I. Radosavovic, A. Kanazawa, J. Malik, Reconstructing hand-object interactions in the wild, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 12417\u201312426.","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"10.1016\/j.jvcir.2026.104887_b13","doi-asserted-by":"crossref","first-page":"2883","DOI":"10.1109\/TPAMI.2017.2759736","article-title":"Hand-object contact force estimation from markerless visual tracking","volume":"40","author":"Pham","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"10.1016\/j.jvcir.2026.104887_b14","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/s11263-016-0895-4","article-title":"Capturing hands in action using discriminative salient points and physics simulation","volume":"118","author":"Tzionas","year":"2016","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"10.1016\/j.jvcir.2026.104887_b15","doi-asserted-by":"crossref","unstructured":"Y. Ye, A. Gupta, S. Tulsiani, What\u2019s in your hands? 3d reconstruction of generic objects in hands, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 3895\u20133905.","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"10.1016\/j.jvcir.2026.104887_b16","doi-asserted-by":"crossref","unstructured":"Z. Chen, S. Chen, C. Schmid, I. Laptev, Gsdf: Geometry-driven signed distance functions for 3d hand-object reconstruction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 12890\u201312900.","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"10.1016\/j.jvcir.2026.104887_b17","series-title":"Moho: Learning single-view hand-held object reconstruction with multi-view occlusion-aware supervision","author":"Zhang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b18","series-title":"Occ-mllm: Empowering multimodal large language model for the understanding of occluded objects","author":"Qiu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b19","series-title":"Occ-mllm-alpha: Empowering multi-modal large language model for the understanding of occluded objects with self-supervised test-time learning","author":"Yang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b20","series-title":"Occ-mllm-cot-alpha: Towards multi-stage occlusion recognition based on large language models via 3d-aware supervision and chain-of-thoughts guidance","author":"Wang","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b21","first-page":"1","article-title":"Precise no-reference image quality evaluation based on distortion identification","volume":"17","author":"Yan","year":"2021","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.jvcir.2026.104887_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3404374","article-title":"Depth image denoising using nuclear norm and learning graph model","volume":"16","author":"Yan","year":"2020","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.jvcir.2026.104887_b23","doi-asserted-by":"crossref","unstructured":"C. Wu, X. Chen, Z. Wu, Y. Ma, X. Liu, Z. Pan, W. Liu, Z. Xie, X. Yu, C. Ruan, et al., Janus: Decoupling visual encoding for unified multimodal understanding and generation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 12966\u201312977.","DOI":"10.1109\/CVPR52734.2025.01210"},{"key":"10.1016\/j.jvcir.2026.104887_b24","series-title":"Chameleon: Mixed-modal early-fusion foundation models, 2024","author":"Team","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3472810","article-title":"Age-invariant face recognition by multi-feature fusionand decomposition with self-attention","volume":"18","author":"Yan","year":"2022","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"10.1016\/j.jvcir.2026.104887_b26","series-title":"Chatgpt","author":"OpenAI","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104887_b27","series-title":"Grok-3","author":"xAI","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b28","series-title":"Claude 3.7","author":"Claude","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b29","series-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b30","series-title":"Autoregressive models in vision: A survey","author":"Xiong","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b31","series-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b32","series-title":"Scalable pre-training of large autoregressive image models","author":"El-Nouby","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b33","doi-asserted-by":"crossref","unstructured":"J. Lu, C. Clark, S. Lee, Z. Zhang, S. Khosla, R. Marten, D. Hoiem, A. Kembhavi, Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 26439\u201326455.","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"10.1016\/j.jvcir.2026.104887_b34","doi-asserted-by":"crossref","unstructured":"Q. Sun, Y. Cui, X. Zhang, F. Zhang, Q. Yu, Y. Wang, Y. Rao, J. Liu, T. Huang, X. Wang, Generative multimodal models are in-context learners, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14398\u201314409.","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"10.1016\/j.jvcir.2026.104887_b35","doi-asserted-by":"crossref","first-page":"84839","DOI":"10.52202\/079017-2694","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","volume":"37","author":"Tian","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104887_b36","series-title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b37","doi-asserted-by":"crossref","unstructured":"Y. Ma, X. Liu, X. Chen, W. Liu, C. Wu, Z. Wu, Z. Pan, Z. Xie, H. Zhang, X. Yu, et al., Janusflow: Harmonizing autoregression and rectified flow for unified multimodal understanding and generation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 7739\u20137751.","DOI":"10.1109\/CVPR52734.2025.00725"},{"key":"10.1016\/j.jvcir.2026.104887_b38","doi-asserted-by":"crossref","unstructured":"L. Qu, H. Zhang, Y. Liu, X. Wang, Y. Jiang, Y. Gao, H. Ye, D.K. Du, Z. Yuan, X. Wu, Tokenflow: Unified image tokenizer for multimodal understanding and generation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 2545\u20132555.","DOI":"10.1109\/CVPR52734.2025.00243"},{"key":"10.1016\/j.jvcir.2026.104887_b39","series-title":"Uniflow: A unified pixel flow tokenizer for visual understanding and generation","author":"Yue","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b40","series-title":"Dreamfuse: Adaptive image fusion with diffusion transformer","author":"Huang","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b41","series-title":"Towards visuospatial cognition via hierarchical fusion of visual experts","author":"Feng","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b42","series-title":"Multimodal alignment and fusion: A survey","author":"Li","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b43","series-title":"Think hierarchically, act dynamically: Hierarchical multi-modal fusion and reasoning for vision-and-language navigation","author":"Yue","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104887_b44","unstructured":"C. Wang, F. Meng, J. Pei, L. Xia, J. Liu, X. Yuan, X. Di, Occ-mllm-cot: Self-correction enhanced occlusion recognition with large language models via 3d-aware supervision, chain-of-thoughts guidance, Chain-of-Thoughts Guid.."},{"key":"10.1016\/j.jvcir.2026.104887_b45","unstructured":"C. Wang, Q. He, J. Pei, L. Xia, J. Liu, B. Li, X. Di, Occ-mllm-v1: Commonsense-guided multi-modal llm based agent for occlusion reasoning with internal chain-of-thoughts (cots) guidance. Available at SSRN 5702186."},{"key":"10.1016\/j.jvcir.2026.104887_b46","series-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b47","doi-asserted-by":"crossref","unstructured":"X. Zhai, B. Mustafa, A. Kolesnikov, L. Beyer, Sigmoid loss for language image pre-training, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 11975\u201311986.","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"10.1016\/j.jvcir.2026.104887_b48","doi-asserted-by":"crossref","unstructured":"Y. Hasson, G. Varol, D. Tzionas, I. Kalevatykh, M.J. Black, I. Laptev, C. Schmid, Learning joint reconstruction of hands and manipulated objects, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11807\u201311816.","DOI":"10.1109\/CVPR.2019.01208"},{"key":"10.1016\/j.jvcir.2026.104887_b49","doi-asserted-by":"crossref","unstructured":"Y.W. Chao, W. Yang, Y. Xiang, P. Molchanov, A. Handa, J. Tremblay, Y.S. Narang, K.V. Wyk, U. Iqbal, S. Birchfield, et al., Dexycb: A benchmark for capturing hand grasping of objects, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 9044\u20139053.","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"10.1016\/j.jvcir.2026.104887_b50","doi-asserted-by":"crossref","unstructured":"Y. Zhu, Y. Tian, D. Metaxas, P. Doll\u00e1r, Semantic amodal segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1464\u20131472.","DOI":"10.1109\/CVPR.2017.320"},{"key":"10.1016\/j.jvcir.2026.104887_b51","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.jvcir.2026.104887_b52","doi-asserted-by":"crossref","unstructured":"S. Hampali, M. Rad, M. Oberweger, V. Lepetit, Honnotate: A method for 3d annotation of hand and object poses, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020, pp. 3196\u20133206.","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"10.1016\/j.jvcir.2026.104887_b53","series-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104887_b54","series-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104887_b55","series-title":"Autodl","author":"AutoDL","year":"2026"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001823?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001823?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:29:37Z","timestamp":1783456177000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326001823"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":55,"alternative-id":["S1047320326001823"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104887","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/github.com\/chaoyiwang09\/occ-mllm","asserted-by":"subject"}]},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OCC-MLLM-V2: Joint understanding and generation for occluded objects via multi-modal token learning","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104887","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104887"}}