{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:03:35Z","timestamp":1774631015500,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["62472206"],"award-info":[{"award-number":["62472206"]}]},{"name":"Shenzhen Science and Technology Innovation Committee","award":["RCYX20231211090405003 & KJZD20230923115221044"],"award-info":[{"award-number":["RCYX20231211090405003 & KJZD20230923115221044"]}]},{"name":"Guangdong Provincial Key Laboratory of Advanced Biomaterials","award":["2022B1212010003"],"award-info":[{"award-number":["2022B1212010003"]}]},{"name":"Open Research Fund of Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems"},{"name":"Center for Computational Science and Engineering at Southern University of Science and Technology"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754996","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"5577-5586","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["BrainFLORA: Uncovering Brain Concept Representation via Multimodal Neural Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6841-0929","authenticated-orcid":false,"given":"Dongyang","family":"Li","sequence":"first","affiliation":[{"name":"NCC lab, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3070-6059","authenticated-orcid":false,"given":"Haoyang","family":"Qin","sequence":"additional","affiliation":[{"name":"NCC lab, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1297-8286","authenticated-orcid":false,"given":"Mingyang","family":"Wu","sequence":"additional","affiliation":[{"name":"NCC lab, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2999-2771","authenticated-orcid":false,"given":"Chen","family":"Wei","sequence":"additional","affiliation":[{"name":"NCC lab, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2501-7656","authenticated-orcid":false,"given":"Quanying","family":"Liu","sequence":"additional","affiliation":[{"name":"NCC lab, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Y. Song B. Liu X. Li N. Shi Y. Wang and X. Gao ''Decoding natural images from eeg for object recognition '' in The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","unstructured":"D. Li C. Wei S. Li J. Zou and Q. Liu ''Visual decoding and reconstruction via eeg embeddings with guided diffusion '' in The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_3_1","volume-title":"Cognitioncapturer: Decoding visual stimuli from human eeg signal with multimodal information,'' arXiv preprint arXiv:2412.10489","author":"Zhang K.","year":"2024","unstructured":"K. Zhang, L. He, X. Jiang, W. Lu, D. Wang, and X. Gao, ''Cognitioncapturer: Decoding visual stimuli from human eeg signal with multimodal information,'' arXiv preprint arXiv:2412.10489, 2024."},{"key":"e_1_3_2_1_4_1","first-page":"22","article-title":"Seeing beyond the brain: Conditional diffusion model with sparse masked modeling for vision decoding","author":"Chen Z.","year":"2023","unstructured":"Z. Chen, J. Qing, T. Xiang, W. L. Yue, and J. H. Zhou, ''Seeing beyond the brain: Conditional diffusion model with sparse masked modeling for vision decoding,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22,710-22,720.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_1_5_1","first-page":"14","article-title":"High-resolution image reconstruction with latent diffusion models from human brain activity","author":"Takagi Y.","year":"2023","unstructured":"Y. Takagi and S. Nishimoto, ''High-resolution image reconstruction with latent diffusion models from human brain activity,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14,453-14,463.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_1_6_1","volume-title":"Goode et al., ''Reconstructing the mind's eye: fmri-to-image with contrastive learning and diffusion priors,'' Advances in Neural Information Processing Systems","author":"Scotti P.","year":"2024","unstructured":"P. Scotti, A. Banerjee, J. Goode et al., ''Reconstructing the mind's eye: fmri-to-image with contrastive learning and diffusion priors,'' Advances in Neural Information Processing Systems, vol. 36, 2024."},{"key":"e_1_3_2_1_7_1","volume-title":"Norman et al., ''Mindeye2: Shared-subject models enable fmri-to-image with 1 hour of data,'' in Forty-first International Conference on Machine Learning","author":"Scotti P. S.","year":"2024","unstructured":"P. S. Scotti, M. Tripathy, C. Torrico, R. Kneeland, T. Chen, A. Narang, C. Santhirasegaran, J. Xu, T. Naselaris, K. A. Norman et al., ''Mindeye2: Shared-subject models enable fmri-to-image with 1 hour of data,'' in Forty-first International Conference on Machine Learning, 2024."},{"key":"e_1_3_2_1_8_1","volume-title":"Brain decoding: toward real-time reconstruction of visual perception,'' in The Twelfth International Conference on Learning Representations","author":"Benchetrit Y.","year":"2024","unstructured":"Y. Benchetrit, H. Banville, and J.-R. King, ''Brain decoding: toward real-time reconstruction of visual perception,'' in The Twelfth International Conference on Learning Representations, 2024."},{"key":"e_1_3_2_1_9_1","volume-title":"Neurobind: Towards unified multimodal representations for neural signals","author":"Yang F.","year":"2024","unstructured":"BIBentryALTinterwordspacing F. Yang, C. Feng, D. Wang, T. Wang, Z. Zeng, Z. Xu, H. Park, P. Ji, H. Zhao, Y. Li, and A. Wong, ''Neurobind: Towards unified multimodal representations for neural signals,'' 2024. [Online]. Available: https:\/\/arxiv.org\/abs\/2407.14020 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_10_1","first-page":"242","volume-title":"Umbrae: Unified multimodal brain decoding,'' in European Conference on Computer Vision. hskip 1em plus 0.5em minus 0.4emrelax Springer","author":"Xia W.","year":"2024","unstructured":"W. Xia, R. de Charette, C. Oztireli, and J.-H. Xue, ''Umbrae: Unified multimodal brain decoding,'' in European Conference on Computer Vision. hskip 1em plus 0.5em minus 0.4emrelax Springer, 2024, pp. 242-259."},{"key":"e_1_3_2_1_11_1","first-page":"26","article-title":"Unified-io 2: Scaling autoregressive multimodal models with vision language audio and action","author":"Lu J.","year":"2024","unstructured":"J. Lu, C. Clark, S. Lee, Z. Zhang, S. Khosla, R. Marten, D. Hoiem, and 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. 26,439-26,455.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-01102-7"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.82580"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.23730"},{"key":"e_1_3_2_1_15_1","first-page":"6809","article-title":"Deep learning human mind for automated visual classification","author":"Spampinato C.","year":"2017","unstructured":"C. Spampinato, S. Palazzo, I. Kavasidis, D. Giordano, N. Souly, and M. Shah, ''Deep learning human mind for automated visual classification,'' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 6809-6817.","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102174"},{"key":"e_1_3_2_1_17_1","volume-title":"See what you see: Self-supervised cross-modal retrieval of visual stimuli from brain activity","author":"Ye Z.","year":"2022","unstructured":"BIBentryALTinterwordspacing Z. Ye, L. Yao, Y. Zhang, and S. Gustin, ''See what you see: Self-supervised cross-modal retrieval of visual stimuli from brain activity,'' 2022. [Online]. Available: https:\/\/arxiv.org\/abs\/2208.03666 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_18_1","first-page":"12","article-title":"attend and diffuse to decode high-resolution images from brain activities","volume":"36","author":"Sun J.","year":"2023","unstructured":"J. Sun, M. Li, Z. Chen, Y. Zhang, S. Wang, and M.-F. Moens, ''Contrast, attend and diffuse to decode high-resolution images from brain activities,'' Advances in Neural Information Processing Systems, vol. 36, pp. 12,332-12,348, 2023.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","unstructured":"Q. Zhou C. Du S. Wang and H. He ''Clip-mused: Clip-guided multi-subject visual neural information semantic decoding '' in The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","volume-title":"Aligned with llm: a new multi-modal training paradigm for encoding fmri activity in visual cortex","author":"Ma S.","year":"2024","unstructured":"BIBentryALTinterwordspacing S. Ma, L. Wang, S. Hou, and B. Yan, ''Aligned with llm: a new multi-modal training paradigm for encoding fmri activity in visual cortex,'' 2024. [Online]. Available: https:\/\/arxiv.org\/abs\/2401.03851 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_21_1","first-page":"6840","volume-title":"Denoising diffusion probabilistic models,'' Advances in neural information processing systems","author":"Ho J.","year":"2020","unstructured":"J. Ho, A. Jain, and P. Abbeel, ''Denoising diffusion probabilistic models,'' Advances in neural information processing systems, vol. 33, pp. 6840-6851, 2020."},{"key":"e_1_3_2_1_22_1","first-page":"10","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach R.","year":"2022","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, ''High-resolution image synthesis with latent diffusion models,'' in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2022, pp. 10,684-10,695.","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"e_1_3_2_1_23_1","unstructured":"X. Liu C. Gong et al. ''Flow straight and fast: Learning to generate and transfer data with rectified flow '' in The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","volume-title":"Llama: Open and efficient foundation language models","author":"Touvron H.","year":"2023","unstructured":"BIBentryALTinterwordspacing H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar, A. Rodriguez, A. Joulin, E. Grave, and G. Lample, ''Llama: Open and efficient foundation language models,'' 2023. [Online]. Available: https:\/\/arxiv.org\/abs\/2302.13971 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_25_1","first-page":"1877","volume-title":"Askell et al., ''Language models are few-shot learners,'' Advances in neural information processing systems","author":"Brown T.","year":"2020","unstructured":"T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell et al., ''Language models are few-shot learners,'' Advances in neural information processing systems, vol. 33, pp. 1877-1901, 2020."},{"key":"e_1_3_2_1_26_1","volume-title":"Realmind: Zero-shot eeg-based visual decoding and captioning using multi-modal models","author":"Li D.","year":"2024","unstructured":"BIBentryALTinterwordspacing D. Li, H. Qin, M. Wu, Y. Cao, C. Wei, and Q. Liu, ''Realmind: Zero-shot eeg-based visual decoding and captioning using multi-modal models,'' 2024. [Online]. Available: https:\/\/arxiv.org\/abs\/2410.23754 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-020-00951-3"},{"key":"e_1_3_2_1_28_1","first-page":"50","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","volume":"36","author":"Fu S.","year":"2023","unstructured":"S. Fu, N. Tamir, S. Sundaram, L. Chai, R. Zhang, T. Dekel, and P. Isola, ''Dreamsim: Learning new dimensions of human visual similarity using synthetic data,'' Advances in Neural Information Processing Systems, vol. 36, pp. 50,742-50,768, 2023.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"Cocog: Controllable visual stimuli generation based on human concept representations,'' arXiv preprint arXiv:2404.16482","author":"Wei C.","year":"2024","unstructured":"C. Wei, J. Zou, D. Heinke, and Q. Liu, ''Cocog: Controllable visual stimuli generation based on human concept representations,'' arXiv preprint arXiv:2404.16482, 2024."},{"key":"e_1_3_2_1_30_1","first-page":"1","article-title":"Human-like object concept representations emerge naturally in multimodal large language models","author":"Du C.","year":"2025","unstructured":"C. Du, K. Fu, B. Wen, Y. Sun, J. Peng, W. Wei, Y. Gao, S. Wang, C. Zhang, J. Li et al., ''Human-like object concept representations emerge naturally in multimodal large language models,'' Nature Machine Intelligence, pp. 1-16, 2025.","journal-title":"Nature Machine Intelligence"},{"key":"e_1_3_2_1_31_1","volume-title":"Investigating the role of modality and training objective on representational alignment between transformers and the brain,'' in UniReps","author":"Han H. W.","year":"2024","unstructured":"H. W. Han, R. Dhar, Q. Yang, M. H. Behbahani, M. A. M. Ortiz, T. S. Oladele, D. C. Dima, H.-H. Li, A. S\u00f8gaard, and Y. Mohsenzadeh, ''Investigating the role of modality and training objective on representational alignment between transformers and the brain,'' in UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models, 2024.","edition":"2"},{"key":"e_1_3_2_1_32_1","first-page":"50","volume-title":"Improving neural network representations using human similarity judgments,'' Advances in neural information processing systems","author":"Muttenthaler L.","year":"2023","unstructured":"L. Muttenthaler, L. Linhardt, J. Dippel, R. A. Vandermeulen, K. Hermann, A. Lampinen, and S. Kornblith, ''Improving neural network representations using human similarity judgments,'' Advances in neural information processing systems, vol. 36, pp. 50,978-51,007, 2023."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Y.-L. Sung J. Cho and M. Bansal ''Vl-adapter: Parameter-efficient transfer learning for vision-and-language tasks '' in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2022 pp. 5217-5227.","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_34_1","volume-title":"P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, ''LoRA: Low-rank adaptation of large language models,'' in International Conference on Learning Representations","author":"Hu E. J.","year":"2022","unstructured":"BIBentryALTinterwordspacing E. J. Hu, yelong shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, ''LoRA: Low-rank adaptation of large language models,'' in International Conference on Learning Representations, 2022. [Online]. Available: https:\/\/openreview.net\/forum?id=nZeVKeeFYf9 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"e_1_3_2_1_36_1","volume-title":"Multimodal-gpt: A vision and language model for dialogue with humans","author":"Gong T.","year":"2023","unstructured":"BIBentryALTinterwordspacing T. Gong, C. Lyu, S. Zhang, Y. Wang, M. Zheng, Q. Zhao, K. Liu, W. Zhang, P. Luo, and K. Chen, ''Multimodal-gpt: A vision and language model for dialogue with humans,'' 2023. [Online]. Available: https:\/\/arxiv.org\/abs\/2305.04790 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"X. Du Z. Yu J. Lin B. Zhu and Q. Kong ''Joint music and language attention models for zero-shot music tagging '' in ICASSP 2024-2024 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). hskip 1em plus 0.5em minus 0.4emrelax IEEE 2024 pp. 1126-1130.","DOI":"10.1109\/ICASSP48485.2024.10447760"},{"key":"e_1_3_2_1_38_1","volume-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue L.","year":"2024","unstructured":"BIBentryALTinterwordspacing L. Xue, M. Shu, A. Awadalla, J. Wang, A. Yan, S. Purushwalkam, H. Zhou, V. Prabhu, Y. Dai, M. S. Ryoo, S. Kendre, J. Zhang, C. Qin, S. Zhang, C.-C. Chen, N. Yu, J. Tan, T. M. Awalgaonkar, S. Heinecke, H. Wang, Y. Choi, L. Schmidt, Z. Chen, S. Savarese, J. C. Niebles, C. Xiong, and R. Xu, ''xgen-mm (blip-3): A family of open large multimodal models,'' 2024. [Online]. Available: https:\/\/arxiv.org\/abs\/2408.08872 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_39_1","first-page":"603","article-title":"Ccnet: Criss-cross attention for semantic segmentation","author":"Huang Z.","year":"2019","unstructured":"Z. Huang, X. Wang, L. Huang, C. Huang, Y. Wei, and W. Liu, ''Ccnet: Criss-cross attention for semantic segmentation,'' in Proceedings of the IEEE\/CVF international conference on computer vision, 2019, pp. 603-612.","journal-title":"Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"e_1_3_2_1_40_1","volume-title":"June","author":"Wei X.","year":"2020","unstructured":"X. Wei, T. Zhang, Y. Li, Y. Zhang, and F. Wu, ''Multi-modality cross attention network for image and sentence matching,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020."},{"key":"e_1_3_2_1_41_1","unstructured":"D. Zhu J. Chen X. Shen X. Li and M. Elhoseiny ''Minigpt-4: Enhancing vision-language understanding with advanced large language models '' in The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_42_1","volume-title":"Palm2-vadapter: Progressively aligned language model makes a strong vision-language adapter","author":"Xiao J.","year":"2024","unstructured":"BIBentryALTinterwordspacing J. Xiao, Z. Xu, A. Yuille, S. Yan, and B. Wang, ''Palm2-vadapter: Progressively aligned language model makes a strong vision-language adapter,'' 2024. [Online]. Available: https:\/\/arxiv.org\/abs\/2402.10896 BIBentrySTDinterwordspacing"},{"key":"e_1_3_2_1_43_1","first-page":"23","volume-title":"Reynolds et al., ''Flamingo: a visual language model for few-shot learning,'' Advances in neural information processing systems","author":"Alayrac J.-B.","year":"2022","unstructured":"J.-B. Alayrac, J. Donahue, P. Luc, A. Miech, I. Barr, Y. Hasson, K. Lenc, A. Mensch, K. Millican, M. Reynolds et al., ''Flamingo: a visual language model for few-shot learning,'' Advances in neural information processing systems, vol. 35, pp. 23,716-23,736, 2022."},{"key":"e_1_3_2_1_44_1","unstructured":"Y. Wang N. Huang T. Li Y. Yan and X. Zhang ''Medformer: A multi-granularity patching transformer for medical time-series classification '' in The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_45_1","unstructured":"X. Zhu Y. Hu F. Mo M. Li and J. Wu ''Uni-med: A unified medical generalist foundation model for multi-task learning via connector-moe '' in The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_46_1","volume-title":"Hierarchical text-conditional image generation with clip latents,'' arXiv preprint arXiv:2204.06125","author":"Ramesh A.","unstructured":"A. Ramesh, P. Dhariwal, A. Nichol, C. Chu, and M. Chen, ''Hierarchical text-conditional image generation with clip latents,'' arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3, 2022."},{"key":"e_1_3_2_1_47_1","unstructured":"D. Podell Z. English K. Lacey A. Blattmann T. Dockhorn J. M\u00fcller J. Penna and R. Rombach ''Sdxl: Improving latent diffusion models for high-resolution image synthesis '' in The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_48_1","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang R.","year":"2018","unstructured":"R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, ''The unreasonable effectiveness of deep features as a perceptual metric,'' in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 586-595.","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119754"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-77923-4"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c"},{"key":"e_1_3_2_1_52_1","first-page":"11","article-title":"Mindbridge: A cross-subject brain decoding framework","author":"Wang S.","year":"2024","unstructured":"S. Wang, S. Liu, Z. Tan, and X. Wang, ''Mindbridge: A cross-subject brain decoding framework,'' in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 11,333-11,342.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_1_53_1","volume-title":"Decoding visual experience and mapping semantics through whole-brain analysis using fmri foundation models,'' arXiv preprint arXiv:2411.07121","author":"Wang Y.","year":"2024","unstructured":"Y. Wang, A. Turnbull, T. Xiang, Y. Xu, S. Zhou, A. Masoud, S. Azizi, F. V. Lin, and E. Adeli, ''Decoding visual experience and mapping semantics through whole-brain analysis using fmri foundation models,'' arXiv preprint arXiv:2411.07121, 2024."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681292"},{"key":"e_1_3_2_1_55_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models,'' arXiv preprint arXiv:2308.06721","author":"Ye H.","year":"2023","unstructured":"H. Ye, J. Zhang, S. Liu, X. Han, and W. Yang, ''Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models,'' arXiv preprint arXiv:2308.06721, 2023."},{"key":"e_1_3_2_1_56_1","volume-title":"Sagawa et al., ''Openflamingo: An open-source framework for training large autoregressive vision-language models,'' arXiv preprint arXiv:2308.01390","author":"Awadalla A.","year":"2023","unstructured":"A. Awadalla, I. Gao, J. Gardner, J. Hessel, Y. Hanafy, W. Zhu, K. Marathe, Y. Bitton, S. Gadre, S. Sagawa et al., ''Openflamingo: An open-source framework for training large autoregressive vision-language models,'' arXiv preprint arXiv:2308.01390, 2023."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:25Z","timestamp":1765340125000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754996"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":56,"alternative-id":["10.1145\/3746027.3754996","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754996","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}