{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:08:30Z","timestamp":1788894510478,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370341","type":"print"},{"value":"9783032370358","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37035-8_16","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:54:15Z","timestamp":1788893655000},"page":"284-300","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fourier Compressor: Frequency-Domain Visual Token Compression for\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3457-0106","authenticated-orcid":false,"given":"Huanyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jushi","family":"Kai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoli","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouhan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"16_CR1","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Si, C., Wang, J., Liu, Z.: FreeMorph: tuning-free generalized image morphing with diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18111\u201318120 (2025)","DOI":"10.1109\/ICCV51701.2025.01683"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: An Image is Worth 1\/2 tokens after layer 2: plug-and-play inference acceleration for large vision-language models. In: European Conference on Computer Vision, pp. 19\u201335. Springer (2024)","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., et\u00a0al.: Are we on the right way for evaluating large vision-language models?. In: Advances in Neural Information Processing Systems, vol.\u00a037, pp. 27056\u201327087 (2024)","DOI":"10.52202\/079017-0850"},{"issue":"12","key":"16_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y","volume":"67","author":"H Feng","year":"2024","unstructured":"Feng, H., et al.: DocPedia: unleashing the power of large multimodal model in the frequency domain for versatile document understanding. Sci. China Inf. Sci. 67(12), 220106 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models. In: Advances in Neural Information Processing Systems, vol. 38 (2025)","DOI":"10.52202\/085713-4899"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"He, Z., et al.: Fourier transformer: fast long range modeling by removing sequence redundancy with FFT operator. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 8954\u20138966 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.570"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Hu, W., Dou, Z.Y., Li, L.H., Kamath, A., Peng, N., Chang, K.W.: Matryoshka query transformer for large vision-language models. In: Advances in Neural Information Processing Systems, vol. 37, pp. 50168\u201350188 (2024)","DOI":"10.52202\/079017-1588"},{"key":"16_CR10","unstructured":"Huang, M., et al.: Efficient multi-modal large language models via visual token grouping. arXiv preprint arXiv:2411.17773 (2024)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"16_CR12","unstructured":"Kai, J., et al.: FreqKV: key-value compression in frequency domain for context window extension. In: International Conference on Learning Representations (2026)"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Lee-Thorp, J., Ainslie, J., Eckstein, I., Ontanon, S.: FNet: mixing tokens with Fourier transforms. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4296\u20134313 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"16_CR14","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"16_CR15","unstructured":"Li, K., Goyal, S., Semedo, J.D., Kolter, Z.: Inference optimal VLMs need fewer visual tokens and more parameters. In: International Conference on Learning Representations, vol. 2025, pp. 96066\u201396083 (2025)"},{"issue":"10","key":"16_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9","volume":"68","author":"K Li","year":"2025","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. Sci. China Inf. Sci. 68(10), 200102 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: MVBench: a comprehensive multi-modal video understanding benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22195\u201322206 (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 292\u2013305 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLaVA: learning united visual representation by alignment before projection. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 5971\u20135984 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"16_CR21","unstructured":"Liu, H., et al.: LLaVA-NeXT: improved reasoning, OCR, and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next (2024). Accessed 27 June 2026"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: . Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: Advances in Neural Information Processing Systems, vol. 35, pp. 2507\u20132521 (2022)","DOI":"10.52202\/068431-0182"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: Video-ChatGPT: towards detailed video understanding via large vision and language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 12585\u201312602 (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Shang, Y., Cai, M., Xu, B., Lee, Y.J., Yan, Y.: LLaVA-PruMerge: adaptive token reduction for efficient large multimodal models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22857\u201322867 (2025)","DOI":"10.1109\/ICCV51701.2025.02122"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"issue":"4","key":"16_CR28","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/103085.103089","volume":"34","author":"GK Wallace","year":"1991","unstructured":"Wallace, G.K.: The JPEG still picture compression standard. Commun. ACM 34(4), 30\u201344 (1991)","journal-title":"Commun. ACM"},{"key":"16_CR29","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"16_CR30","unstructured":"xAI: RealWorldQA: a benchmark for real-world understanding. https:\/\/huggingface.co\/datasets\/xai-org\/RealworldQA (2024). Accessed 27 June 2026"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y.K., Ren, F.: Learning in the frequency domain. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1740\u20131749 (2020)","DOI":"10.1109\/CVPR42600.2020.00181"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: VisionZip: longer is better but not necessary in vision language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19792\u201319802 (2025)","DOI":"10.1109\/CVPR52734.2025.01843"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Ye, X., Gan, Y., Ge, Y., Zhang, X.P., Tang, Y.: ATP-LLaVA: adaptive token pruning for large vision language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24972\u201324982 (2025)","DOI":"10.1109\/CVPR52734.2025.02325"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 543\u2013553 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, K., et\u00a0al.: LMMs-Eval: reality check on the evaluation of large multimodal models. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 881\u2013916 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"16_CR37","unstructured":"Zhang, S., Fang, Q., Yang, Y., Feng, Y.: LLaVA-Mini: efficient image and video large multimodal models with one vision token. In: International Conference on Learning Representations, vol. 2025, pp. 53285\u201353310 (2025)"},{"key":"16_CR38","unstructured":"Zhang, Y., et al.: SparseVLM: visual token sparsification for efficient vision-language model inference (2024). arXiv:2410.04417 arXiv preprint"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37035-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:54:21Z","timestamp":1788893661000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37035-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370341","9783032370358"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37035-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}