{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:08:41Z","timestamp":1777655321438,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726422","type":"print"},{"value":"9783031726439","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72643-9_13","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T20:48:26Z","timestamp":1732222106000},"page":"214-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["IVTP: Instruction-Guided Visual Token Pruning for\u00a0Large Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Kai","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Xi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"BoChen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928 (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"13_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"13_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"13_CR4","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Cha, J., Kang, W., Mun, J., Roh, B.: Honeybee: locality-enhanced projector for multimodal LLM. arXiv preprint arXiv:2312.06742 (2023)","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"13_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"13_CR8","doi-asserted-by":"publisher","unstructured":"Fayyaz, M., et al.: Adaptive token sampling for efficient vision transformers. In: Proceedings of the IEEE\/CVF European Conference on Computer Vision, pp. 396\u2013414. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_24","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"13_CR9","unstructured":"Fu, C., et\u00a0al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"13_CR10","unstructured":"Goyal, S., Choudhury, A.R., Raje, S., Chakaravarthy, V., Sabharwal, Y., Verma, A.: Power-BERT: accelerating BERT inference via progressive word-vector elimination. In: International Conference on Machine Learning, pp. 3690\u20133699. PMLR (2020)"},{"key":"13_CR11","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"13_CR12","unstructured":"Guo, Y., Zhang, H., Nie, L., Wong, Y., Kankanhalli, M.: ELIP: efficient language-image pre-training with fewer vision tokens. arXiv preprint arXiv:2309.16738 (2023)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: VizWiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"13_CR14","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":"13_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: BUS: efficient and effective vision-language pre-training with bottom-up patch summarization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2900\u20132910 (2023)","DOI":"10.1109\/ICCV51070.2023.00271"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Kim, G., Cho, K.: Length-adaptive transformer: train once with length drop, use anytime with search. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 6501\u20136511 (2021)","DOI":"10.18653\/v1\/2021.acl-long.508"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Kim, S., et al.: Learned token pruning for transformers. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 784\u2013794 (2022)","DOI":"10.1145\/3534678.3539260"},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/978-3-031-20083-0_37","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XI","author":"Z Kong","year":"2022","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via\u00a0latency-aware soft token pruning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XI, pp. 620\u2013640. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: SEED-Bench: benchmarking multimodal LLMs with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"13_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"13_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: LLaMA-VID: an image is worth 2 tokens in large language models. arXiv preprint arXiv:2311.17043 (2023)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"13_CR23","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. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"13_CR24","unstructured":"Liang, Y., Chongjian, G., Tong, Z., Song, Y., Wang, J., Xie, P.: EVIT: expediting vision transformers via token reorganizations. In: International Conference on Learning Representations (2021)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"13_CR26","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"13_CR28","first-page":"2507","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu, P., et al.: Learn to Explain: multimodal reasoning via thought chains for science question answering. Adv. Neural. Inf. Process. Syst. 35, 2507\u20132521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR29","unstructured":"OpenAI: ChatGPT. https:\/\/openai.com\/blog\/chatgpt\/1, 2 (2023)"},{"key":"13_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"13_CR31","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. Adv. Neural. Inf. Process. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"13_CR33","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"},{"key":"13_CR34","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Wei, S., Ye, T., Zhang, S., Tang, Y., Liang, J.: Joint token pruning and squeezing towards more aggressive compression of vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2092\u20132101 (2023)","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"13_CR36","unstructured":"Wu, X., Zeng, F., Wang, X., Wang, Y., Chen, X.: PPT: token pruning and pooling for efficient vision transformers. arXiv preprint arXiv:2310.01812 (2023)"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: EVO-ViT: slow-fast token evolution for dynamic vision transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2964\u20132972 (2022)","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Ye, D., Lin, Y., Huang, Y., Sun, M.: TR-BERT: dynamic token reduction for accelerating BERT inference. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5798\u20135809 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.463"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J.M., Mallya, A., Kautz, J., Molchanov, P.: A-ViT: adaptive tokens for efficient vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10809\u201310818 (2022)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"13_CR40","unstructured":"Yu, W., et al.: MM-Vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"13_CR41","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72643-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T21:26:48Z","timestamp":1732224408000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72643-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726422","9783031726439"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72643-9_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}