{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:04:02Z","timestamp":1789376642746,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373823","type":"print"},{"value":"9783032373830","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\/978-3-032-37383-0_32","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:21:11Z","timestamp":1789374071000},"page":"555-571","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Focusing by\u00a0Contrastive Attention: Enhancing VLMs\u2019 Visual Reasoning"],"prefix":"10.1007","author":[{"given":"Yuyao","family":"Ge","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenghua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingrui","family":"Mei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baolong","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanshan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayu","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"32_CR1","unstructured":"Acharya, S., Jia, F., Ginsburg, B.: Star attention: efficient LLM inference over long sequences (2024). arXiv:2411.17116 arXiv preprint"},{"key":"32_CR2","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report (2025)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Bi, B., et al.: Decoding by contrasting knowledge: Enhancing large language model confidence on edited facts. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 17198\u201317208 (2025)","DOI":"10.18653\/v1\/2025.acl-long.841"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(6), 679\u2013698 (1986)","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"32_CR6","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":"32_CR7","unstructured":"Chen, L., Zhou, B., Ge, Y., Chen, J., Ni, S.: PIS: linking importance sampling and attention mechanisms for efficient prompt compression. arXiv preprint arXiv:2504.16574 (2025)"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Gkartzonika, I., Gkalelis, N., Mezaris, V.: Learning visual explanations for DCNN-based image classifiers using an attention mechanism. In: European Conference on Computer Vision, pp. 396\u2013411. Springer (2022)","DOI":"10.1007\/978-3-031-25085-9_23"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Hong, W., et\u00a0al.: CogAgent: a visual language model for GUI agents. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14281\u201314290 (2024)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"32_CR10","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: Hallucination augmented contrastive learning for multimodal large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27036\u201327046 (2024)","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"32_CR12","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, 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":"32_CR14","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shi, K., He, K., Ye, L., Fabbri, A.R., Liu, P., Radev, D., Cohan, A.: On learning to summarize with large language models as references. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (vol. 1: Long Papers), pp. 8647\u20138664 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.478"},{"key":"32_CR16","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.52202\/068431-0182","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":"32_CR17","unstructured":"Ma, F., et al.: Ee-MLLM: a data-efficient and compute-efficient multimodal large language model. arXiv preprint arXiv:2408.11795 (2024)"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Masry, A., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"32_CR20","doi-asserted-by":"publisher","first-page":"110290","DOI":"10.52202\/079017-3500","volume":"37","author":"K Pan","year":"2024","unstructured":"Pan, K., et al.: Towards unified multimodal editing with enhanced knowledge collaboration. Adv. Neural. Inf. Process. Syst. 37, 110290\u2013110314 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR21","unstructured":"Qi, J., et al.: CogCom: train large vision-language models diving into details through chain of manipulations (2024). arXiv:2402.04236 arXiv preprint"},{"key":"32_CR22","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-OKVQA: a benchmark for visual question answering using world knowledge. In: European Conference on Computer Vision, pp. 146\u2013162. Springer (2022)","DOI":"10.1007\/978-3-031-20074-8_9"},{"issue":"3","key":"32_CR25","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Techn. J. 27(3), 379\u2013423 (1948)","journal-title":"Bell Syst. Techn. J."},{"key":"32_CR26","unstructured":"Shi, Y., Pei, X., Dong, M., Xu, C.: Catching the details: self-distilled ROI predictors for fine-grained MLLM perception (2025). arXiv:2509.16944 arXiv preprint"},{"key":"32_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"},{"key":"32_CR28","unstructured":"Team, K., et\u00a0al.: Kimi K2.5: visual agentic intelligence (2026). arXiv:2602.02276"},{"issue":"1","key":"32_CR29","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/0010-0285(80)90005-5","volume":"12","author":"AM Treisman","year":"1980","unstructured":"Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97\u2013136 (1980)","journal-title":"Cogn. Psychol."},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V*: guided visual search as a core mechanism in multimodal LLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13084\u201313094 (2024)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Yao, J., et al.: Who is in the spotlight: the hidden bias undermining multimodal retrieval-augmented generation. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 15194\u201315204 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.768"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"You, K., et al.: Ferret-UI: grounded mobile UI understanding with multimodal LLMs. In: European Conference on Computer Vision, pp. 240\u2013255. Springer (2024)","DOI":"10.1007\/978-3-031-73039-9_14"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Zhai, S., Meng, Y., Zhang, Y., Qi, G.: Parameter-aware contrastive knowledge editing: tracing and rectifying based on critical transmission paths. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 28189\u201328200 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1367"},{"key":"32_CR34","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: MLLMs know where to look: training-free perception of small visual details with multimodal LLMs. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yu, T., Feng, Y.: TruthX: alleviating hallucinations by editing large language models in truthful space. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 8908\u20138949 (2024)","DOI":"10.18653\/v1\/2024.acl-long.483"},{"key":"32_CR36","unstructured":"Zhang, X., et al.: Seeing clearly by layer two: enhancing attention heads to alleviate hallucination in LVLMs (2024). arXiv:2411.09968 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\/978-3-032-37383-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:21:31Z","timestamp":1789374091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37383-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373823","9783032373830"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37383-0_32","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":"15 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"}}]}}