{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T07:48:49Z","timestamp":1784274529351,"version":"3.55.0"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730030","type":"print"},{"value":"9783031730047","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73004-7_19","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:06:30Z","timestamp":1730394390000},"page":"323-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["SAM4MLLM: Enhance Multi-Modal Large Language Model for\u00a0Referring Expression Segmentation"],"prefix":"10.1007","author":[{"given":"Yi-Chia","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Hua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu-Song","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"19_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"19_CR2","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Aminabadi, R.Y., et\u00a0al.: Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale. In: SC (2022)","DOI":"10.1109\/SC41404.2022.00051"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: Vqa: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"19_CR5","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"19_CR6","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"19_CR8","unstructured":"Cai, H., Gan, C., Han, S.: Efficientvit: enhanced linear attention for high-resolution low-computation visual recognition. In: ECCV (2023)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Chen, D.J., Jia, S., Lo, Y.C., Chen, H.T., Liu, T.L.: See-through-text grouping for referring image segmentation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00755"},{"key":"19_CR10","unstructured":"Chen, J., et al.: Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"19_CR11","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal llm\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"19_CR12","unstructured":"Chen, X., et\u00a0al.: Symbolic discovery of optimization algorithms. In: NeurIPS (2024)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.: Detect what you can: detecting and representing objects using holistic models and body parts. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.254"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"19_CR15","unstructured":"Chowdhery, A., et\u00a0al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. (2023)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Floridi, L., Chiriatti, M.: Gpt-3: its nature, scope, limits, and consequences. Minds Mach. (2020)","DOI":"10.2139\/ssrn.3827044"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"He, J., et al.: Partimagenet: a large, high-quality dataset of parts. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"19_CR20","unstructured":"Hu, E.J., et\u00a0al.: Lora: low-rank adaptation of large language models. In: ICLR (2021)"},{"key":"19_CR21","unstructured":"Huang, S., et\u00a0al.: Language is not all you need: aligning perception with language models. In: NeurIPS (2023)"},{"key":"19_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-030-58607-2_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Hui","year":"2020","unstructured":"Hui, T., Liu, S., Huang, S., Li, G., Yu, S., Zhang, F., Han, J.: Linguistic structure guided context modeling for referring image segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 59\u201375. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_4"},{"key":"19_CR23","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Jing, Y., Kong, T., Wang, W., Wang, L., Li, L., Tan, T.: Locate then segment: a strong pipeline for referring image segmentation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"19_CR26","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32\u201373 (2017)","journal-title":"IJCV"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"19_CR28","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: ICML (2023)"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"19_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Lin, Z., et\u00a0al.: Sphinx: the joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. arXiv preprint arXiv:2311.07575 (2023)","DOI":"10.1007\/978-3-031-73033-7_3"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: Gres: generalized referring expression segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"19_CR33","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2024)"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Polyformer: referring image segmentation as sequential polygon generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"19_CR37","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. In: ICLR (2024)"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: Detgpt: detect what you need via reasoning. In: ACL (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Pi, R., Yao, L., Gao, J., Zhang, J., Zhang, T.: Perceptiongpt: effectively fusing visual perception into llm. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"19_CR40","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., et\u00a0al.: Paco: parts and attributes of common objects. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: Glamm: pixel grounding large multimodal model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: Pixellm: pixel reasoning with large multimodal model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"19_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/978-3-319-46448-0_49","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Rohrbach","year":"2016","unstructured":"Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T., Schiele, B.: Grounding of textual phrases in images by reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 817\u2013834. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_49"},{"key":"19_CR45","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"19_CR46","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"19_CR47","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Cris: clip-driven referring image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"19_CR49","unstructured":"Workshop, B., et\u00a0al.: Bloom: a 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Xia, Z., Han, D., Han, Y., Pan, X., Song, S., Huang, G.: Gsva: generalized segmentation via multimodal large language models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, Z., Zhang, Y., Song, Y., Wan, X., Li, G.: Bridging vision and language encoders: parameter-efficient tuning for referring image segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"19_CR52","doi-asserted-by":"publisher","unstructured":"Yang, J., Ang, Y.Z., Guo, Z., Zhou, K., Zhang, W., Liu, Z.: Panoptic scene graph generation. In: ECCV 2022, pp. 178\u2013196. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_11","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: Lavt: language-aware vision transformer for referring image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"19_CR54","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity. In: ICLR (2024)"},{"key":"19_CR55","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. (2014)","DOI":"10.1162\/tacl_a_00166"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Mattnet: modular attention network for referring expression comprehension. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00142"},{"key":"19_CR57","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"19_CR58","unstructured":"Zhang, R., et al.: Llama-adapter: efficient fine-tuning of language models with zero-init attention. In: ICLR (2023)"},{"key":"19_CR59","unstructured":"Zhang, S., et al.: Gpt4roi: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"19_CR60","unstructured":"Zhang, S., et\u00a0al.: Opt: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"19_CR61","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"19_CR62","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. In: ICCV (2019)","DOI":"10.1007\/s11263-018-1140-0"},{"key":"19_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, C., et al.: Seqtr: a simple yet universal network for visual grounding. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"19_CR64","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)"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"19_CR66","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. In: NeurIPS (2024)"}],"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\/978-3-031-73004-7_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:08:44Z","timestamp":1730394524000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}