{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:14:23Z","timestamp":1781018063906,"version":"3.54.1"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031918124","type":"print"},{"value":"9783031918131","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91813-1_4","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:41:58Z","timestamp":1748090518000},"page":"52-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["GPT4RoI: Instruction Tuning Large Language Model on\u00a0Region-of-Interest"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4336-4941","authenticated-orcid":false,"given":"Shilong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0636-2224","authenticated-orcid":false,"given":"Peize","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6126-2595","authenticated-orcid":false,"given":"Shoufa","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqi","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-4514","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"4_CR1","first-page":"23716","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":"4_CR2","unstructured":"Anthropic: Claude (2023). https:\/\/www.anthropic.com\/index\/introducing-claude"},{"key":"4_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR4","unstructured":"Bubeck, S., et\u00a0al.: Sparks of artificial general intelligence: early experiments with GPT-4. arXiv preprint arXiv:2303.12712 (2023)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cai, M., et al.: Making large multimodal models understand arbitrary visual prompts (2023)","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"4_CR8","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic (2023)"},{"key":"4_CR9","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: universal image-text representation learning (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"4_CR11","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"4_CR12","unstructured":"Chowdhery, A., et\u00a0al.: PALM: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"4_CR13","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: ECCV, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"4_CR15","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"4_CR16","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":"4_CR17","unstructured":"Driess, D., et\u00a0al.: PALM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Du, Z., et al.: GLM: general language model pretraining with autoregressive blank infilling. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 320\u2013335 (2022)","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: EVA-02: a visual representation for neon genesis. arXiv preprint arXiv:2303.11331 (2023)","DOI":"10.2139\/ssrn.4813567"},{"key":"4_CR20","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning (2020)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"4_CR22","unstructured":"Gong, T., et al.: Multimodal-GPT: a vision and language model for dialogue with humans (2023)"},{"key":"4_CR23","unstructured":"Google: Bard (2023). https:\/\/bard.google.com\/"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Guo, Q., et al.: RegionGPT: towards region understanding vision language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13796\u201313806 (2024)","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE international Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4_CR26","unstructured":"Huang, S., et\u00a0al.: Language is not all you need: aligning perception with language models. arXiv preprint arXiv:2302.14045 (2023)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning (2015)","DOI":"10.1109\/CVPR.2016.494"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR \u2013 modulated detection for end-to-end multi-modal understanding (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"4_CR29","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. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D., Zhou, M.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training (2019)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"4_CR31","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"4_CR32","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language (2019)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., Wang, X.: Scene graph generation from objects, phrases and region captions (2017)","DOI":"10.1109\/ICCV.2017.142"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"4_CR36","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":"4_CR37","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"4_CR38","unstructured":"Liu, R., et al.: An intriguing failing of convolutional neural networks and the coordconv solution (2018)"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4_CR41","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":"4_CR42","unstructured":"Liu, Z., et\u00a0al.: InternChat: solving vision-centric tasks by interacting with chatbots beyond language. arXiv preprint arXiv:2305.05662 (2023)"},{"key":"4_CR43","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks (2019)"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Ma, C., Jiang, Y., Wu, J., Yuan, Z., Qi, X.: Groma: localized visual tokenization for grounding multimodal large language models. arXiv preprint arXiv:2404.13013 (2024)","DOI":"10.1007\/978-3-031-72658-3_24"},{"key":"4_CR45","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"4_CR46","unstructured":"Mu, Y., et al.: EmbodiedGPT: vision-language pre-training via embodied chain of thought. arXiv preprint arXiv:2305.15021 (2023)"},{"key":"4_CR47","unstructured":"OpenAI: ChatGPT (2022). https:\/\/openai.com\/blog\/chatgpt"},{"key":"4_CR48","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"4_CR49","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2Text: describing images using 1 million captioned photographs. Advances in Neural Inf. Process. Syst. 24 (2011)"},{"key":"4_CR50","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR51","unstructured":"Peng, Z., Wang, W., Dong, L., Hao, Y., Huang, S., Ma, S., Wei, F.: Kosmos-2: grounding multimodal large language models to the world (2023)"},{"key":"4_CR52","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: DetGPT: detect what you need via reasoning. arXiv preprint arXiv:2305.14167 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Pi, R., Yao, L., Gao, J., Zhang, J., Zhang, T.: PerceptionGPT: effectively fusing visual perception into LLM (2023)","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Pramanick, S., et al.: Jack of all tasks, master of many: designing general-purpose coarse-to-fine vision-language model (2023)","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"4_CR56","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":"4_CR57","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training. OpenAI (2018)"},{"issue":"1","key":"4_CR58","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"4_CR59","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GLaMM: pixel grounding large multimodal model. arXiv preprint arXiv:2311.03356 (2023)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"4_CR60","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR61","unstructured":"Schuhmann, C., et al.: LAION-400m: open dataset of CLIP-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"4_CR63","unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"4_CR64","unstructured":"Sun, T., Xipeng, Q.: Moss (2022). https:\/\/github.com\/OpenLMLab\/MOSS"},{"key":"4_CR65","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: ViperGPT: visual inference via python execution for reasoning. arXiv preprint arXiv:2303.08128 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts (2018)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"4_CR67","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following llama model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"4_CR68","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"4_CR69","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"4_CR70","unstructured":"Wang, T., et\u00a0al.: Caption anything: interactive image description with diverse multimodal controls. arXiv preprint arXiv:2305.02677 (2023)"},{"key":"4_CR71","unstructured":"Wang, W., et al.: CogVLM: visual expert for pretrained language models (2023)"},{"key":"4_CR72","unstructured":"Wang, W., et\u00a0al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. arXiv preprint arXiv:2305.11175 (2023)"},{"key":"4_CR73","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-030-58523-5_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Wang","year":"2020","unstructured":"Wang, X., Kong, T., Shen, C., Jiang, Y., Li, L.: SOLO: segmenting objects by locations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 649\u2013665. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_38"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yasunaga, M., Ren, H., Wada, S., Leskovec, J.: VQA-GNN: reasoning with multimodal semantic graph for visual question answering (2022)","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"key":"4_CR75","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatGPT: talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)"},{"key":"4_CR76","unstructured":"Wu, J., et al.: GRiT: a generative region-to-text transformer for object understanding (2022)"},{"key":"4_CR77","unstructured":"Xu, P., et al.: LVLM-eHub: a comprehensive evaluation benchmark for large vision-language models (2023)"},{"key":"4_CR78","unstructured":"Yang, J., et al.: pave the way to grasp anything: transferring foundation models for universal pick-place robots. arXiv preprint arXiv:2306.05716 (2023)"},{"key":"4_CR79","doi-asserted-by":"crossref","unstructured":"Yang, J., Ang, Y.Z., Guo, Z., Zhou, K., Zhang, W., Liu, Z.: Panoptic scene graph generation (2022)","DOI":"10.1007\/978-3-031-19812-0_11"},{"key":"4_CR80","doi-asserted-by":"crossref","unstructured":"Yang, L., Tang, K., Yang, J., Li, L.J.: Dense captioning with joint inference and visual context. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.214"},{"key":"4_CR81","unstructured":"Yang, Z., et al.: MM-react: prompting chatGPT for multimodal reasoning and action. arXiv preprint arXiv:2303.11381 (2023)"},{"key":"4_CR82","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: PEVL: position-enhanced pre-training and prompt tuning for vision-language models. arXiv preprint arXiv:2205.11169 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"4_CR83","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704 (2023)"},{"key":"4_CR84","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: ERNIE-ViL: knowledge enhanced vision-language representations through scene graph (2021)","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"4_CR85","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":"4_CR86","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et al.: Osprey: pixel understanding with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"4_CR87","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Han, J., Zhou, K., Loy, C.C.: Contextual object detection with multimodal large language models (2023)","DOI":"10.1007\/s11263-024-02214-4"},{"key":"4_CR88","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6720\u20136731 (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"4_CR89","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"4_CR90","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: MERLOT reserve: multimodal neural script knowledge through vision and language and sound. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"4_CR91","unstructured":"Zellers, R., et al.: MERLOT: multimodal neural script knowledge models. In: Adv. Neural Inf. Process. Syst. 34 (2021)"},{"key":"4_CR92","unstructured":"Zhang, A., et al.: Transfer visual prompt generator across LLMs. arXiv preprint arXiv:2305.01278 (2023)"},{"key":"4_CR93","unstructured":"Zhang, A., Zhao, L., Xie, C.W., Zheng, Y., Ji, W., Chua, T.S.: Next-chat: an LMM for chat, detection and segmentation. arXiv preprint arXiv:2311.04498 (2023)"},{"key":"4_CR94","unstructured":"Zhang, R., et al.: LLaMA-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"4_CR95","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Dense distinct query for end-to-end object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7329\u20137338 (2023)","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"4_CR96","unstructured":"Zhao, Y., Lin, Z., Zhou, D., Huang, Z., Feng, J., Kang, B.: BuboGPT: enabling visual grounding in multi-modal LLMs (2023)"},{"key":"4_CR97","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"},{"key":"4_CR98","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"4_CR99","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"4_CR100","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":"4_CR101","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91813-1_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:42:25Z","timestamp":1748090545000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91813-1_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031918124","9783031918131"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91813-1_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}