{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:42:01Z","timestamp":1783096921457,"version":"3.54.6"},"publisher-location":"Cham","reference-count":102,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734137","type":"print"},{"value":"9783031734144","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-73414-4_27","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:02:54Z","timestamp":1729789374000},"page":"471-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["The All-Seeing Project V2: Towards General Relation Comprehension of\u00a0the\u00a0Open World"],"prefix":"10.1007","author":[{"given":"Weiyun","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haowen","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lewei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xizhou","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 39\u201348 (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"27_CR2","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"27_CR3","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. (2023). https:\/\/cdnopenai.com\/papers\/dall-e-3.pdf"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Biten, A.F., et al.: Scene text visual question answering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4291\u20134301 (2019)","DOI":"10.1109\/ICCV.2019.00439"},{"key":"27_CR5","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"27_CR6","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":"27_CR7","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":"27_CR8","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":"27_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793 (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"27_CR10","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.14238 (2023)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Clark, C., Gardner, M.: Simple and effective multi-paragraph reading comprehension. arXiv preprint arXiv:1710.10723 (2017)","DOI":"10.18653\/v1\/P18-1078"},{"key":"27_CR13","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1109\/TPAMI.2023.3268066","volume":"45","author":"Y Cong","year":"2023","unstructured":"Cong, Y., Yang, M.Y., Rosenhahn, B.: Reltr: relation transformer for scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 11169\u201311183 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Dai, B., Zhang, Y., Lin, D.: Detecting visual relationships with deep relational networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.352"},{"key":"27_CR15","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. arXiv preprint arXiv:2305.06500 (2023)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Dupty, M.H., Zhang, Z., Lee, W.S.: Visual relationship detection with low rank non-negative tensor decomposition. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6702"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Eva: exploring the limits of masked visual representation learning at scale. arXiv preprint arXiv:2211.07636 (2022)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"27_CR18","unstructured":"Fu, C., et\u00a0al.: Mme: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"27_CR19","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. In: NeurIPS (2020)"},{"key":"27_CR20","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544 (2021)"},{"key":"27_CR21","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., Ling, M.: Scene graph generation with external knowledge and image reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00207"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"27_CR24","unstructured":"Hu, Y., Chen, S., Chen, X., Zhang, Y., Gu, X.: Neural message passing for visual relationship detection. In: ICMLW (2019)"},{"key":"27_CR25","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"27_CR26","doi-asserted-by":"publisher","first-page":"3820","DOI":"10.1109\/TPAMI.2020.2992222","volume":"43","author":"ZS Hung","year":"2020","unstructured":"Hung, Z.S., Mallya, A., Lazebnik, S.: Contextual translation embedding for visual relationship detection and scene graph generation. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3820\u20133832 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Hwang, S.J., Ravi, S.N., Tao, Z., Kim, H.J., Collins, M.D., Singh, V.: Tensorize, factorize and regularize: robust visual relationship learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00112"},{"key":"27_CR28","unstructured":"IDEFICS: Introducing idefics: an open reproduction of state-of-the-art visual language model (2023). https:\/\/huggingface.co\/blog\/idefics"},{"key":"27_CR29","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning (2021)"},{"key":"27_CR30","unstructured":"Jiang, Y., et al.: Effectiveness assessment of recent large vision-language models. arXiv preprint arXiv:2403.04306 (2024)"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der\u00a0Maaten, L., Fei-Fei, L., Lawrence\u00a0Zitnick, C., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"27_CR33","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":"27_CR34","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. arXiv preprint arXiv:2308.00692 (2023)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"27_CR35","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":"27_CR36","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"27_CR37","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":"27_CR38","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"27_CR39","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS (2021)"},{"key":"27_CR40","unstructured":"Li, K., et al.: Videochat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, S., He, X.: Sgtr: end-to-end scene graph generation with transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"27_CR42","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: EMNLP (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Wang, X., Tang, X.: Vip-cnn: visual phrase guided convolutional neural network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.766"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Li, Y., Ouyang, W., Zhou, B., Wang, K., Wang, X.: Scene graph generation from objects, phrases and region captions. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.142"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Liao, W., Rosenhahn, B., Shuai, L., Ying\u00a0Yang, M.: Natural language guided visual relationship detection. In: CVPRW (2019)","DOI":"10.1109\/CVPRW.2019.00058"},{"key":"27_CR46","unstructured":"Lin, J., et al.: Vila: on pre-training for visual language models. arXiv preprint arXiv:2312.07533 (2023)"},{"key":"27_CR47","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":"27_CR48","doi-asserted-by":"crossref","unstructured":"Lin, X., Ding, C., Zeng, J., Tao, D.: Gps-net: graph property sensing network for scene graph generation. In: CVPR, pp. 3746\u20133753 (2020)","DOI":"10.1109\/CVPR42600.2020.00380"},{"issue":"1","key":"27_CR49","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s44267-024-00049-8","volume":"2","author":"C Liu","year":"2024","unstructured":"Liu, C., Jiang, X., Ding, H.: Primitivenet: decomposing the global constraints for referring segmentation. Visual Intell. 2(1), 16 (2024)","journal-title":"Visual Intell."},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Trans. Assoc. Comput. Linguist. (2023)","DOI":"10.1162\/tacl_a_00566"},{"key":"27_CR51","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Aligning large multi-modal model with robust instruction tuning. arXiv preprint arXiv:2306.14565 (2023)"},{"key":"27_CR52","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":"27_CR53","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"27_CR54","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":"27_CR55","unstructured":"Liu, Z., et\u00a0al.: Interngpt: solving vision-centric tasks by interacting with chatgpt beyond language. arXiv preprint arXiv:2305.05662 (2023)"},{"key":"27_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1007\/978-3-319-46448-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"C Lu","year":"2016","unstructured":"Lu, C., Krishna, R., Bernstein, M., Fei-Fei, L.: Visual relationship detection with language priors. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 852\u2013869. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_51"},{"key":"27_CR57","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"27_CR58","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS (2022)"},{"key":"27_CR59","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":"27_CR60","unstructured":"OpenAI: Gpt-4 technical report (2023). arXiv preprint arXiv:2303.08774"},{"key":"27_CR61","unstructured":"OpenAI: Gpt-4v(ision) system card (2023)"},{"key":"27_CR62","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"27_CR63","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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"27_CR64","doi-asserted-by":"crossref","unstructured":"Qi, M., Li, W., Yang, Z., Wang, Y., Luo, J.: Attentive relational networks for mapping images to scene graphs. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00408"},{"key":"27_CR65","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"27_CR66","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":"27_CR67","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: ACL (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"27_CR68","doi-asserted-by":"publisher","unstructured":"Shit, S., et\u00a0al.: Relationformer: a unified framework for image-to-graph generation. In: ECCV 2022, pp. 422\u2013439. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_24","DOI":"10.1007\/978-3-031-19836-6_24"},{"key":"27_CR69","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards vqa models that can read. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"27_CR70","unstructured":"Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"27_CR71","doi-asserted-by":"crossref","unstructured":"Suhr, A., Lewis, M., Yeh, J., Artzi, Y.: A corpus of natural language for visual reasoning. In: Annual Meeting of the Association for Computer Linguistics (2017)","DOI":"10.18653\/v1\/P17-2034"},{"key":"27_CR72","doi-asserted-by":"crossref","unstructured":"Tang, K., Zhang, H., Wu, B., Luo, W., Liu, W.: Learning to compose dynamic tree structures for visual contexts. In: CVPR, pp. 6619\u20136628 (2019)","DOI":"10.1109\/CVPR.2019.00678"},{"key":"27_CR73","unstructured":"Tian, C., et\u00a0al.: Mm-interleaved: interleaved image-text generative modeling via multi-modal feature synchronizer. arXiv preprint arXiv:2401.10208 (2024)"},{"key":"27_CR74","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"27_CR75","doi-asserted-by":"crossref","unstructured":"Wang, J., Wen, Z., Li, X., Guo, Z., Yang, J., Liu, Z.: Pair then relation: pair-net for panoptic scene graph generation. arXiv preprint arXiv:2307.08699 (2023)","DOI":"10.1109\/TPAMI.2024.3442301"},{"key":"27_CR76","unstructured":"Wang, P., et al.: Ofa: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: ICML (2022)"},{"key":"27_CR77","unstructured":"Wang, W., et\u00a0al.: The all-seeing project: towards panoptic visual recognition and understanding of the open world. arXiv preprint arXiv:2308.01907 (2023)"},{"key":"27_CR78","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":"27_CR79","unstructured":"Wu, J., et al.: Grit: a generative region-to-text transformer for object understanding. arXiv preprint arXiv:2212.00280 (2022)"},{"key":"27_CR80","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"27_CR81","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":"27_CR82","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity. arXiv preprint arXiv:2310.07704 (2023)"},{"key":"27_CR83","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Ernie-vil: knowledge enhanced vision-language representations through scene graphs. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"27_CR84","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"27_CR85","doi-asserted-by":"crossref","unstructured":"Yu, L., Tan, H., Bansal, M., Berg, T.L.: A joint speaker-listener-reinforcer model for referring expressions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.375"},{"key":"27_CR86","doi-asserted-by":"crossref","unstructured":"Yu, Q., et al.: Capsfusion: rethinking image-text data at scale. arXiv preprint arXiv:2310.20550 (2023)","DOI":"10.1109\/CVPR52733.2024.01330"},{"key":"27_CR87","unstructured":"Yu, W., et al.: Mm-vet: evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"27_CR88","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"27_CR89","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00611"},{"key":"27_CR90","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"27_CR91","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":"27_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, H., Kyaw, Z., Chang, S.F., Chua, T.S.: Visual translation embedding network for visual relation detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.331"},{"key":"27_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, J., Kalantidis, Y., Rohrbach, M., Paluri, M., Elgammal, A., Elhoseiny, M.: Large-scale visual relationship understanding. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33019185"},{"key":"27_CR94","unstructured":"Zhang, S., et al.: Gpt4roi: instruction tuning large language model on region-of-interest. arXiv preprint arXiv:2307.03601 (2023)"},{"key":"27_CR95","unstructured":"Zhang, Y., et al.: Llavar: enhanced visual instruction tuning for text-rich image understanding. arXiv preprint arXiv:2306.17107 (2023)"},{"key":"27_CR96","unstructured":"Zhao, B., Wu, B., Huang, T.: Svit: scaling up visual instruction tuning. arXiv preprint arXiv:2307.04087 (2023)"},{"key":"27_CR97","doi-asserted-by":"crossref","unstructured":"Zhao, C., Shen, Y., Chen, Z., Ding, M., Gan, C.: Textpsg: panoptic scene graph generation from textual descriptions. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00266"},{"key":"27_CR98","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena (2023)"},{"key":"27_CR99","doi-asserted-by":"crossref","unstructured":"Zheng, S., Chen, S., Jin, Q.: Visual relation detection with multi-level attention. In: ACM MM (2019)","DOI":"10.1145\/3343031.3350962"},{"key":"27_CR100","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Shi, J., Yang, J., Xu, C., Li, Y.: Learning to generate scene graph from natural language supervision. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00184"},{"key":"27_CR101","unstructured":"Zhou, Z., Shi, M., Caesar, H.: Vlprompt: vision-language prompting for panoptic scene graph generation. arXiv preprint arXiv:2311.16492 (2023)"},{"key":"27_CR102","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\/978-3-031-73414-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T06:54:22Z","timestamp":1732949662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73414-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031734137","9783031734144"],"references-count":102,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73414-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 October 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"}}]}}