{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T01:10:13Z","timestamp":1743383413415,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":47,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819626403","type":"print"},{"value":"9789819626410","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\/978-981-96-2641-0_23","type":"book-chapter","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:55:44Z","timestamp":1743382544000},"page":"338-354","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Approach to\u00a0Complex Visual Data Interpretation with\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0491-9327","authenticated-orcid":false,"given":"Thanh-Son","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8537-1331","authenticated-orcid":false,"given":"Viet-Tham","family":"Huynh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9351-3750","authenticated-orcid":false,"given":"Van-Loc","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"23_CR1","unstructured":"Agrawal, A., et al.: VQA: visual question answering (2016). https:\/\/arxiv.org\/abs\/1505.00468"},{"key":"23_CR2","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning (2022). https:\/\/arxiv.org\/abs\/2204.14198"},{"key":"23_CR3","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: NeurIPS (2022)"},{"key":"23_CR4","unstructured":"Awadalla, A., et al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models (2023). https:\/\/arxiv.org\/abs\/2308.01390"},{"key":"23_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821 (2024)","DOI":"10.1007\/s11432-024-4231-5"},{"key":"23_CR7","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":"23_CR8","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":"23_CR9","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv:2210.11416 (2022)"},{"key":"23_CR10","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023). https:\/\/arxiv.org\/abs\/2305.06500"},{"key":"23_CR11","unstructured":"Dai, W., Li, X., Zhang, C., Hu, X., Li, J., Yin, X.: MiniGPT-4: enhancing ChatGPT with multimodal abilities. arXiv:2304.10592 (2023)"},{"key":"23_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"23_CR13","unstructured":"Gao, P., et al.: Llama-adapter V2: parameter-efficient visual instruction model (2023). https:\/\/arxiv.org\/abs\/2304.15010"},{"key":"23_CR14","unstructured":"Huang, Y., Meng, Z., Liu, F., Su, Y., Collier, N., Lu, Y.: Sparkles: Unlocking chats across multiple images for multimodal instruction-following models (2024). https:\/\/arxiv.org\/abs\/2308.16463"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering (2019). https:\/\/arxiv.org\/abs\/1902.09506","DOI":"10.1109\/CVPR.2019.00686"},{"key":"23_CR16","unstructured":"Jia, C., et al.: Align: scaling up visual and vision-language representation learning with noisy text supervision. In: ICML. PMLR (2021)"},{"key":"23_CR17","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: A multi-modal model with in-context instruction tuning (2023). https:\/\/arxiv.org\/abs\/2305.03726"},{"key":"23_CR18","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: Benchmarking multimodal LLMS with generative comprehension (2023). https:\/\/arxiv.org\/abs\/2307.16125"},{"key":"23_CR19","unstructured":"Li, J., Hu, D., Zhao, H., Zhang, L., Li, X., Gao, J.: BLIP-2: bootstrapped language-image pre-training with frozen image encoders and large language models. arXiv:2301.12597 (2023)"},{"key":"23_CR20","unstructured":"Li, L., et al.: M$$^3$$it: a large-scale dataset towards multi-modal multilingual instruction tuning. arXiv preprint arXiv:2306.04387 (2023)"},{"key":"23_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"23_CR22","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 (2023). https:\/\/arxiv.org\/abs\/2305.10355","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"23_CR23","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context (2015). https:\/\/arxiv.org\/abs\/1405.0312"},{"key":"23_CR24","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":"23_CR25","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., Gehrig, M., Messikommer, N., Cannici, M., Scaramuzza, D.: Revisiting token pruning for object detection and instance segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00264"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: MMBench: is your multi-modal model an all-around player? (2024). https:\/\/arxiv.org\/abs\/2307.06281","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"23_CR28","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"23_CR29","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts (2024). https:\/\/arxiv.org\/abs\/2310.02255"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge (2019). https:\/\/arxiv.org\/abs\/1906.00067","DOI":"10.1109\/CVPR.2019.00331"},{"key":"23_CR31","unstructured":"Mialon, G., Fourrier, C., Swift, C., Wolf, T., LeCun, Y., Scialom, T.: Gaia: a benchmark for general AI assistants (2023). https:\/\/arxiv.org\/abs\/2311.12983"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Monajatipoor, M., Li, L.H., Rouhsedaghat, M., Yang, L.F., Chang, K.W.: MetaVL: transferring in-context learning ability from language models to vision-language models (2023). https:\/\/arxiv.org\/abs\/2306.01311","DOI":"10.18653\/v1\/2023.acl-short.43"},{"key":"23_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv:2103.00020 (2021)"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: EMNLP-IJCNLP. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"23_CR35","unstructured":"Wang, J., et\u00a0al.: Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126 (2023)"},{"key":"23_CR36","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"23_CR37","unstructured":"Wang, Y., et al.: SIMVLM: simple visual language model pretraining with weak supervision. arXiv:2108.10904 (2021)"},{"key":"23_CR38","unstructured":"Xu, P., et al.: LVLM-EHUB: a comprehensive evaluation benchmark for large vision-language models (2023). https:\/\/arxiv.org\/abs\/2306.09265"},{"key":"23_CR39","unstructured":"Ye, Q., et al.: MPLUG-OWL: modularization empowers large language models with multimodality (2024). https:\/\/arxiv.org\/abs\/2304.14178"},{"key":"23_CR40","unstructured":"Yin, Z.,et\u00a0al.: LAMM: language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR41","unstructured":"Yu, J., et al.: COCA: contrastive captioners are image-text foundation models. arXiv:2205.01917 (2022)"},{"key":"23_CR42","unstructured":"Yu, W., et al.: MM-VET: evaluating large multimodal models for integrated capabilities (2023). https:\/\/arxiv.org\/abs\/2308.02490"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"23_CR44","unstructured":"Zhang, M., et al.: FUYU: fully unified vision-language models for multimodal tasks. arXiv:2305.05999 (2023)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VINVL: revisiting visual representations in vision-language models. In: CVPR. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"23_CR46","unstructured":"Zhao, H., et al.: MMICL: empowering vision-language model with multi-modal in-context learning (2024). https:\/\/arxiv.org\/abs\/2309.07915"},{"key":"23_CR47","unstructured":"Zhu, Y., et al.: LLAVA: large language and vision assistant. arXiv:2304.08485 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2641-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:56:21Z","timestamp":1743382581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2641-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819626403","9789819626410"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2641-0_23","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":"29 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}