{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:02:13Z","timestamp":1782576133580,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":59,"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_17","type":"book-chapter","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:57:43Z","timestamp":1743382663000},"page":"249-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Questioning, Answering, and\u00a0Captioning for\u00a0Zero-Shot Detailed Image Caption"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3893-8582","authenticated-orcid":false,"given":"Duc-Tuan","family":"Luu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2289-8128","authenticated-orcid":false,"given":"Viet-Tuan","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4839-032X","authenticated-orcid":false,"given":"Duc Minh","family":"Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"17_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"17_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., 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":"17_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"17_CR4","unstructured":"Anil, R., Dai, A.M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et\u00a0al.: Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"17_CR5","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":"17_CR6","unstructured":"Chen, D., Cahyawijaya, S., Ishii, E., Chan, H.S., Bang, Y., Fung, P.: The pyramid of captions. arXiv preprint arXiv:2405.00485 (2024)"},{"key":"17_CR7","unstructured":"Chen, G.H., Chen, S., Zhang, R., Chen, J., Wu, X., Zhang, Z., Chen, Z., Li, J., Wan, X., Wang, B.: Allava: Harnessing gpt4v-synthesized data for a lite vision-language model. arXiv preprint arXiv:2402.11684 (2024)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, J., Dong, X., Zhang, P., He, C., Wang, J., Zhao, F., Lin, D.: 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":"17_CR9","unstructured":"Chen, X., Wang, X., Changpinyo, S., Piergiovanni, A., Padlewski, P., Salz, D., Goodman, S., Grycner, A., Mustafa, B., Beyer, L., et\u00a0al.: Pali: A jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Cherti, M., Beaumont, R., Wightman, R., Wortsman, M., Ilharco, G., Gordon, C., Schuhmann, C., Schmidt, L., Jitsev, J.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"17_CR11","unstructured":"Chiang, W.L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J.E., et\u00a0al.: Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna.lmsys.org (accessed 14 April 2023) 2(3), 6 (2023)"},{"issue":"240","key":"17_CR12","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., Gehrmann, S., et al.: Palm: Scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"17_CR13","unstructured":"Dai, W., Li, J., Li, D., Tiong, A.M.H., Zhao, J., Wang, W., Li, B., Fung, P., Hoi, S.: Instructblip: Towards general-purpose vision-language models with instruction tuning. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"17_CR14","unstructured":"Dai, W., Li, J., Li, D., Tiong, A.M.H., Zhao, J., Wang, W., Li, B., Fung, P., Hoi, S.: Instructblip: Towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"17_CR15","unstructured":"Desai, K., Kaul, G., Aysola, Z., Johnson, J.: Redcaps: Web-curated image-text data created by the people, for the people. arXiv preprint arXiv:2111.11431 (2021)"},{"key":"17_CR16","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., Tian, Y.: Improving clip training with language rewrites. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Garg, R., Burns, A., Ayan, B.K., Bitton, Y., Montgomery, C., Onoe, Y., Bunner, A., Krishna, R., Baldridge, J., Soricut, R.: Imageinwords: Unlocking hyper-detailed image descriptions. arXiv preprint arXiv:2405.02793 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.6"},{"key":"17_CR18","unstructured":"Gaur, M., Tapaswi, M., et\u00a0al.: No detail left behind: Revisiting self-retrieval for fine-grained image captioning. arXiv preprint arXiv:2409.03025 (2024)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Ge, Y., Zeng, X., Huffman, J.S., Lin, T.Y., Liu, M.Y., Cui, Y.: Visual fact checker: Enabling high-fidelity detailed caption generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14033\u201314042 (2024)","DOI":"10.1109\/CVPR52733.2024.01331"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Hong, W., Wang, W., Lv, Q., Xu, J., Yu, W., Ji, J., Wang, Y., Wang, Z., Dong, Y., Ding, M., 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":"17_CR21","unstructured":"Hsieh, Y.G., Hsieh, C.Y., Yeh, S.Y., B\u00e9thune, L., Ansari, H.P., Vasu, P.K.A., Li, C.L., Krishna, R., Tuzel, O., Cuturi, M.: Graph-based captioning: Enhancing visual descriptions by interconnecting region captions. arXiv preprint arXiv:2407.06723 (2024)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: Fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"17_CR24","unstructured":"Li, F., Zhang, R., Zhang, H., Zhang, Y., Li, B., Li, W., Ma, Z., Li, C.: Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Li, J., Vo, D.M., Sugimoto, A., Nakayama, H.: Evcap: Retrieval-augmented image captioning with external visual-name memory for open-world comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13733\u201313742 (2024)","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"17_CR26","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: International conference on machine learning. pp. 19730\u201319742. PMLR (2023)"},{"key":"17_CR27","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International conference on machine learning. pp. 12888\u201312900. PMLR (2022)"},{"key":"17_CR28","unstructured":"Li, X., Zhang, F., Diao, H., Wang, Y., Wang, X., Duan, L.Y.: Densefusion-1m: Merging vision experts for comprehensive multimodal perception. arXiv preprint arXiv:2407.08303 (2024)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., Yang, B., Liu, Q., Ma, Z., Zhang, S., Yang, J., Sun, Y., Liu, Y., Bai, X.: Monkey: Image resolution and text label are important things for large multi-modal models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 26763\u201326773 (2024)","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"17_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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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":"17_CR31","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"17_CR32","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Advances in neural information processing systems 36 (2024)"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Onoe, Y., Rane, S., Berger, Z., Bitton, Y., Cho, J., Garg, R., Ku, A., Parekh, Z., Pont-Tuset, J., Tanzer, G., et\u00a0al.: Docci: Descriptions of connected and contrasting images. arXiv preprint arXiv:2404.19753 (2024)","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"17_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/978-3-030-58558-7_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Pont-Tuset","year":"2020","unstructured":"Pont-Tuset, J., Uijlings, J., Changpinyo, S., Soricut, R., Ferrari, V.: Connecting Vision and Language with Localized Narratives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 647\u2013664. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_38"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Radenovic, F., Dubey, A., Kadian, A., Mihaylov, T., Vandenhende, S., Patel, Y., Wen, Y., Ramanathan, V., Mahajan, D.: Filtering, distillation, and hard negatives for vision-language pre-training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 6967\u20136977 (2023)","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"17_CR36","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Ramos, R., Martins, B., Elliott, D., Kementchedjhieva, Y.: Smallcap: lightweight image captioning prompted with retrieval augmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2840\u20132849 (2023)","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Rasheed, H., Maaz, M., Shaji, S., Shaker, A., Khan, S., Cholakkal, H., Anwer, R.M., Xing, E., Yang, M.H., Khan, F.S.: Glamm: Pixel grounding large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13009\u201313018 (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"17_CR39","unstructured":"Ravi, N., Gabeur, V., Hu, Y.T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., Gustafson, L., et\u00a0al.: Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"17_CR40","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al.: Laion-5b: An open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR41","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":"17_CR42","doi-asserted-by":"crossref","unstructured":"Shi, B., Wu, Z., Mao, M., Wang, X., Darrell, T.: When do we not need larger vision models? arXiv preprint arXiv:2403.13043 (2024)","DOI":"10.1007\/978-3-031-73242-3_25"},{"key":"17_CR43","unstructured":"Singla, V., Yue, K., Paul, S., Shirkavand, R., Jayawardhana, M., Ganjdanesh, A., Huang, H., Bhatele, A., Somepalli, G., Goldstein, T.: From pixels to prose: A large dataset of dense image captions. arXiv preprint arXiv:2406.10328 (2024)"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Sun, Q., Cui, Y., Zhang, X., Zhang, F., Yu, Q., Wang, Y., Rao, Y., Liu, J., Huang, T., Wang, X.: Generative multimodal models are in-context learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14398\u201314409 (2024)","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"17_CR45","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"17_CR46","unstructured":"Sun, Q., Yu, Q., Cui, Y., Zhang, F., Zhang, X., Wang, Y., Gao, H., Liu, J., Huang, T., Wang, X.: Emu: Generative pretraining in multimodality. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"17_CR47","unstructured":"Team, G., Anil, R., Borgeaud, S., Wu, Y., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"issue":"2","key":"17_CR48","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., Shamma, D.A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., Li, L.J.: Yfcc100m: The new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016)","journal-title":"Commun. ACM"},{"key":"17_CR49","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Urbanek, J., Bordes, F., Astolfi, P., Williamson, M., Sharma, V., Romero-Soriano, A.: A picture is worth more than 77 text tokens: Evaluating clip-style models on dense captions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 26700\u201326709 (2024)","DOI":"10.1109\/CVPR52733.2024.02521"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Wang, W., Ren, Y., Luo, H., Li, T., Yan, C., Chen, Z., Wang, W., Li, Q., Lu, L., Zhu, X., et\u00a0al.: The all-seeing project v2: Towards general relation comprehension of the open world. arXiv preprint arXiv:2402.19474 (2024)","DOI":"10.1007\/978-3-031-73414-4_27"},{"key":"17_CR52","unstructured":"Wang, W., Shi, M., Li, Q., Wang, W., Huang, Z., Xing, L., Chen, Z., Li, H., Zhu, X., Cao, Z., et\u00a0al.: The all-seeing project: Towards panoptic visual recognition and understanding of the open world. arXiv preprint arXiv:2308.01907 (2023)"},{"key":"17_CR53","unstructured":"Xie, N., Lai, F., Doran, D., Kadav, A.: Visual entailment: A novel task for fine-grained image understanding. arXiv preprint arXiv:1901.06706 (2019)"},{"key":"17_CR54","unstructured":"Xu, R., Yao, Y., Guo, Z., Cui, J., Ni, Z., Ge, C., Chua, T.S., Liu, Z., Sun, M., Huang, G.: Llava-uhd: an lmm perceiving any aspect ratio and high-resolution images. arXiv preprint arXiv:2403.11703 (2024)"},{"key":"17_CR55","unstructured":"You, H., Guo, M., Wang, Z., Chang, K.W., Baldridge, J., Yu, J.: Cobit: A contrastive bi-directional image-text generation model. arXiv preprint arXiv:2303.13455 (2023)"},{"key":"17_CR56","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics 2, 67\u201378 (2014)","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"17_CR57","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":"17_CR58","doi-asserted-by":"crossref","unstructured":"Yu, Q., Sun, Q., Zhang, X., Cui, Y., Zhang, F., Cao, Y., Wang, X., Liu, J.: Capsfusion: Rethinking image-text data at scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14022\u201314032 (2024)","DOI":"10.1109\/CVPR52733.2024.01330"},{"key":"17_CR59","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"}],"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_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:58:46Z","timestamp":1743382726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2641-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819626403","9789819626410"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2641-0_17","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"}}]}}