{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T06:11:44Z","timestamp":1730700704172,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681400","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"38-47","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Flexible Evaluation for Generative Visual Question Answering"],"prefix":"10.1145","author":[{"ORCID":"http:\/\/orcid.org\/0009-0002-7815-9508","authenticated-orcid":false,"given":"Huishan","family":"Ji","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8433-0215","authenticated-orcid":false,"given":"Qingyi","family":"Si","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8432-1658","authenticated-orcid":false,"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences &amp; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8618-4992","authenticated-orcid":false,"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2387636.2387697"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-2010"},{"key":"e_1_3_2_2_3_1","first-page":"497","volume-title":"10th International Workshop on Semantic Evaluation; 2016 Jun 16--17; San Diego, CA","author":"Agirre Eneko","year":"2016","unstructured":"Eneko Agirre, Carmen Banea, Daniel Cer, Mona Diab, Aitor Gonzalez Agirre, Rada Mihalcea, German Rigau Claramunt, and Janyce Wiebe. 2016. Semeval-2016 task 1: Semantic textual similarity, monolingual and cross-lingual evaluation. In SemEval-2016. 10th International Workshop on Semantic Evaluation; 2016 Jun 16--17; San Diego, CA. Stroudsburg (PA): ACL; 2016. p. 497--511. ACL (Association for Computational Linguistics)."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval","author":"Agirre Eneko","year":"2012","unstructured":"Eneko Agirre, Daniel Cer, Mona Diab, and Aitor Gonzalez-Agirre. 2012. SemEval-2012 Task 6: A Pilot on Semantic Textual Similarity.* SEM 2012: The First Joint Conference on Lexical and Computational Semantics?. In Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012), Montr\u00e9al, QC, Canada. 7--8."},{"volume-title":"Second joint conference on lexical and computational semantics (* SEM)","author":"Agirre Eneko","key":"e_1_3_2_2_5_1","unstructured":"Eneko Agirre, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, and Weiwei Guo. 2013. * SEM 2013 shared task: Semantic textual similarity. In Second joint conference on lexical and computational semantics (* SEM), volume 1: proceedings of the Main conference and the shared task: semantic textual similarity. 32--43."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_8_1","volume-title":"Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"volume-title":"Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305","year":"2023","key":"e_1_3_2_2_9_1","unstructured":"Baichuan. 2023. Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305 (2023). https:\/\/arxiv.org\/abs\/2309.10305"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_2_11_1","volume-title":"Re-evaluating evaluation in text summarization. arXiv preprint arXiv:2010.07100","author":"Bhandari Manik","year":"2020","unstructured":"Manik Bhandari, Pranav Gour, Atabak Ashfaq, Pengfei Liu, and Graham Neubig. 2020. Re-evaluating evaluation in text summarization. arXiv preprint arXiv:2010.07100 (2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation. arXiv preprint arXiv:1708.00055","author":"Cer Daniel","year":"2017","unstructured":"Daniel Cer, Mona Diab, Eneko Agirre, Inigo Lopez-Gazpio, and Lucia Specia. 2017. Semeval-2017 task 1: Semantic textual similarity-multilingual and cross-lingual focused evaluation. arXiv preprint arXiv:1708.00055 (2017)."},{"key":"e_1_3_2_2_13_1","volume-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models. arXiv preprint arXiv:2306.13394","author":"Chaoyou Fu","year":"2023","unstructured":"Fu Chaoyou, Chen Peixian, Shen Yunhang, Qin Yulei, Zhang Mengdan, Lin Xu, Yang Jinrui, Zheng Xiawu, Li Ke, Sun Xing, Wu Yunsheng, and Ji Rongrong. 2023. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models. arXiv preprint arXiv:2306.13394 (2023)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2023. BGE M3-Embedding: Multi-Lingual Multi-Functionality Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. arxiv: 2309.07597 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_2_15_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_16_1","volume-title":"Senteval: An evaluation toolkit for universal sentence representations. arXiv preprint arXiv:1803.05449","author":"Conneau Alexis","year":"2018","unstructured":"Alexis Conneau and Douwe Kiela. 2018. Senteval: An evaluation toolkit for universal sentence representations. arXiv preprint arXiv:1803.05449 (2018)."},{"key":"e_1_3_2_2_17_1","volume-title":"Supervised learning of universal sentence representations from natural language inference data. arXiv preprint arXiv:1705.02364","author":"Conneau Alexis","year":"2017","unstructured":"Alexis Conneau, Douwe Kiela, Holger Schwenk, Lo\"ic Barrault, and Antoine Bordes. 2017. Supervised learning of universal sentence representations from natural language inference data. arXiv preprint arXiv:1705.02364 (2017)."},{"key":"e_1_3_2_2_18_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv preprint arXiv:2305.06500 (2023)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00373"},{"key":"e_1_3_2_2_20_1","volume-title":"Brown corpus manual. Letters to the Editor","author":"Nelson Francis W","year":"1979","unstructured":"W Nelson Francis and Henry Kucera. 1979. Brown corpus manual. Letters to the Editor, Vol. 5, 2 (1979), 7."},{"key":"e_1_3_2_2_21_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_2_23_1","volume-title":"Newsroom: A dataset of 1.3 million summaries with diverse extractive strategies. arXiv preprint arXiv:1804.11283","author":"Grusky Max","year":"2018","unstructured":"Max Grusky, Mor Naaman, and Yoav Artzi. 2018. Newsroom: A dataset of 1.3 million summaries with diverse extractive strategies. arXiv preprint arXiv:1804.11283 (2018)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_2_2_25_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_2_27_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"e_1_3_2_2_29_1","unstructured":"Klaus Krippendorff. 2011. Computing Krippendorff?s alpha-reliability."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision Vol. 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_31_1","volume-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_32_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_2_33_1","volume-title":"AnglE-optimized Text Embeddings. arXiv preprint arXiv:2309.12871","author":"Li Xianming","year":"2023","unstructured":"Xianming Li and Jing Li. 2023. AnglE-optimized Text Embeddings. arXiv preprint arXiv:2309.12871 (2023)."},{"key":"e_1_3_2_2_34_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_2_35_1","volume-title":"Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023. Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)."},{"key":"e_1_3_2_2_36_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_37_1","volume-title":"Convbench: A multi-turn conversation evaluation benchmark with hierarchical capability for large vision-language models. arXiv preprint arXiv:2403.20194","author":"Liu Shuo","year":"2024","unstructured":"Shuo Liu, Kaining Ying, Hao Zhang, Yue Yang, Yuqi Lin, Tianle Zhang, Chuanhao Li, Yu Qiao, Ping Luo, Wenqi Shao, et al. 2024. Convbench: A multi-turn conversation evaluation benchmark with hierarchical capability for large vision-language models. arXiv preprint arXiv:2403.20194 (2024)."},{"key":"e_1_3_2_2_38_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_39_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Fixing weight decay regularization in adam. (2017)."},{"key":"e_1_3_2_2_40_1","volume-title":"A multi-world approach to question answering about real-world scenes based on uncertain input. Advances in neural information processing systems","author":"Malinowski Mateusz","year":"2014","unstructured":"Mateusz Malinowski and Mario Fritz. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_2_41_1","volume-title":"9th Language Resources and Evaluation Conference. Reykjavik.","author":"Marelli Marco","year":"2014","unstructured":"Marco Marelli, Stefano Menini, Marco Baroni, Luisa Bentivogli, Raffaella Bernardi, and Roberto Zamparelli. 2014. A SICK cure for the evaluation of compositional distributional semantic models. In 9th Language Resources and Evaluation Conference. Reykjavik."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1093\/ijl\/3.4.235"},{"key":"e_1_3_2_2_44_1","volume-title":"Generative Representational Instruction Tuning. arXiv preprint arXiv:2402.09906","author":"Niklas Muennighoff","year":"2024","unstructured":"Muennighoff Niklas, Su Hongjin, Wang Liang, Yang Nan, Wei Furu, Yu Tao, Singh Amanpreet, and Kiela Douwe. 2024. Generative Representational Instruction Tuning. arXiv preprint arXiv:2402.09906 (2024)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_2_47_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_2_48_1","volume-title":"Exploring models and data for image question answering. Advances in neural information processing systems","author":"Ren Mengye","year":"2015","unstructured":"Mengye Ren, Ryan Kiros, and Richard Zemel. 2015. Exploring models and data for image question answering. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_2_49_1","volume-title":"A-okvqa: A benchmark for visual question answering using world knowledge. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27","author":"Schwenk Dustin","year":"2022","unstructured":"Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, and Roozbeh Mottaghi. 2022. A-okvqa: A benchmark for visual question answering using world knowledge. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part VIII. Springer, 146--162."},{"key":"e_1_3_2_2_50_1","unstructured":"Wenqi Shao Yutao Hu Peng Gao Meng Lei Kaipeng Zhang Fanqing Meng Peng Xu Siyuan Huang Hongsheng Li Yu Qiao et al. 2023. Tiny lvlm-ehub: Early multimodal experiments with bard. arXiv preprint arXiv:2308.03729 (2023)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Chuanqi Tan Furu Wei Wenhui Wang Weifeng Lv and Ming Zhou. 2018. Multiway attention networks for modeling sentence pairs.. In IJCAI. 4411--4417.","DOI":"10.24963\/ijcai.2018\/613"},{"key":"e_1_3_2_2_52_1","volume-title":"Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490","author":"Tan Hao","year":"2019","unstructured":"Hao Tan and Mohit Bansal. 2019. Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)."},{"key":"e_1_3_2_2_53_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_54_1","volume-title":"Fvqa: Fact-based visual question answering","author":"Wang Peng","year":"2017","unstructured":"Peng Wang, Qi Wu, Chunhua Shen, Anthony Dick, and Anton Van Den Hengel. 2017. Fvqa: Fact-based visual question answering. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 10 (2017), 2413--2427."},{"key":"e_1_3_2_2_55_1","volume-title":"Explicit knowledge-based reasoning for visual question answering. arXiv preprint arXiv:1511.02570","author":"Wang Peng","year":"2015","unstructured":"Peng Wang, Qi Wu, Chunhua Shen, Anton van den Hengel, and Anthony Dick. 2015. Explicit knowledge-based reasoning for visual question answering. arXiv preprint arXiv:1511.02570 (2015)."},{"key":"e_1_3_2_2_56_1","volume-title":"International Conference on Machine Learning. PMLR, 23318--23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning. PMLR, 23318--23340."},{"key":"e_1_3_2_2_57_1","volume-title":"A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:1704.05426","author":"Williams Adina","year":"2017","unstructured":"Adina Williams, Nikita Nangia, and Samuel R Bowman. 2017. A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:1704.05426 (2017)."},{"key":"e_1_3_2_2_58_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online, 38--45. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"e_1_3_2_2_59_1","volume-title":"Image captioning and visual question answering based on attributes and external knowledge","author":"Wu Qi","year":"2017","unstructured":"Qi Wu, Chunhua Shen, Peng Wang, Anthony Dick, and Anton Van Den Hengel. 2017. Image captioning and visual question answering based on attributes and external knowledge. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 6 (2017), 1367--1381."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_2_61_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00097"},{"key":"e_1_3_2_2_63_1","volume-title":"Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi. arXiv preprint arXiv:2404.16006","author":"Ying Kaining","year":"2024","unstructured":"Kaining Ying, Fanqing Meng, Jin Wang, Zhiqian Li, Han Lin, Yue Yang, Hao Zhang, Wenbo Zhang, Yuqi Lin, Shuo Liu, et al. 2024. Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi. arXiv preprint arXiv:2404.16006 (2024)."},{"key":"e_1_3_2_2_64_1","volume-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490","author":"Yu Weihao","year":"2023","unstructured":"Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)."},{"key":"e_1_3_2_2_65_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T05:31:40Z","timestamp":1730698300000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":64,"alternative-id":["10.1145\/3664647.3681400","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681400","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}  <script>parent.window.postMessage('ixistenz.url:https://api.crossref.org/works/10.1145%2F3664647.3681400', '*'); </script> <div id='browserdiffcontainer' style='position: fixed; right: 10px; top: 10vh; min-width: 60px;  border: 1px solid white; background: rgb(251, 189, 0);; opacity: 0.9; font-family: helvetica, arial, sans serif;  font-size: 12px; z-index: 20001; padding-bottom: 20px;'><div onclick="toggle('browserdiffcontainerlist'); return false;" style='background: rgb(151, 89, 0);; color: white; '><strong>&nbsp; <span class='glyphicon glyphicon-minus'></span> NODES</strong></div><div id='browserdiffcontainerlist' style='padding-left: 10px; padding-right: 5px; max-height: 50vh; overflow: auto; '><div><a href='#diffid883' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:883', '*');; return false;" style='text-decoration: none; '>Association </a> <a style='color: white;' href='#diffid883'><sup>5</sup></a></div><div><a href='#diffid117' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:117', '*');; return false;" style='text-decoration: none; '>chat </a> <a style='color: white;' href='#diffid117'><sup>1</sup></a></div><div><a href='#diffid123' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:123', '*');; return false;" style='text-decoration: none; '>INTERN </a> <a style='color: white;' href='#diffid123'><sup>11</sup></a></div></div></div>
<script>
function toggle( divname ) {
  var x = document.getElementById( divname );
  if (x.style.display === 'none') {
    x.style.display = 'block';
  } else {
    x.style.display = 'none';
  }
} </script>