{"type":"ScholarlyArticle","title":"An Empirical Study on the Language Modal in Visual Question Answering","authors":[{"name":"Daowan Peng","slug":"daowan-peng","given":"Daowan","family":"Peng","affiliation":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory , School of Computer Science and Technology , Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"},{"name":"Wei Wei","slug":"wei-wei","given":"Wei","family":"Wei","affiliation":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory , School of Computer Science and Technology , Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"},{"name":"Xian-Ling Mao","slug":"xian-ling-mao","given":"Xian-Ling","family":"Mao","affiliation":"Department of Computer Science and Technology , Beijing Institute of Technology"},{"name":"Yuanyuan Fu","slug":"yuanyuan-fu","given":"Yuanyuan","family":"Fu","affiliation":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property & Casualty Insurance Company of China , Ltd"},{"name":"Dangyang Chen","slug":"dangyang-chen","given":"Dangyang","family":"Chen","affiliation":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property & Casualty Insurance Company of China , Ltd"}],"abstract":"Generalization beyond in-domain experience to out-of-distribution data is of paramount significance in the AI domain. Of late, state-of-the-art Visual Question Answering (VQA) models have shown impressive performance on in-domain data, partially due to the language prior bias which, however, hinders the generalization ability in practice. This paper attempts to provide new insights into the influence of language modality on VQA performance from an empirical study perspective. To achieve this, we conducted a series of experiments on six models. The results of these experiments revealed that, 1) apart from prior bias caused by question types, there is a notable influence of postfix-related bias in inducing biases, and 2) training VQA models with word-sequence-related variant questions demonstrated improved performance on the out-of-distribution benchmark, and the LXMERT even achieved a 10-point gain without adopting any debiasing methods. We delved into the underlying reasons behind these experimental results and put forward some simple proposals to reduce the models' dependency on language priors. The experimental results demonstrated the effectiveness of our proposed method in improving performance on the out-of-distribution benchmark, VQA-CPv2.  We hope this study can inspire novel insights for future research on designing bias-reduction approaches.","doi":"10.24963/ijcai.2023/457","url":"https://ijcai.org/proceedings/2023/457","pdf":"https://ijcai.org/proceedings/2023/0457.pdf","markdown":"https://ijcai.org/proceedings/2023/457.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/457","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":457,"pages":{"first":4109,"last":4117},"keywords":["Computer Vision: CV: Vision and language","Machine Learning: ML: Multi-modal learning","Natural Language Processing: NLP: Question answering"],"videos":[],"references":[{"position":1,"raw":"[Agrawal et al., 2017] Aishwarya Agrawal, Jiasen Lu, Stanislaw Antol, Margaret Mitchell, C Zitnick, Devi Parikh, and Dhruv Batra. Vqa: Visual question answering. IJCV, 123(1):4-31, 2017.","title":"Vqa: Visual question answering","authors":"Aishwarya Agrawal, Jiasen Lu, Stanislaw Antol, Margaret Mitchell, C Zitnick, Devi Parikh, Dhruv Batra","year":"2017","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Agrawal et al., 2018] Aishwarya Agrawal, Dhruv Batra, Devi Parikh, and Aniruddha Kembhavi. Don't just assume; look and answer: Overcoming priors for visual question answering. In CVPR, pages 4971-4980, 2018.","title":"Don't just assume; look and answer: Overcoming priors for visual question answering","authors":"Aishwarya Agrawal, Dhruv Batra, Devi Parikh, Aniruddha Kembhavi","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Anderson et al., 2018] Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. Bottom-up and top-down attention for im- age captioning and visual question answering. In CVPR, pages 6077-6086, 2018.","title":"Bottom-up and top-down attention for image captioning and visual question answering","authors":"Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, Lei Zhang","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Antol et al., 2015] Stanislaw Antol, Aishwarya Agrawal, Ji- asen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zit- nick, and Devi Parikh. VQA: visual question answering. In ICCV, pages 2425-2433, 2015.","title":"VQA: visual question answering","authors":"Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, Devi Parikh","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cadene et al., 2019] Remi Cadene, Corentin Dancette, Matthieu Cord, Devi Parikh, et al. Rubi: Reducing uni- modal biases for visual question answering. In NeurIPS, pages 839-850, 2019.","title":"Rubi: Reducing unimodal biases for visual question answering","authors":"Cadene","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2020a] Long Chen, Xin Yan, Jun Xiao, Han- wang Zhang, Shiliang Pu, and Yueting Zhuang. Coun- terfactual samples synthesizing for robust visual question answering. In CVPR, pages 10800-10809, 2020.","title":"Counterfactual samples synthesizing for robust visual question answering","authors":"Chen","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2020b] Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. Uniter: Universal image-text representation learning. In ECCV, pages 104-120, 2020.","title":"Uniter: Universal image-text representation learning","authors":"Chen","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. In EMNLP, pages 1724-1734, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Clark et al., 2019] Christopher Clark, Mark Yatskar, and Luke Zettlemoyer. Don't take the easy way out: Ensem- ble based methods for avoiding known dataset biases. In EMNLP-IJCNLP, pages 4067-4080, 2019.","title":"Don't take the easy way out: Ensemble based methods for avoiding known dataset biases","authors":"Christopher Clark, Mark Yatskar, Luke Zettlemoyer","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cui et al., 2022] Yiming Cui, Ziqing Yang, and Ting Liu. Pert: Pre-training bert with permuted language model. CoRR, abs/2203.06906, 2022.","title":"Pert: Pre-training bert with permuted language model","authors":"Yiming Cui, Ziqing Yang, Ting Liu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: pre-training of deep bidirectional transformers for language understand- ing. In NAACL-HLT, pages 4171-4186, 2019.","title":"BERT: pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gokhale et al., 2020] Tejas Gokhale, Pratyay Banerjee, Chitta Baral, and Yezhou Yang. Vqa-lol: Visual question answering under the lens of logic. In ECCV, pages 379- 396, 2020.","title":"Vqa-lol: Visual question answering under the lens of logic","authors":"Gokhale","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Goyal et al., 2017] Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. Making the v in vqa matter: Elevating the role of image understanding in visual question answering. In CVPR, pages 6325-6334, 2017.","title":"Making the v in vqa matter: Elevating the role of image understanding in visual question answering","authors":"Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, Devi Parikh","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Guo et al., 2021] Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, and Del Alberto Bimbo. Adavqa: Overcoming language priors with adapted mar- gin cosine loss. In IJCAI, pages 708-714, 2021.","title":"Adavqa: Overcoming language priors with adapted margin cosine loss","authors":"Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Del Alberto Bimbo","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/98"},{"position":15,"raw":"[Gupta et al., 2022] Vipul Gupta, Zhuowan Li, Adam Ko- rtylewski, Chenyu Zhang, Yingwei Li, and Alan Yuille. Swapmix: Diagnosing and regularizing the over-reliance on visual context in visual question answering. In CVPR, pages 5078-5088, 2022.","title":"Swapmix: Diagnosing and regularizing the over-reliance on visual context in visual question answering","authors":"Vipul Gupta, Zhuowan Li, Adam Kortylewski, Chenyu Zhang, Yingwei Li, Alan Yuille","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Han et al., 2021] Xinzhe Han, Shuhui Wang, Chi Su, Qing- ming Huang, and Qi Tian. Greedy gradient ensemble for robust visual question answering. In ICCV, pages 1564- 1573, 2021.","title":"Greedy gradient ensemble for robust visual question answering","authors":"Han","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Jing et al., 2020] Chenchen Jing, Yuwei Wu, Xiaoxun Zhang, Yunde Jia, and Qi Wu. Overcoming language pri- ors in vqa via decomposed linguistic representations. In AAAI, pages 11181-11188, 2020.","title":"Overcoming language priors in vqa via decomposed linguistic representations","authors":"Chenchen Jing, Yuwei Wu, Xiaoxun Zhang, Yunde Jia, Qi Wu","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Karpathy and Fei-Fei, 2015] Andrej Karpathy and Li Fei- Fei. Deep visual-semantic alignments for generating im- age descriptions. In CVPR, pages 3128-3137, 2015.","title":"Deep visual-semantic alignments for generating image descriptions","authors":"Fei-Fei ; Karpathy, Andrej Karpathy, Li Fei-Fei","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kervadec et al., 2021a] Corentin Kervadec, Grigory An- tipov, Moez Baccouche, and Christian Wolf. Roses are red, violets are blue... but should vqa expect them to? In CVPR, pages 2776-2785, 2021.","title":"Corentin Kervadec, Grigory Antipov, Moez Baccouche, and Christian Wolf. Roses are red, violets are blue... but should vqa expect them to","authors":"Kervadec","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Kervadec et al., 2021b] Corentin Kervadec, Theo Jaunet, Grigory Antipov, Moez Baccouche, Romain Vuillemot, and Christian Wolf. How transferable are reasoning pat- terns in vqa? In CVPR, pages 4207-4216, 2021.","title":"How transferable are reasoning patterns in vqa?","authors":"Kervadec","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Kim et al., 2018] Jin-Hwa Kim, Jaehyun Jun, and Byoung- Tak Zhang. Bilinear attention networks. In NeurIPS, pages 1571-1581, 2018.","title":"Bilinear attention networks","authors":"Jin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lao et al., 2021] Mingrui Lao, Yanming Guo, Yu Liu, and Michael S Lew. A language prior based focal loss for vi- sual question answering. In ICME, pages 1-6. IEEE, 2021.","title":"A language prior based focal loss for visual question answering","authors":"Lao","year":"2021","venue":"ICME","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Liang et al., 2020] Zujie Liang, Weitao Jiang, Haifeng Hu, and Jiaying Zhu. Learning to contrast the counterfactual samples for robust visual question answering. In EMNLP, pages 3285-3292, 2020.","title":"Learning to contrast the counterfactual samples for robust visual question answering","authors":"Liang","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Liang et al., 2021] Zujie Liang, Haifeng Hu, and Jiaying Zhu. Lpf: A language-prior feedback objective function for de-biased visual question answering. In SIGIR, pages 1955-1959, 2021.","title":"Lpf: A language-prior feedback objective function for de-biased visual question answering","authors":"Liang","year":"2021","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Liu et al., 2022a] Yuhang Liu, Wei Wei, Daowan Peng, Xian-Ling Mao, Zhiyong He, and Pan Zhou. Depth-aware and semantic guided relational attention network for visual question answering. TMM, pages 1-14, 2022.","title":"Depth-aware and semantic guided relational attention network for visual question answering","authors":"Liu","year":"2022","venue":"TMM","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Liu et al., 2022b] Yuhang Liu, Wei Wei, Daowan Peng, and Feida Zhu. Declaration-based prompt tuning for visual question answering. In IJCAI, pages 3264-3270, 2022.","title":"Declaration-based prompt tuning for visual question answering","authors":"Liu","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2022/453"},{"position":28,"raw":"[Ramakrishnan et al., 2018] Sainandan Ramakrishnan, Aishwarya Agrawal, and Stefan Lee. Overcoming lan- guage priors in visual question answering with adversarial regularization. In NeurIPS, pages 1548-1558, 2018.","title":"Overcoming language priors in visual question answering with adversarial regularization","authors":"Ramakrishnan","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Selvaraju et al., 2019] Ramprasaath R Selvaraju, Stefan Lee, Yilin Shen, Hongxia Jin, Shalini Ghosh, Larry Heck, Dhruv Batra, and Devi Parikh. Taking a hint: Leverag- ing explanations to make vision and language models more grounded. In ICCV, pages 2591-2600, 2019.","title":"Taking a hint: Leveraging explanations to make vision and language models more grounded","authors":"Stefan Ramprasaath R Selvaraju, Yilin Lee, Hongxia Shen, Shalini Jin, Larry Ghosh, Dhruv Heck, Devi Batra, Parikh","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Shah et al., 2019] Meet Shah, Xinlei Chen, Marcus Rohrbach, and Devi Parikh. Cycle-consistency for robust visual question answering. In CVPR, pages 6649-6658, 2019.","title":"Cycle-consistency for robust visual question answering","authors":"Shah","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Shrestha et al., 2020] Robik Shrestha, Kushal Kafle, and Christopher Kanan. A negative case analysis of visual grounding methods for vqa. In ACL, pages 8172-8181, 2020.","title":"A negative case analysis of visual grounding methods for vqa","authors":"Shrestha","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Su et al., 2020] Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. Vl-bert: Pre-training of generic visual-linguistic representations. In ICLR, 2020.","title":"Vl-bert: Pre-training of generic visual-linguistic representations","authors":"Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Suhr et al., 2017] Alane Suhr, Mike Lewis, James Yeh, and Yoav Artzi. A corpus of natural language for visual rea- soning. In ACL, pages 217-223, 2017.","title":"A corpus of natural language for visual reasoning","authors":"Alane Suhr, Mike Lewis, James Yeh, Yoav Artzi","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Tan and Bansal, 2019] Hao Tan and Mohit Bansal. Lxmert: Learning cross-modality encoder representations from transformers. In EMNLP-IJCNLP, pages 5099-5110, 2019.","title":"Lxmert: Learning cross-modality encoder representations from transformers","authors":"Hao Tan, Mohit Bansal","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wang et al., 2022] Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. Simvlm: Sim- ple visual language model pretraining with weak supervi- sion. In ICLR, 2022.","title":"Simvlm: Simple visual language model pretraining with weak supervision","authors":"Wang","year":"2022","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wen et al., 2021] Zhiquan Wen, Guanghui Xu, Mingkui Tan, Qingyao Wu, and Qi Wu. Debiased visual ques- tion answering from feature and sample perspectives. In NeurIPS, pages 3784-3796, 2021.","title":"Debiased visual question answering from feature and sample perspectives","authors":"Wen","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Wu and Mooney, 2019] Jialin Wu and J. Raymond Mooney. Self-critical reasoning for robust visual question answer- ing. In NeurIPS, pages 8601-8611, 2019.","title":"Self-critical reasoning for robust visual question answering","authors":"Jialin Wu, J Raymond Mooney","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Xie et al., 2018] Ning Xie, Farley Lai, Derek Doran, and Asim Kadav. Visual entailment task for visually-grounded language learning. CoRR, abs/1811.10582, 2018.","title":"Visual entailment task for visually-grounded language learning","authors":"Ning Xie, Farley Lai, Derek Doran, Asim Kadav","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Yang et al., 2016] Zichao Yang, Xiaodong He, Jianfeng Gao, Li Deng, and Alex Smola. Stacked attention net- works for image question answering. In CVPR, pages 21- 29, 2016.","title":"Stacked attention networks for image question answering","authors":"Yang","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Yang et al., 2021] Chao Yang, Su Feng, Dongsheng Li, Huawei Shen, Guoqing Wang, and Bin Jiang. Learning content and context with language bias for visual question answering. In ICME, pages 1-6. IEEE, 2021.","title":"Learning content and context with language bias for visual question answering","authors":"Chao Yang, Su Feng, Dongsheng Li, Huawei Shen, Guoqing Wang, Bin Jiang","year":"2021","venue":"ICME","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Yu et al., 2016] Licheng Yu, Patrick Poirson, Shan Yang, Alexander C Berg, and Tamara L Berg. Modeling context in referring expressions. In ECCV, pages 69-85, 2016.","title":"Modeling context in referring expressions","authors":"Licheng Yu, Patrick Poirson, Shan Yang, Alexander C Berg, Tamara L Berg","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Yu et al., 2019] Zhou Yu, Jun Yu, Yuhao Cui, Dacheng Tao, and Qi Tian. Deep modular co-attention networks for visual question answering. In CVPR, pages 6281-6290, 2019.","title":"Deep modular co-attention networks for visual question answering","authors":"Zhou Yu, Jun Yu, Yuhao Cui, Dacheng Tao, Qi Tian","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Yulei et al., 2021] Niu Yulei, Tang Kaihua, Zhang Han- wang, Lu Zhiwu, Hua Xian-Sheng, and Wen Ji-Rong. Counterfactual vqa: A cause-effect look at language bias. In CVPR, pages 12700-12710, 2021.","title":"Counterfactual vqa: A cause-effect look at language bias","authors":"Niu Yulei, Tang Kaihua, Zhang Hanwang, Lu Zhiwu, Wen Ji-Rong Hua Xian-Sheng","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Zellers et al., 2019] Rowan Zellers, Yonatan Bisk, Ali Farhadi, and Yejin Choi. From recognition to cognition: Visual commonsense reasoning. In CVPR, pages 6720- 6731, 2019.","title":"From recognition to cognition: Visual commonsense reasoning","authors":"Rowan Zellers, Yonatan Bisk, Ali Farhadi, Yejin Choi","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Zeng et al., 2022] Yan Zeng, Xinsong Zhang, and Hang Li. Multi-grained vision language pre-training: Aligning texts with visual concepts. In ICML, pages 25994-26009, 2022.","title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","authors":"Yan Zeng, Xinsong Zhang, Hang Li","year":"2022","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Zhang et al., 2021] Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, and Jianfeng Gao. Vinvl: Revisiting visual representations in vision-language models. In CVPR, pages 5579-5588, 2021.","title":"Vinvl: Revisiting visual representations in vision-language models","authors":"Zhang","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}