{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:47:28Z","timestamp":1781797648726,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Ministry of Science, Research and the Arts Baden-W\u00fcrttemberg in the Artificial Intelligence Software Academy (AISA)"},{"name":"Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy -- EXC 2075","award":["390740016"],"award-info":[{"award-number":["390740016"]}]},{"name":"Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)","award":["251654672 -- TRR 161"],"award-info":[{"award-number":["251654672 -- TRR 161"]}]},{"name":"Swiss National Science Foundation (SNSF), Postdoc. Mobility Fellowship","award":["214434"],"award-info":[{"award-number":["214434"]}]},{"name":"European Research Council (ERC)","award":["801708"],"award-info":[{"award-number":["801708"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642942","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:38:06Z","timestamp":1715416686000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["SalChartQA: Question-driven Saliency on Information Visualisations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3633-8623","authenticated-orcid":false,"given":"Yao","family":"Wang","sequence":"first","affiliation":[{"name":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4781-0120","authenticated-orcid":false,"given":"Weitian","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7385-4287","authenticated-orcid":false,"given":"Abdullah","family":"Abdelhafez","sequence":"additional","affiliation":[{"name":"German University in Cairo, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6490-9139","authenticated-orcid":false,"given":"Mayar","family":"Elfares","sequence":"additional","affiliation":[{"name":"Institute for Visualisation and Interactive Systems\/ Institute for Information Security, University of Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5105-9753","authenticated-orcid":false,"given":"Zhiming","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1446-379X","authenticated-orcid":false,"given":"Mihai","family":"B\u00e2ce","sequence":"additional","affiliation":[{"name":"Department of Computer Science, KU Leuven, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6317-7303","authenticated-orcid":false,"given":"Andreas","family":"Bulling","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557200"},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376449"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2857491.2857524"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247710"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2467732"},{"key":"e_1_3_3_3_7_1","first-page":"1","article-title":"Saliency based on information maximization","volume":"18","author":"Bruce Neil","year":"2005","unstructured":"Neil Bruce and John Tsotsos. 2005. Saliency based on information maximization. Advances in Neural Information Processing Systems 18 (2005), 1\u20138.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3573381.3596153"},{"key":"e_1_3_3_3_9_1","volume-title":"ETVIS","author":"Burch Michael","year":"2017","unstructured":"Michael Burch, Lewis Chuang, Brian Fisher, Albrecht Schmidt, and Daniel Weiskopf. 2017. Eye tracking and visualization: Foundations, Techniques, and applications. ETVIS 2015. ACM."},{"key":"e_1_3_3_3_10_1","volume-title":"What do different evaluation metrics tell us about saliency models?IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 41, 3","author":"Bylinskii Zoya","year":"2018","unstructured":"Zoya Bylinskii, Tilke Judd, Aude Oliva, Antonio Torralba, and Fr\u00e9do Durand. 2018. What do different evaluation metrics tell us about saliency models?IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 41, 3 (2018), 740\u2013757."},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126653"},{"key":"e_1_3_3_3_12_1","volume-title":"Enhancing Product Images for Click-Through Rate Improvement. In 2018 25th IEEE International Conference on Image Processing (ICIP). 1428\u20131432","author":"Chae Yeongnam","year":"2018","unstructured":"Yeongnam Chae, Mitsuru Nakazawa, and Bj\u00f6rn Stenger. 2018. Enhancing Product Images for Click-Through Rate Improvement. In 2018 25th IEEE International Conference on Image Processing (ICIP). 1428\u20131432."},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2851672"},{"key":"e_1_3_3_3_16_1","volume-title":"Proceedings of the International Conference on Human-Computer Interaction (INTERACT). Springer, 428\u2013437","author":"Cubero Carlos\u00a0Gomez","year":"2021","unstructured":"Carlos\u00a0Gomez Cubero and Matthias Rehm. 2021. Intention Recognition in Human Robot Interaction Based on Eye Tracking. In Proceedings of the International Conference on Human-Computer Interaction (INTERACT). Springer, 428\u2013437."},{"key":"e_1_3_3_3_17_1","volume-title":"Human attention in visual question answering: Do humans and deep networks look at the same regions?Computer Vision and Image Understanding 163","author":"Das Abhishek","year":"2017","unstructured":"Abhishek Das, Harsh Agrawal, Larry Zitnick, Devi Parikh, and Dhruv Batra. 2017. Human attention in visual question answering: Do humans and deep networks look at the same regions?Computer Vision and Image Understanding 163 (2017), 90\u2013100."},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_3_19_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (NAACL). ACL, 4171\u20134186."},{"key":"e_1_3_3_3_20_1","volume-title":"International Conference on Learning Representations (ICLR). 1\u201322","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR). 1\u201322."},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415825"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00453"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2532331"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206505.3206592"},{"key":"e_1_3_3_3_25_1","volume-title":"Attentive Turkers: MTurk participants perform better on online attention checks than do subject pool participants. Behavior research methods 48","author":"Hauser J","year":"2016","unstructured":"David\u00a0J Hauser and Norbert Schwarz. 2016. Attentive Turkers: MTurk participants perform better on online attention checks than do subject pool participants. Behavior research methods 48 (2016), 400\u2013407."},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3138902"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3067779"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2973473"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.834657"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2019.102376"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2164420"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131275"},{"key":"e_1_3_3_3_34_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR). 1\u201311","author":"Kingma P","year":"2015","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR). 1\u201311."},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2016.7504694"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2669557.2669560"},{"key":"e_1_3_3_3_37_1","unstructured":"S\u00e9bastien Lall\u00e9 Cristina Conati and Giuseppe Carenini. 2016. Predicting Confusion in Information Visualization from Eye Tracking and Interaction Data.. In IJCAI. 2529\u20132535."},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0226-9"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_3_3_40_1","unstructured":"Max Limper Arjan Kuijper and Dieter\u00a0W Fellner. 2016. Mesh Saliency Analysis via Local Curvature Entropy.. In Eurographics (Short Papers). 13\u201316."},{"key":"e_1_3_3_3_41_1","volume-title":"Task-driven visual saliency and attention-based visual question answering. arXiv preprint arXiv:1702.06700","author":"Lin Yuetan","year":"2017","unstructured":"Yuetan Lin, Zhangyang Pang, Donghui Wang, and Yueting Zhuang. 2017. Task-driven visual saliency and attention-based visual question answering. arXiv preprint arXiv:1702.06700 (2017), 1\u20138."},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_3_44_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations. 1\u201311","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations. 1\u201311."},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.04.008"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58628-1_15"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2743939"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2674978"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2004.07.042"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2018.01.010"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.334"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2829750"},{"key":"e_1_3_3_3_56_1","first-page":"396","article-title":"A scanner deeply: Predicting gaze heatmaps on visualizations using crowdsourced eye movement data","volume":"29","author":"Shin Sungbok","year":"2022","unstructured":"Sungbok Shin, Sunghyo Chung, Sanghyun Hong, and Niklas Elmqvist. 2022. A scanner deeply: Predicting gaze heatmaps on visualizations using crowdsourced eye movement data. IEEE Transactions on Visualization and Computer Graphics (TVCG) 29, 1 (2022), 396\u2013406.","journal-title":"IEEE Transactions on Visualization and Computer Graphics (TVCG)"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581067"},{"key":"e_1_3_3_3_58_1","volume-title":"GraphDecoder: Recovering Diverse Network Graphs from Visualization Images via Attention-Aware Learning","author":"Song Sicheng","year":"2022","unstructured":"Sicheng Song, Chenhui Li, Dong Li, Juntong Chen, and Changbo Wang. 2022. GraphDecoder: Recovering Diverse Network Graphs from Visualization Images via Attention-Aware Learning. IEEE Transactions on Visualization and Computer Graphics Early Access (2022), 1\u201317."},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00265"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.conll-1.3"},{"key":"e_1_3_3_3_61_1","volume-title":"Proc. the 45th Annual Meeting of the Cognitive Science Society (CogSci). 3639\u20133646","author":"Sood Ekta","year":"2023","unstructured":"Ekta Sood, Lei Shi, Matteo Bortoletto, Yao Wang, Philipp M\u00fcller, and Andreas Bulling. 2023. Improving Neural Saliency Prediction with a Cognitive Model of Human Visual Attention. In Proc. the 45th Annual Meeting of the Cognitive Science Society (CogSci). 3639\u20133646."},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"e_1_3_3_3_63_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023), 1\u201316."},{"key":"e_1_3_3_3_64_1","volume-title":"Estimating the sample mean and standard deviation from the sample size, median, range and\/or interquartile range. BMC medical research methodology 14","author":"Wan Xiang","year":"2014","unstructured":"Xiang Wan, Wenqian Wang, Jiming Liu, and Tiejun Tong. 2014. Estimating the sample mean and standard deviation from the sample size, median, range and\/or interquartile range. BMC medical research methodology 14 (2014), 1\u201313."},{"key":"e_1_3_3_3_65_1","volume-title":"Scanpath Prediction on Information Visualisations","author":"Wang Yao","year":"2023","unstructured":"Yao Wang, Mihai B\u00e2ce, and Andreas Bulling. 2023. Scanpath Prediction on Information Visualisations. IEEE Transactions on Visualization and Computer Graphics (TVCG) Early Access (2023), 1\u201315."},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3198163"},{"key":"e_1_3_3_3_67_1","volume-title":"Workshop, Teven\u00a0Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra\u00a0Sasha Luccioni","year":"2022","unstructured":"BigScience Workshop, Teven\u00a0Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra\u00a0Sasha Luccioni, Fran\u00e7ois Yvon, 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022), 1\u201373."},{"key":"e_1_3_3_3_68_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Vol.\u00a01. ACL, 2324\u20132335","author":"Xu Hu","year":"2019","unstructured":"Hu Xu, Bing Liu, Lei Shu, and Philip Yu. 2019. BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Vol.\u00a01. ACL, 2324\u20132335."},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858479"},{"key":"e_1_3_3_3_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00027"},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_18"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642942","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:02Z","timestamp":1750291022000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":71,"alternative-id":["10.1145\/3613904.3642942","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642942","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}