{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T22:57:02Z","timestamp":1773442622073,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hong Kong General Research Fund","award":["16200120"],"award-info":[{"award-number":["16200120"]}]},{"name":"Innovation and Technology Fund for Better Living","award":["ITB\/FBL\/B051\/20\/P"],"award-info":[{"award-number":["ITB\/FBL\/B051\/20\/P"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548424","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"5751-5760","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["A Tree-Based Structure-Aware Transformer Decoder for Image-To-Markup Generation"],"prefix":"10.1145","author":[{"given":"Shuhan","family":"Zhong","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sizhe","family":"Song","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanyao","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology & Guangzhou Urban Planning and Design Survey Research Institute, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.-H. Gary","family":"Chan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.09.013"},{"key":"e_1_3_2_2_2_1","volume-title":"Symposium on Interactive Systems for Experimental Applied Mathematics: Proceedings of the Association for Computing Machinery Inc. Symposium (Washington, D.C.)","author":"Anderson Robert H.","unstructured":"Robert H. Anderson . 1967. Syntax-Directed Recognition of Hand-Printed Two-Dimensional Mathematics . In Symposium on Interactive Systems for Experimental Applied Mathematics: Proceedings of the Association for Computing Machinery Inc. Symposium (Washington, D.C.) . Association for Computing Machinery , New York, NY, USA , 436--459. Robert H. Anderson. 1967. Syntax-Directed Recognition of Hand-Printed Two-Dimensional Mathematics. In Symposium on Interactive Systems for Experimental Applied Mathematics: Proceedings of the Association for Computing Machinery Inc. Symposium (Washington, D.C.). Association for Computing Machinery, New York, NY, USA, 436--459."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1984.4767483"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3220134.3220135"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180240"},{"key":"e_1_3_2_2_7_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Chen Xinyun","year":"2018","unstructured":"Xinyun Chen , Chang Liu , and Dawn Song . 2018 a. Tree-to-tree Neural Networks for Program Translation . In Advances in Neural Information Processing Systems , Vol. 31 . Curran Associates, Inc., Montr\u00e9al,Canada. Xinyun Chen, Chang Liu, and Dawn Song. 2018a. Tree-to-tree Neural Networks for Program Translation. In Advances in Neural Information Processing Systems, Vol. 31. Curran Associates, Inc., Montr\u00e9al,Canada."},{"key":"e_1_3_2_2_8_1","volume-title":"Transition based Graph Decoder for Neural Machine Translation. CoRR","author":"Choshen Leshem","year":"2021","unstructured":"Leshem Choshen and Omri Abend . 2021. Transition based Graph Decoder for Neural Machine Translation. CoRR , Vol. abs\/ 2101 .12640 ( 2021 ). showeprint[arXiv]2101.12640 Leshem Choshen and Omri Abend. 2021. Transition based Graph Decoder for Neural Machine Translation. CoRR, Vol. abs\/2101.12640 (2021). showeprint[arXiv]2101.12640"},{"key":"e_1_3_2_2_9_1","volume-title":"Image-to-Markup Generation with Coarse-to-Fine Attention. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"989","author":"Deng Yuntian","unstructured":"Yuntian Deng , Anssi Kanervisto , Jeffrey Ling , and Alexander M. Rush . 2017 . Image-to-Markup Generation with Coarse-to-Fine Attention. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 70). PMLR, Sydney, Australia, 980-- 989 . Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, and Alexander M. Rush. 2017. Image-to-Markup Generation with Coarse-to-Fine Attention. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 70). PMLR, Sydney, Australia, 980--989."},{"key":"e_1_3_2_2_10_1","volume-title":"Global Relational Models of Source Code. In International Conference on Learning Representations. OpenReview.net, Addis Ababa, Ethiopia.","author":"Hellendoorn Vincent J.","year":"2020","unstructured":"Vincent J. Hellendoorn , Charles Sutton , Rishabh Singh , Petros Maniatis , and David Bieber . 2020 . Global Relational Models of Source Code. In International Conference on Learning Representations. OpenReview.net, Addis Ababa, Ethiopia. Vincent J. Hellendoorn, Charles Sutton, Rishabh Singh, Petros Maniatis, and David Bieber. 2020. Global Relational Models of Source Code. In International Conference on Learning Representations. OpenReview.net, Addis Ababa, Ethiopia."},{"key":"e_1_3_2_2_11_1","volume-title":"Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society","author":"Huang G.","unstructured":"G. Huang , Z. Liu , L. Van Der Maaten, and K. Q. Weinberger. 2017 . Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society , Los Alamitos, CA, USA, 2261--2269. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger. 2017. Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, USA, 2261--2269."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00349-6"},{"key":"e_1_3_2_2_13_1","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society","author":"Karpathy A.","unstructured":"A. Karpathy and L. Fei-Fei . 2015. Deep visual-semantic alignments for generating image descriptions . In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society , Los Alamitos, CA, USA, 3128--3137. A. Karpathy and L. Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, USA, 3128--3137."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1954","author":"Kusner Matt J.","year":"2017","unstructured":"Matt J. Kusner , Brooks Paige , and Jos\u00e9 Miguel Hern\u00e1 ndez- Lobato . 2017 . Grammar Variational Autoencoder . In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 70). PMLR, Sydney, NSW, Australia, 1945-- 1954 . Matt J. Kusner, Brooks Paige, and Jos\u00e9 Miguel Hern\u00e1 ndez-Lobato. 2017. Grammar Variational Autoencoder. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 70). PMLR, Sydney, NSW, Australia, 1945--1954."},{"key":"e_1_3_2_2_15_1","unstructured":"Leslie Lamport. 1985. LaTeX - A document preparation system. https:\/\/www.latex-project.org\/  Leslie Lamport. 1985. LaTeX - A document preparation system. https:\/\/www.latex-project.org\/"},{"key":"e_1_3_2_2_16_1","unstructured":"Greg Landrum et al. 2013. RDKit: A software suite for cheminformatics computational chemistry and predictive modeling.  Greg Landrum et al. 2013. RDKit: A software suite for cheminformatics computational chemistry and predictive modeling."},{"key":"e_1_3_2_2_17_1","volume-title":"Optical Formula Recognition. In 2013 12th International Conference on Document Analysis and Recognition. IEEE Computer Society","author":"Lavirotte S.","year":"1997","unstructured":"S. Lavirotte . 1997 . Optical Formula Recognition. In 2013 12th International Conference on Document Analysis and Recognition. IEEE Computer Society , Los Alamitos, CA, USA, 357. S. Lavirotte. 1997. Optical Formula Recognition. In 2013 12th International Conference on Document Analysis and Recognition. IEEE Computer Society, Los Alamitos, CA, USA, 357."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475578"},{"key":"e_1_3_2_2_19_1","volume-title":"LocalViT: Bringing Locality to Vision Transformers. CoRR","author":"Li Yawei","year":"2021","unstructured":"Yawei Li , Kai Zhang , Jiezhang Cao , Radu Timofte , and Luc Van Gool . 2021a. LocalViT: Bringing Locality to Vision Transformers. CoRR , Vol. abs\/ 2104 .05707 ( 2021 ). showeprint[arXiv]2104.05707 Yawei Li, Kai Zhang, Jiezhang Cao, Radu Timofte, and Luc Van Gool. 2021a. LocalViT: Bringing Locality to Vision Transformers. CoRR, Vol. abs\/2104.05707 (2021). showeprint[arXiv]2104.05707"},{"key":"e_1_3_2_2_20_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations. OpenReview.net","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter . 2017 . SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations. OpenReview.net , Toulon, France. Ilya Loshchilov and Frank Hutter. 2017. SGDR: Stochastic Gradient Descent with Warm Restarts. In 5th International Conference on Learning Representations. OpenReview.net, Toulon, France."},{"key":"e_1_3_2_2_21_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations. OpenReview.net","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter . 2019 . Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations. OpenReview.net , New Orleans, LA, USA. Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations. OpenReview.net, New Orleans, LA, USA."},{"key":"e_1_3_2_2_22_1","volume-title":"Image-to-Tree: A Tree-Structured Decoder for Image Captioning. In 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE Computer Society","author":"Ma Z.","unstructured":"Z. Ma , C. Yuan , Y. Cheng , and X. Zhu . 2019 . Image-to-Tree: A Tree-Structured Decoder for Image Captioning. In 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE Computer Society , Los Alamitos, CA, USA, 1294--1299. Z. Ma, C. Yuan, Y. Cheng, and X. Zhu. 2019. Image-to-Tree: A Tree-Structured Decoder for Image Captioning. In 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE Computer Society, Los Alamitos, CA, USA, 1294--1299."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-012-0184-x"},{"key":"e_1_3_2_2_24_1","volume-title":"ICDAR 2019 CROHME TFD: Competition on Recognition of Handwritten Mathematical Expressions and Typeset Formula Detection. In 2019 International Conference on Document Analysis and Recognition (ICDAR)","author":"Mahdavi Mahshad","unstructured":"Mahshad Mahdavi , Richard Zanibbi , Harold Mouchere , Christian Viard-Gaudin , and Utpal Garain . 2019. ICDAR 2019 CROHME TFD: Competition on Recognition of Handwritten Mathematical Expressions and Typeset Formula Detection. In 2019 International Conference on Document Analysis and Recognition (ICDAR) . IEEE Computer Society , Los Alamitos, CA, USA , 1533--1538. Mahshad Mahdavi, Richard Zanibbi, Harold Mouchere, Christian Viard-Gaudin, and Utpal Garain. 2019. ICDAR 2019 CROHME TFD: Competition on Recognition of Handwritten Mathematical Expressions and Typeset Formula Detection. In 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE Computer Society, Los Alamitos, CA, USA, 1533--1538."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"H. Mouchere C. Viard-Gaudin R. Zanibbi and U. Garain. 2014. ICFHR 2014 Competition on Recognition of On-Line Handwritten Mathematical Expressions (CROHME 2014). In 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE Computer Society Los Alamitos CA USA 791--796.  H. Mouchere C. Viard-Gaudin R. Zanibbi and U. Garain. 2014. ICFHR 2014 Competition on Recognition of On-Line Handwritten Mathematical Expressions (CROHME 2014). In 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE Computer Society Los Alamitos CA USA 791--796.","DOI":"10.1109\/ICFHR.2014.138"},{"key":"e_1_3_2_2_26_1","volume-title":"CROHME: Competition on Recognition of Online Handwritten Mathematical Expressions. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR)","author":"Mouchere H.","year":"2016","unstructured":"H. Mouchere , C. Viard-Gaudin , R. Zanibbi , and U. Garain . 2016 . ICFHR 2016 CROHME: Competition on Recognition of Online Handwritten Mathematical Expressions. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) . IEEE Computer Society , Los Alamitos, CA, USA , 607--612. H. Mouchere, C. Viard-Gaudin, R. Zanibbi, and U. Garain. 2016. ICFHR2016 CROHME: Competition on Recognition of Online Handwritten Mathematical Expressions. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE Computer Society, Los Alamitos, CA, USA, 607--612."},{"key":"e_1_3_2_2_27_1","volume-title":"Tree-Structured Attention with Hierarchical Accumulation. In International Conference on Learning Representations. OpenReview.net, Addis Ababa, Ethiopia.","author":"Nguyen Xuan-Phi","year":"2020","unstructured":"Xuan-Phi Nguyen , Shafiq Joty , Steven Hoi , and Richard Socher . 2020 . Tree-Structured Attention with Hierarchical Accumulation. In International Conference on Learning Representations. OpenReview.net, Addis Ababa, Ethiopia. Xuan-Phi Nguyen, Shafiq Joty, Steven Hoi, and Richard Socher. 2020. Tree-Structured Attention with Hierarchical Accumulation. In International Conference on Learning Representations. OpenReview.net, Addis Ababa, Ethiopia."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00465-0"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics","author":"Liu Peter J.","unstructured":"Abigail See, Peter J. Liu , and Christopher D. Manning . 2017. Get To The Point: Summarization with Pointer-Generator Networks . In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics , Vancouver, Canada, 1073--1083. Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get To The Point: Summarization with Pointer-Generator Networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada, 1073--1083."},{"key":"e_1_3_2_2_30_1","volume-title":"International Conference on Learning Representations. OpenReview.net","author":"Shen Yikang","year":"2019","unstructured":"Yikang Shen , Shawn Tan , Alessandro Sordoni , and Aaron Courville . 2019 . Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks . In International Conference on Learning Representations. OpenReview.net , New Orleans, LA, USA. Yikang Shen, Shawn Tan, Alessandro Sordoni, and Aaron Courville. 2019. Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks. In International Conference on Learning Representations. OpenReview.net, New Orleans, LA, USA."},{"key":"e_1_3_2_2_31_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Shiv Vighnesh","year":"2019","unstructured":"Vighnesh Shiv and Chris Quirk . 2019 . Novel positional encodings to enable tree-based transformers . In Advances in Neural Information Processing Systems , Vol. 32 . Curran Associates, Inc., Vancouver, Canada. Vighnesh Shiv and Chris Quirk. 2019. Novel positional encodings to enable tree-based transformers. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc., Vancouver, Canada."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6430"},{"key":"e_1_3_2_2_33_1","volume-title":"Manning","author":"Tai Kai Sheng","year":"2015","unstructured":"Kai Sheng Tai , Richard Socher , and Christopher D . Manning . 2015 . Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Beijing, China, 1556--1566. Kai Sheng Tai, Richard Socher, and Christopher D. Manning. 2015. Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Beijing, China, 1556--1566."},{"key":"e_1_3_2_2_34_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , \u0141ukasz Kaiser , and Illia Polosukhin . 2017 . Attention is All you Need . In Advances in Neural Information Processing Systems , Vol. 30 . Curran Associates, Inc., Long Beach, CA, USA, 5998--6008. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc., Long Beach, CA, USA, 5998--6008."},{"key":"e_1_3_2_2_35_1","volume-title":"Graph Attention Networks. In International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic , Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Li\u00f2 , and Yoshua Bengio . 2018 . Graph Attention Networks. In International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net , Vancouver, BC, Canada. Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, Vancouver, BC, Canada."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1509"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Yaushian Wang Hung-Yi Lee and Yun-Nung Chen. 2019. Tree Transformer: Integrating Tree Structures into Self-Attention. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics Hong Kong China 1061--1070.  Yaushian Wang Hung-Yi Lee and Yun-Nung Chen. 2019. Tree Transformer: Integrating Tree Structures into Self-Attention. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics Hong Kong China 1061--1070.","DOI":"10.18653\/v1\/D19-1098"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"e_1_3_2_2_39_1","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Wu Jin-Wen","unstructured":"Jin-Wen Wu , Fei Yin , Yan-Ming Zhang , Xu-Yao Zhang , and Cheng-Lin Liu . 2019. Image-to-Markup Generation via Paired Adversarial Learning . In Machine Learning and Knowledge Discovery in Databases . Springer International Publishing , Cham , 18--34. Jin-Wen Wu, Fei Yin, Yan-Ming Zhang, Xu-Yao Zhang, and Cheng-Lin Liu. 2019. Image-to-Markup Generation via Paired Adversarial Learning. In Machine Learning and Knowledge Discovery in Databases. Springer International Publishing, Cham, 18--34."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01291-5"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17662"},{"key":"e_1_3_2_2_42_1","volume-title":"Attend and Tell: Neural Image Caption Generation with Visual Attention. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"2057","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu , Jimmy Ba , Ryan Kiros , Kyunghyun Cho , Aaron Courville , Ruslan Salakhudinov , Rich Zemel , and Yoshua Bengio . 2015 . Show , Attend and Tell: Neural Image Caption Generation with Visual Attention. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 37). PMLR, Lille, France, 2048-- 2057 . Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37). PMLR, Lille, France, 2048--2057."},{"key":"e_1_3_2_2_43_1","volume-title":"TACC: A Full-stack Cloud Computing Infrastructure for Machine Learning Tasks.","author":"Xu Kaiqiang","year":"2021","unstructured":"Kaiqiang Xu , Xinchen Wan , Hao Wang , Zhenghang Ren , Xudong Liao , Decang Sun , Chaoliang Zeng , and Kai Chen . 2021 . TACC: A Full-stack Cloud Computing Infrastructure for Machine Learning Tasks. Kaiqiang Xu, Xinchen Wan, Hao Wang, Zhenghang Ren, Xudong Liao, Decang Sun, Chaoliang Zeng, and Kai Chen. 2021. TACC: A Full-stack Cloud Computing Infrastructure for Machine Learning Tasks."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.432"},{"key":"e_1_3_2_2_45_1","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics","author":"Yin Pengcheng","year":"2018","unstructured":"Pengcheng Yin and Graham Neubig . 2018 . TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation . In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics , Brussels, Belgium, 7--12. Pengcheng Yin and Graham Neubig. 2018. TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Brussels, Belgium, 7--12."},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"11085","author":"Zhang Jianshu","year":"2020","unstructured":"Jianshu Zhang , Jun Du , Yongxin Yang , Yi-Zhe Song , Si Wei , and Lirong Dai . 2020 . A Tree-Structured Decoder for Image-to-Markup Generation . In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 119). PMLR, Virtual Event, 11076-- 11085 . Jianshu Zhang, Jun Du, Yongxin Yang, Yi-Zhe Song, Si Wei, and Lirong Dai. 2020. A Tree-Structured Decoder for Image-to-Markup Generation. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119). PMLR, Virtual Event, 11076--11085."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"e_1_3_2_2_48_1","volume-title":"International Conference on Learning Representations. OpenReview.net, Austria.","author":"Z\u00fcgner Daniel","year":"2021","unstructured":"Daniel Z\u00fcgner , Tobias Kirschstein , Michele Catasta , Jure Leskovec , and Stephan G\u00fcnnemann . 2021 . Language-Agnostic Representation Learning of Source Code from Structure and Context . In International Conference on Learning Representations. OpenReview.net, Austria. Daniel Z\u00fcgner, Tobias Kirschstein, Michele Catasta, Jure Leskovec, and Stephan G\u00fcnnemann. 2021. Language-Agnostic Representation Learning of Source Code from Structure and Context. In International Conference on Learning Representations. OpenReview.net, Austria."}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548424","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:17Z","timestamp":1750182557000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":48,"alternative-id":["10.1145\/3503161.3548424","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548424","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}