{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:54:43Z","timestamp":1770274483918,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","award":["VRLAB2019C03"],"award-info":[{"award-number":["VRLAB2019C03"]}]},{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772047, 61772513"],"award-info":[{"award-number":["61772047, 61772513"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Open Funds of CETC Big Data Research Institute Co.,Ltd.,","award":["W-2018022"],"award-info":[{"award-number":["W-2018022"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["328201907"],"award-info":[{"award-number":["328201907"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350970","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"311-319","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":45,"title":["Aesthetic Attributes Assessment of Images"],"prefix":"10.1145","author":[{"given":"Xin","family":"Jin","sequence":"first","affiliation":[{"name":"Beijing Electronic Science and Technology Institute & CETC Big Data Research Institute Co.,Ltd., Beijing, China"}]},{"given":"Le","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology Institute, Beijing, China"}]},{"given":"Geng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology Institute, Beijing, China"}]},{"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology Institute, Beijing, China"}]},{"given":"Xiaokun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology Institute, Beijing, China"}]},{"given":"Shiming","family":"Ge","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}]},{"given":"Dongqing","family":"Zou","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}]},{"given":"Bin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Xinghui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing Electronic Science and Technology Institute, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings, Part V (Lecture Notes in Computer Science), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.)","volume":"9909","author":"Anderson Peter","year":"2016","unstructured":"Peter Anderson , Basura Fernando , Mark Johnson , and Stephen Gould . 2016 . SPICE: Semantic Propositional Image Caption Evaluation. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016 , Proceedings, Part V (Lecture Notes in Computer Science), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.) , Vol. 9909 . Springer, 382--398. https:\/\/doi.org\/10.1007\/978--3--319--46454--1_24 10.1007\/978--3--319--46454--1_24 Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. 2016. SPICE: Semantic Propositional Image Caption Evaluation. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part V (Lecture Notes in Computer Science), Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.), Vol. 9909. Springer, 382--398. https:\/\/doi.org\/10.1007\/978--3--319--46454--1_24"},{"key":"e_1_3_2_1_2_1","volume-title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson , Xiaodong He , Chris Buehler , Damien Teney , Mark Johnson , Stephen Gould , and Lei Zhang . 2018 . Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, and Lei Zhang. 2018. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_3_1","volume-title":"Convolutional Image Captioning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Aneja Jyoti","unstructured":"Jyoti Aneja , Aditya Deshpande , and Alexander G. Schwing . 2018 . Convolutional Image Captioning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Jyoti Aneja, Aditya Deshpande, and Alexander G. Schwing. 2018. Convolutional Image Captioning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_4_1","volume-title":"Aesthetic Critiques Generation for Photos. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Chang Kuang-Yu","year":"2017","unstructured":"Kuang-Yu Chang , Kung-Hung Lu , and Chu-Song Chen . 2017 . Aesthetic Critiques Generation for Photos. In IEEE International Conference on Computer Vision, ICCV 2017 , Venice, Italy, October 22--29 , 2017. IEEE Computer Society, 3534--3543. https:\/\/doi.org\/10.1109\/ICCV.2017.380 10.1109\/ICCV.2017.380 Kuang-Yu Chang, Kung-Hung Lu, and Chu-Song Chen. 2017. Aesthetic Critiques Generation for Photos. In IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22--29, 2017. IEEE Computer Society, 3534--3543. https:\/\/doi.org\/10.1109\/ICCV.2017.380"},{"key":"e_1_3_2_1_5_1","volume-title":"GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Chen Fuhai","year":"2018","unstructured":"Fuhai Chen , Rongrong Ji , Xiaoshuai Sun , Yongjian Wu , and Jinsong Su . 2018 . GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Fuhai Chen, Rongrong Ji, Xiaoshuai Sun, Yongjian Wu, and Jinsong Su. 2018. GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_6_1","volume-title":"SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Chen Long","year":"2017","unstructured":"Long Chen , Hanwang Zhang , Jun Xiao , Liqiang Nie , Jian Shao , Wei Liu , and Tat-Seng Chua . 2017 . SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 , Honolulu, HI, USA, July 21--26 , 2017 . 6298--6306. https:\/\/doi.org\/10.1109\/CVPR.2017.667 10.1109\/CVPR.2017.667 Long Chen, Hanwang Zhang, Jun Xiao, Liqiang Nie, Jian Shao, Wei Liu, and Tat-Seng Chua. 2017. SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21--26, 2017 . 6298--6306. https:\/\/doi.org\/10.1109\/CVPR.2017.667"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2369962"},{"key":"#cr-split#-e_1_3_2_1_8_1.1","doi-asserted-by":"crossref","unstructured":"C. Cui H. Liu T. Lian L. Nie L. Zhu and Y. Yin. 2018. Distribution-oriented Aesthetics Assessment with Semantic-Aware Hybrid Network. IEEE Transactions on Multimedia (2018) 1--1. https:\/\/doi.org\/10.1109\/TMM.2018.2875357 10.1109\/TMM.2018.2875357","DOI":"10.1109\/TMM.2018.2875357"},{"key":"#cr-split#-e_1_3_2_1_8_1.2","doi-asserted-by":"crossref","unstructured":"C. Cui H. Liu T. Lian L. Nie L. Zhu and Y. Yin. 2018. Distribution-oriented Aesthetics Assessment with Semantic-Aware Hybrid Network. IEEE Transactions on Multimedia (2018) 1--1. https:\/\/doi.org\/10.1109\/TMM.2018.2875357","DOI":"10.1109\/TMM.2018.2875357"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2696576"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.05.095"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep Residual Learning for Image Recognition","author":"He Kaiming","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016. Deep Residual Learning for Image Recognition . In CVPR. IEEE Computer Society , 770--778. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. IEEE Computer Society, 770--778."},{"key":"e_1_3_2_1_13_1","volume-title":"Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Huang Gao","year":"2017","unstructured":"Gao Huang , Zhuang Liu , Laurens van der Maaten, and Kilian Q. Weinberger. 2017 . Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 , Honolulu, HI, USA, July 21--26 , 2017 . 2261--2269. https:\/\/doi.org\/10.1109\/CVPR.2017.243 10.1109\/CVPR.2017.243 Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21--26, 2017 . 2261--2269. https:\/\/doi.org\/10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_14_1","volume-title":"The 8th International Conference on Wireless Communications and Signal Processing (WCSP). 1--6.","author":"Jin X.","unstructured":"X. Jin , J. Chi , S. Peng , Y. Tian , C. Ye , and X. Li . 2016. Deep Image Aesthetics Classification using Inception Modules and Fine-tuning Connected Layer . In The 8th International Conference on Wireless Communications and Signal Processing (WCSP). 1--6. X. Jin, J. Chi , S. Peng, Y. Tian, C. Ye, and X. Li. 2016. Deep Image Aesthetics Classification using Inception Modules and Fine-tuning Connected Layer. In The 8th International Conference on Wireless Communications and Signal Processing (WCSP). 1--6."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence","author":"Jin Xin","year":"2018","unstructured":"Xin Jin , Le Wu , Xiaodong Li , Siyu Chen , Siwei Peng , Jingying Chi , Shiming Ge , Chenggen Song , and Geng Zhao . 2018 . Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence . In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence , New Orleans, Louisiana, USA, February 2--7 , 2018 . https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16074 Xin Jin, Le Wu, Xiaodong Li, Siyu Chen, Siwei Peng, Jingying Chi, Shiming Ge, Chenggen Song, and Geng Zhao. 2018. Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, February 2--7, 2018 . https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16074"},{"key":"e_1_3_2_1_16_1","volume-title":"11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5--11, 2010, Proceedings, Part IV. 101--114","author":"Jin Xin","year":"2010","unstructured":"Xin Jin , Mingtian Zhao , Xiaowu Chen , Qinping Zhao , and Song Chun Zhu . 2010 . Learning Artistic Lighting Template from Portrait Photographs. In Computer Vision - ECCV 2010 , 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5--11, 2010, Proceedings, Part IV. 101--114 . Xin Jin, Mingtian Zhao, Xiaowu Chen, Qinping Zhao, and Song Chun Zhu. 2010. Learning Artistic Lighting Template from Portrait Photographs. In Computer Vision - ECCV 2010, 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5--11, 2010, Proceedings, Part IV. 101--114."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651399"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2016.05.004"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2598339"},{"key":"e_1_3_2_1_20_1","volume-title":"Photo Aesthetics Ranking Network with Attributes and Content Adaptation. In European Conference on Computer Vision (ECCV) .","author":"Kong Shu","year":"2016","unstructured":"Shu Kong , Xiaohui Shen , Zhe Lin , Radomir Mech , and Charless Fowlkes . 2016 . Photo Aesthetics Ranking Network with Attributes and Content Adaptation. In European Conference on Computer Vision (ECCV) . Shu Kong, Xiaohui Shen, Zhe Lin, Radomir Mech, and Charless Fowlkes. 2016. Photo Aesthetics Ranking Network with Attributes and Content Adaptation. In European Conference on Computer Vision (ECCV) ."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"e_1_3_2_1_22_1","volume-title":"Discriminability Objective for Training Descriptive Captions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Luo Ruotian","year":"2018","unstructured":"Ruotian Luo , Brian Price , Scott Cohen , and Gregory Shakhnarovich . 2018 . Discriminability Objective for Training Descriptive Captions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Ruotian Luo, Brian Price, Scott Cohen, and Gregory Shakhnarovich. 2018. Discriminability Objective for Training Descriptive Captions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_23_1","volume-title":"A-Lamp: Adaptive Layout-Aware Multi-patch Deep Convolutional Neural Network for Photo Aesthetic Assessment","author":"Ma Shuang","unstructured":"Shuang Ma , Jing Liu , and Chang Wen Chen . 2017. A-Lamp: Adaptive Layout-Aware Multi-patch Deep Convolutional Neural Network for Photo Aesthetic Assessment . In CVPR. IEEE Computer Society , 722--731. Shuang Ma, Jing Liu, and Chang Wen Chen. 2017. A-Lamp: Adaptive Layout-Aware Multi-patch Deep Convolutional Neural Network for Photo Aesthetic Assessment. In CVPR. IEEE Computer Society, 722--731."},{"key":"e_1_3_2_1_24_1","volume-title":"Composition-Preserving Deep Photo Aesthetics Assessment. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) .","author":"Mai Long","year":"2016","unstructured":"Long Mai , Hailin Jin , and Feng Liu . 2016 . Composition-Preserving Deep Photo Aesthetics Assessment. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Long Mai, Hailin Jin, and Feng Liu. 2016. Composition-Preserving Deep Photo Aesthetics Assessment. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ."},{"key":"e_1_3_2_1_25_1","volume-title":"Generation and Comprehension of Unambiguous Object Descriptions. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016","author":"Mao Junhua","year":"2016","unstructured":"Junhua Mao , Jonathan Huang , Alexander Toshev , Oana Camburu , Alan L. Yuille , and Kevin Murphy . 2016 . Generation and Comprehension of Unambiguous Object Descriptions. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 , Las Vegas, NV, USA, June 27--30 , 2016. 11--20. https:\/\/doi.org\/10.1109\/CVPR.2016.9 10.1109\/CVPR.2016.9 Junhua Mao, Jonathan Huang, Alexander Toshev, Oana Camburu, Alan L. Yuille, and Kevin Murphy. 2016. Generation and Comprehension of Unambiguous Object Descriptions. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27--30, 2016. 11--20. https:\/\/doi.org\/10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00896"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_30_1","volume-title":"Neural Aesthetic Image Reviewer. CoRR","author":"Wang Wenshan","year":"2018","unstructured":"Wenshan Wang , Su Yang , Weishan Zhang , and Jiulong Zhang . 2018. Neural Aesthetic Image Reviewer. CoRR , Vol. abs\/ 1802 .10240 ( 2018 ). arxiv: 1802.10240 http:\/\/arxiv.org\/abs\/1802.10240 Wenshan Wang, Su Yang, Weishan Zhang, and Jiulong Zhang. 2018. Neural Aesthetic Image Reviewer. CoRR , Vol. abs\/1802.10240 (2018). arxiv: 1802.10240 http:\/\/arxiv.org\/abs\/1802.10240"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2016.05.009"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 2016 ACM Conference on Multimedia Conference, MM 2016","author":"Zhou Ye","year":"2016","unstructured":"Ye Zhou , Xin Lu , Junping Zhang , and James Z. Wang . 2016. Joint Image and Text Representation for Aesthetics Analysis . In Proceedings of the 2016 ACM Conference on Multimedia Conference, MM 2016 , Amsterdam, The Netherlands, October 15--19 , 2016 , Alan Hanjalic, Cees Snoek, Marcel Worring, Dick C. A. Bulterman, Benoit Huet, Aisling Kelliher, Yiannis Kompatsiaris, and Jin Li (Eds.). ACM , 262--266. https:\/\/doi.org\/10.1145\/2964284.2967223 10.1145\/2964284.2967223 Ye Zhou, Xin Lu, Junping Zhang, and James Z. Wang. 2016. Joint Image and Text Representation for Aesthetics Analysis. In Proceedings of the 2016 ACM Conference on Multimedia Conference, MM 2016, Amsterdam, The Netherlands, October 15--19, 2016, Alan Hanjalic, Cees Snoek, Marcel Worring, Dick C. A. Bulterman, Benoit Huet, Aisling Kelliher, Yiannis Kompatsiaris, and Jin Li (Eds.). ACM , 262--266. https:\/\/doi.org\/10.1145\/2964284.2967223"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France","acronym":"MM '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350970","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:18Z","timestamp":1750201998000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":33,"alternative-id":["10.1145\/3343031.3350970","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350970","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}