{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:47:18Z","timestamp":1780588038911,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":51,"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":"National Key Research and Development Program of China","award":["2020AAA0107400"],"award-info":[{"award-number":["2020AAA0107400"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China under Grant","award":["LR19F020004"],"award-info":[{"award-number":["LR19F020004"]}]},{"name":"National Natural Science Foundation of China under Grant","award":["U20A20222"],"award-info":[{"award-number":["U20A20222"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547821","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"1593-1602","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation."],"prefix":"10.1145","author":[{"given":"Xintian","family":"Wu","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangli","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[{"name":"Youtu Lab, Tencent, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_2_2_1","volume-title":"Collapse Resistant Deep Convolutional GAN for Multi-Object Image Generation. In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE, 1404--1408","author":"Bolluyt Elijah","year":"2019","unstructured":"Elijah Bolluyt and Cristina Comaniciu . 2019 . Collapse Resistant Deep Convolutional GAN for Multi-Object Image Generation. In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE, 1404--1408 . Elijah Bolluyt and Cristina Comaniciu. 2019. Collapse Resistant Deep Convolutional GAN for Multi-Object Image Generation. In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE, 1404--1408."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958864"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"e_1_3_2_2_7_1","volume-title":"Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems 34","author":"Ding Ming","year":"2021","unstructured":"Ming Ding , Zhuoyi Yang , Wenyi Hong , Wendi Zheng , Chang Zhou , Da Yin , Junyang Lin , Xu Zou , Zhou Shao , Hongxia Yang , 2021 . Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems 34 (2021). Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, et al. 2021. Cogview: Mastering text-to-image generation via transformers. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"TISE: A Toolbox for Textto- Image Synthesis Evaluation. arXiv preprint arXiv:2112.01398","author":"Dinh Tan M","year":"2021","unstructured":"Tan M Dinh , Rang Nguyen , and Binh-Son Hua . 2021 . TISE: A Toolbox for Textto- Image Synthesis Evaluation. arXiv preprint arXiv:2112.01398 (2021). Tan M Dinh, Rang Nguyen, and Binh-Son Hua. 2021. TISE: A Toolbox for Textto- Image Synthesis Evaluation. arXiv preprint arXiv:2112.01398 (2021)."},{"key":"e_1_3_2_2_9_1","volume-title":"Gilt: Generating images from long text. arXiv preprint arXiv:1901.02404","author":"El Ori Bar","year":"2019","unstructured":"Ori Bar El , Ori Licht , and Netanel Yosephian . 2019 . Gilt: Generating images from long text. arXiv preprint arXiv:1901.02404 (2019). Ori Bar El, Ori Licht, and Netanel Yosephian. 2019. Gilt: Generating images from long text. arXiv preprint arXiv:1901.02404 (2019)."},{"key":"e_1_3_2_2_10_1","volume-title":"Modality Disentangled Discriminator for Text-to-Image Synthesis","author":"Feng Fangxiang","year":"2021","unstructured":"Fangxiang Feng , Tianrui Niu , Ruifan Li , and Xiaojie Wang . 2021. Modality Disentangled Discriminator for Text-to-Image Synthesis . IEEE Transactions on Multimedia ( 2021 ). Fangxiang Feng, Tianrui Niu, Ruifan Li, and Xiaojie Wang. 2021. Modality Disentangled Discriminator for Text-to-Image Synthesis. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the Second Workshop on Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN). 17--22","author":"Frolov Stanislav","year":"2020","unstructured":"Stanislav Frolov , Shailza Jolly , J\u00f6rn Hees , and Andreas Dengel . 2020 . Leveraging visual question answering to improve text-to-image synthesis . In Proceedings of the Second Workshop on Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN). 17--22 . Stanislav Frolov, Shailza Jolly, J\u00f6rn Hees, and Andreas Dengel. 2020. Leveraging visual question answering to improve text-to-image synthesis. In Proceedings of the Second Workshop on Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN). 17--22."},{"key":"e_1_3_2_2_12_1","volume-title":"SegAttnGAN: Text to image generation with segmentation attention. arXiv preprint arXiv:2005.12444","author":"Gou Yuchuan","year":"2020","unstructured":"Yuchuan Gou , Qiancheng Wu , Minghao Li , Bo Gong , and Mei Han . 2020. SegAttnGAN: Text to image generation with segmentation attention. arXiv preprint arXiv:2005.12444 ( 2020 ). Yuchuan Gou, Qiancheng Wu, Minghao Li, Bo Gong, and Mei Han. 2020. SegAttnGAN: Text to image generation with segmentation attention. arXiv preprint arXiv:2005.12444 (2020)."},{"key":"e_1_3_2_2_13_1","volume-title":"VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks. arXiv preprint arXiv:2010.03182","author":"Han Soyeon Caren","year":"2020","unstructured":"Soyeon Caren Han , Siqu Long , Siwen Luo , Kunze Wang , and Josiah Poon . 2020 . VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks. arXiv preprint arXiv:2010.03182 (2020). Soyeon Caren Han, Siqu Long, Siwen Luo, Kunze Wang, and Josiah Poon. 2020. VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks. arXiv preprint arXiv:2010.03182 (2020)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_15_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel , Hubert Ramsauer , Thomas Unterthiner , Bernhard Nessler , and Sepp Hochreiter . 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 ( 2017 ). Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_16_1","volume-title":"Semantic object accuracy for generative text-to-image synthesis. arXiv preprint arXiv:1910.13321","author":"Hinz Tobias","year":"2019","unstructured":"Tobias Hinz , Stefan Heinrich , and Stefan Wermter . 2019. Semantic object accuracy for generative text-to-image synthesis. arXiv preprint arXiv:1910.13321 ( 2019 ). Tobias Hinz, Stefan Heinrich, and Stefan Wermter. 2019. Semantic object accuracy for generative text-to-image synthesis. arXiv preprint arXiv:1910.13321 (2019)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"e_1_3_2_2_18_1","volume-title":"Conditional GANs with Auxiliary Discriminative Classifier. arXiv preprint arXiv:2107.10060","author":"Hou Liang","year":"2021","unstructured":"Liang Hou , Qi Cao , Huawei Shen , and Xueqi Cheng . 2021. Conditional GANs with Auxiliary Discriminative Classifier. arXiv preprint arXiv:2107.10060 ( 2021 ). Liang Hou, Qi Cao, Huawei Shen, and Xueqi Cheng. 2021. Conditional GANs with Auxiliary Discriminative Classifier. arXiv preprint arXiv:2107.10060 (2021)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3017881"},{"key":"e_1_3_2_2_20_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_21_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"e_1_3_2_2_23_1","unstructured":"Bowen Li Philip Torr and Thomas Lukasiewicz. 2021. Memory-Driven Text-to-Image Generation. (2021).  Bowen Li Philip Torr and Thomas Lukasiewicz. 2021. Memory-Driven Text-to-Image Generation. (2021)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_29"},{"key":"e_1_3_2_2_26_1","volume-title":"Geometric gan. arXiv preprint arXiv:1705.02894","author":"Lim Jae Hyun","year":"2017","unstructured":"Jae Hyun Lim and Jong Chul Ye. 2017. Geometric gan. arXiv preprint arXiv:1705.02894 ( 2017 ). Jae Hyun Lim and Jong Chul Ye. 2017. Geometric gan. arXiv preprint arXiv:1705.02894 (2017)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_28_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero . 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 ( 2014 ). Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_2_29_1","unstructured":"NVIDIA. 2021. Gaugan2. http:\/\/gaugan.org\/gaugan2\/  NVIDIA. 2021. Gaugan2. http:\/\/gaugan.org\/gaugan2\/"},{"key":"e_1_3_2_2_30_1","volume-title":"Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis","author":"Peng Jun","year":"2021","unstructured":"Jun Peng , Yiyi Zhou , Xiaoshuai Sun , Liujuan Cao , Yongjian Wu , Feiyue Huang , and Rongrong Ji. 2021. Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis . IEEE Transactions on Multimedia ( 2021 ). Jun Peng, Yiyi Zhou, Xiaoshuai Sun, Liujuan Cao, Yongjian Wu, Feiyue Huang, and Rongrong Ji. 2021. Knowledge-Driven Generative Adversarial Network for Text-to-Image Synthesis. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Machine Learning. PMLR, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh , Mikhail Pavlov , Gabriel Goh , Scott Gray , Chelsea Voss , Alec Radford , Mark Chen , and Ilya Sutskever . 2021 . Zero-shot text-to-image generation . In International Conference on Machine Learning. PMLR, 8821--8831 . https:\/\/openai.com\/blog\/dall-e\/ Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning. PMLR, 8821--8831. https:\/\/openai.com\/blog\/dall-e\/"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01370"},{"key":"e_1_3_2_2_34_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems 29","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans , Ian Goodfellow , Wojciech Zaremba , Vicki Cheung , Alec Radford , and Xi Chen . 2016. Improved techniques for training gans. Advances in neural information processing systems 29 ( 2016 ). Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.327"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00669"},{"key":"e_1_3_2_2_37_1","volume-title":"Samira Ebrahimi Kahou, and Yoshua Bengio","author":"Sharma Shikhar","year":"2018","unstructured":"Shikhar Sharma , Dendi Suhubdy , Vincent Michalski , Samira Ebrahimi Kahou, and Yoshua Bengio . 2018 . Chatpainter : Improving text to image generation using dialogue. arXiv preprint arXiv:1802.08216 (2018). Shikhar Sharma, Dendi Suhubdy, Vincent Michalski, Samira Ebrahimi Kahou, and Yoshua Bengio. 2018. Chatpainter: Improving text to image generation using dialogue. arXiv preprint arXiv:1802.08216 (2018)."},{"key":"e_1_3_2_2_38_1","volume-title":"International conference on machine learning workshop","volume":"79","author":"Srivastava Nitish","year":"2012","unstructured":"Nitish Srivastava and Ruslan Salakhutdinov . 2012 . Learning representations for multimodal data with deep belief nets . In International conference on machine learning workshop , Vol. 79 . 978--1. Nitish Srivastava and Ruslan Salakhutdinov. 2012. Learning representations for multimodal data with deep belief nets. In International conference on machine learning workshop, Vol. 79. 978--1."},{"key":"e_1_3_2_2_39_1","unstructured":"Sainbayar Sukhbaatar Jason Weston Rob Fergus etal 2015. End-to-end memory networks. Advances in neural information processing systems 28 (2015).  Sainbayar Sukhbaatar Jason Weston Rob Fergus et al. 2015. End-to-end memory networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia. 2290--2298","author":"Sun Jianxin","year":"2021","unstructured":"Jianxin Sun , Qi Li , Weining Wang , Jian Zhao , and Zhenan Sun . 2021 . Multicaption Text-to-Face Synthesis: Dataset and Algorithm . In Proceedings of the 29th ACM International Conference on Multimedia. 2290--2298 . Jianxin Sun, Qi Li, Weining Wang, Jian Zhao, and Zhenan Sun. 2021. Multicaption Text-to-Face Synthesis: Dataset and Algorithm. In Proceedings of the 29th ACM International Conference on Multimedia. 2290--2298."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 10501--10510","author":"Tan Hongchen","year":"2019","unstructured":"Hongchen Tan , Xiuping Liu , Xin Li , Yi Zhang , and Baocai Yin . 2019 . Semanticsenhanced adversarial nets for text-to-image synthesis . In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 10501--10510 . Hongchen Tan, Xiuping Liu, Xin Li, Yi Zhang, and Baocai Yin. 2019. Semanticsenhanced adversarial nets for text-to-image synthesis. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 10501--10510."},{"key":"e_1_3_2_2_43_1","volume-title":"Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis. arXiv preprint arXiv:2008.05865","author":"Tao Ming","year":"2020","unstructured":"Ming Tao , Hao Tang , Songsong Wu , Nicu Sebe , Xiao-Yuan Jing , Fei Wu , and Bingkun Bao . 2020 . Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis. arXiv preprint arXiv:2008.05865 (2020). Ming Tao, Hao Tang, Songsong Wu, Nicu Sebe, Xiao-Yuan Jing, Fei Wu, and Bingkun Bao. 2020. Df-gan: Deep fusion generative adversarial networks for text-to-image synthesis. arXiv preprint arXiv:2008.05865 (2020)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475226"},{"key":"e_1_3_2_2_45_1","unstructured":"Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010).  Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010)."},{"key":"e_1_3_2_2_46_1","volume-title":"Visual synthesis pre-training for neural visual world creation. arXiv preprint arXiv:2111.12417","author":"Wu Chenfei","year":"2021","unstructured":"Chenfei Wu , Jian Liang , Lei Ji , Fan Yang , Yuejian Fang , Daxin Jiang , and Nan Duan . 2021. N\\\" uwa : Visual synthesis pre-training for neural visual world creation. arXiv preprint arXiv:2111.12417 ( 2021 ). Chenfei Wu, Jian Liang, Lei Ji, Fan Yang, Yuejian Fang, Daxin Jiang, and Nan Duan. 2021. N\\\" uwa: Visual synthesis pre-training for neural visual world creation. arXiv preprint arXiv:2111.12417 (2021)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112059"},{"key":"e_1_3_2_2_48_1","volume-title":"MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification. ACM.","author":"Wu Yiming","year":"2021","unstructured":"Yiming Wu , Xintian Wu , Jian Tian , and Xi Li . 2021 . MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification. ACM. Yiming Wu, Xintian Wu, Jian Tian, and Xi Li. 2021. MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification. ACM."},{"key":"e_1_3_2_2_49_1","volume-title":"GAN inversion: A survey. arXiv preprint arXiv:2101.05278","author":"Xia Weihao","year":"2021","unstructured":"Weihao Xia , Yulun Zhang , Yujiu Yang , Jing-Hao Xue , Bolei Zhou , and Ming-Hsuan Yang . 2021. GAN inversion: A survey. arXiv preprint arXiv:2101.05278 ( 2021 ). Weihao Xia, Yulun Zhang, Yujiu Yang, Jing-Hao Xue, Bolei Zhou, and Ming-Hsuan Yang. 2021. GAN inversion: A survey. arXiv preprint arXiv:2101.05278 (2021)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"e_1_3_2_2_51_1","volume-title":"Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853","author":"Xu Bing","year":"2015","unstructured":"Bing Xu , Naiyan Wang , Tianqi Chen , and Mu Li. 2015. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 ( 2015 ). Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. 2015. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)."}],"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\/3503161.3547821","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:35Z","timestamp":1750186955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":51,"alternative-id":["10.1145\/3503161.3547821","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547821","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"}}]}}