{"type":"ScholarlyArticle","title":"Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding","authors":[{"name":"Tianrui Hui","slug":"tianrui-hui","given":"Tianrui","family":"Hui","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences; School of Cyber Security , University of Chinese Academy of Sciences"},{"name":"Zihan Ding","slug":"zihan-ding","given":"Zihan","family":"Ding","affiliation":"Institute of Artificial Intelligence , Beihang University"},{"name":"Junshi Huang","slug":"junshi-huang","given":"Junshi","family":"Huang","affiliation":""},{"name":"Xiaoming Wei","slug":"xiaoming-wei","given":"Xiaoming","family":"Wei","affiliation":""},{"name":"Xiaolin Wei","slug":"xiaolin-wei","given":"Xiaolin","family":"Wei","affiliation":""},{"name":"Jiao Dai","slug":"jiao-dai","given":"Jiao","family":"Dai","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences; School of Cyber Security , University of Chinese Academy of Sciences"},{"name":"Jizhong Han","slug":"jizhong-han","given":"Jizhong","family":"Han","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences; School of Cyber Security , University of Chinese Academy of Sciences"},{"name":"Si Liu","slug":"si-liu","given":"Si","family":"Liu","affiliation":"Institute of Artificial Intelligence , Beihang University; Hangzhou Innovation Institute , Beihang University"}],"abstract":"Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a Phrase-Object Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.","doi":"10.24963/ijcai.2023/99","url":"https://ijcai.org/proceedings/2023/99","pdf":"https://ijcai.org/proceedings/2023/0099.pdf","markdown":"https://ijcai.org/proceedings/2023/99.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/99","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":"Computer Vision","track":"Main Track","number":99,"pages":{"first":893,"last":901},"keywords":["Computer Vision: CV: Vision and language","Computer Vision: CV: Segmentation"],"videos":[],"references":[{"position":1,"raw":"[Akbari et al., 2019] Hassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, and Shih- Fu Chang. Multi-level multimodal common semantic space for image-phrase grounding. In CVPR, 2019.","title":"Multi-level multimodal common semantic space for image-phrase grounding","authors":"Hassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, Shih-Fu Chang","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bajaj et al., 2019] Mohit Bajaj, Lanjun Wang, and Leonid Sigal. G3raphground: Graph-based language grounding. In ICCV, 2019.","title":"G3raphground: Graph-based language grounding","authors":"Mohit Bajaj, Lanjun Wang, Leonid Sigal","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cheng et al., 2020] Bowen Cheng, Maxwell D Collins, Yukun Zhu, Ting Liu, Thomas S Huang, Hartwig Adam, and Liang-Chieh Chen. Panoptic-deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmen- tation. In CVPR, 2020.","title":"Panoptic-deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmentation","authors":"Bowen Cheng, Maxwell D Collins, Yukun Zhu, Ting Liu, Thomas S Huang, Hartwig Adam, Liang-Chieh Chen","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng et al., 2021] Bowen Cheng, Alex Schwing, and Alexander Kirillov. Per-pixel classification is not all you need for semantic segmentation. In NeurIPS, 2021.","title":"Per-pixel classification is not all you need for semantic segmentation","authors":"Bowen Cheng, Alex Schwing, Alexander Kirillov","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2022] Bowen Cheng, Ishan Misra, Alexan- der G Schwing, Alexander Kirillov, and Rohit Girdhar. Masked-attention mask transformer for universal image segmentation. In CVPR, 2022.","title":"Masked-attention mask transformer for universal image segmentation","authors":"Bowen Cheng, Ishan Misra, Alexander G Schwing, Alexander Kirillov, Rohit Girdhar","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. In NAACL, 2018.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2018","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ding et al., 2022] Zihan Ding, Zi-han Ding, Tianrui Hui, Junshi Huang, Xiaoming Wei, Xiaolin Wei, and Si Liu. Ppmn: Pixel-phrase matching network for one-stage panoptic narrative grounding. In ACM MM, 2022.","title":"Ppmn: Pixel-phrase matching network for one-stage panoptic narrative grounding","authors":"Zihan Ding, Tianrui Zi-Han Ding, Junshi Hui, Xiaoming Huang, Xiaolin Wei, Si Wei, Liu","year":"2022","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dogan et al., 2019] Pelin Dogan, Leonid Sigal, and Markus Gross. Neural sequential phrase grounding (seqground). In CVPR, 2019.","title":"Neural sequential phrase grounding (seqground)","authors":"Pelin Dogan, Leonid Sigal, Markus Gross","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Feng et al., 2021] Guang Feng, Zhiwei Hu, Lihe Zhang, and Huchuan Lu. Encoder fusion network with co- attention embedding for referring image segmentation. In CVPR, 2021.","title":"Encoder fusion network with coattention embedding for referring image segmentation","authors":"Guang Feng, Zhiwei Hu, Lihe Zhang, Huchuan Lu","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[González et al., 2021] Cristina González, Nicolás Ayobi, Isabela Hernández, José Hernández, Jordi Pont-Tuset, and Pablo Arbeláez. Panoptic narrative grounding. In ICCV, 2021.","title":"Panoptic narrative grounding","authors":"Cristina González, Nicolás Ayobi, Isabela Hernández, José Hernández, Jordi Pont-Tuset, Pablo Arbeláez","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2020] Kaiming He, Haoqi Fan, Yuxin Wu, Sain- ing Xie, and Ross Girshick. Momentum contrast for unsu- pervised visual representation learning. In CVPR, 2020.","title":"Momentum contrast for unsupervised visual representation learning","authors":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Huang et al., 2020] Shaofei Huang, Tianrui Hui, Si Liu, Guanbin Li, Yunchao Wei, Jizhong Han, Luoqi Liu, and Bo Li. Referring image segmentation via cross-modal pro- gressive comprehension. In CVPR, 2020.","title":"Referring image segmentation via cross-modal progressive comprehension","authors":"Huang","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hui et al., 2020] Tianrui Hui, Si Liu, Shaofei Huang, Guan- bin Li, Sansi Yu, Faxi Zhang, and Jizhong Han. Linguistic structure guided context modeling for referring image seg- mentation. In ECCV, 2020.","title":"Linguistic structure guided context modeling for referring image segmentation","authors":"Tianrui Hui, Si Liu, Shaofei Huang, Guanbin Li, Sansi Yu, Faxi Zhang, Jizhong Han","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Jing et al., 2021] Ya Jing, Tao Kong, Wei Wang, Liang Wang, Lei Li, and Tieniu Tan. Locate then segment: A strong pipeline for referring image segmentation. In CVPR, 2021.","title":"Locate then segment: A strong pipeline for referring image segmentation","authors":"Ya Jing, Tao Kong, Wei Wang, Liang Wang, Lei Li, Tieniu Tan","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kim et al., 2022] Namyup Kim, Dongwon Kim, Cuiling Lan, Wenjun Zeng, and Suha Kwak. Restr: Convolution- free referring image segmentation using transformers. In CVPR, 2022.","title":"Restr: Convolutionfree referring image segmentation using transformers","authors":"Kim","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kirillov et al., 2019a] Alexander Kirillov, Ross Girshick, Kaiming He, and Piotr Dollár. Panoptic feature pyramid networks. In CVPR, 2019.","title":"Panoptic feature pyramid networks","authors":"Kirillov","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kirillov et al., 2019b] Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, and Piotr Dollár. Panop- tic segmentation. In CVPR, 2019.","title":"Panoptic segmentation","authors":"Kirillov","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2022a] Liunian Harold Li, Pengchuan Zhang, Haotian Zhang, Jianwei Yang, Chunyuan Li, Yiwu Zhong, Lijuan Wang, Lu Yuan, Lei Zhang, Jenq-Neng Hwang, et al. Grounded language-image pre-training. In CVPR, 2022.","title":"Grounded language-image pre-training","authors":"Li","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2022b] Xiangtai Li, Wenwei Zhang, Jiangmiao Pang, Kai Chen, Guangliang Cheng, Yunhai Tong, and Chen Change Loy. Video k-net: A simple, strong, and unified baseline for video segmentation. In CVPR, 2022.","title":"Video k-net: A simple, strong, and unified baseline for video segmentation","authors":"Li","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lin et al., 2014] Tsung-Yi Lin, Michael Maire, Serge Be- longie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Com- mon objects in context. In ECCV, 2014.","title":"Microsoft coco: Common objects in context","authors":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, C Lawrence, Zitnick","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Liu et al., 2021] Si Liu, Tianrui Hui, Shaofei Huang, Yun- chao Wei, Bo Li, and Guanbin Li. Cross-modal progres- sive comprehension for referring segmentation. TPAMI, 2021.","title":"Cross-modal progressive comprehension for referring segmentation","authors":"Si Liu, Tianrui Hui, Shaofei Huang, Yunchao Wei, Bo Li, Guanbin Li","year":"2021","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Long et al., 2015] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for seman- tic segmentation. In CVPR, 2015.","title":"Fully convolutional networks for semantic segmentation","authors":"Jonathan Long, Evan Shelhamer, Trevor Darrell","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Luo et al., 2020] Gen Luo, Yiyi Zhou, Xiaoshuai Sun, Li- ujuan Cao, Chenglin Wu, Cheng Deng, and Rongrong Ji. Multi-task collaborative network for joint referring expres- sion comprehension and segmentation. In CVPR, pages 10034-10043, 2020.","title":"Multi-task collaborative network for joint referring expression comprehension and segmentation","authors":"Gen Luo, Yiyi Zhou, Xiaoshuai Sun, Liujuan Cao, Chenglin Wu, Cheng Deng, Rongrong Ji","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Mohan and Valada, 2021] Rohit Mohan and Abhinav Val- ada. Efficientps: Efficient panoptic segmentation. IJCV, 2021.","title":"Efficientps: Efficient panoptic segmentation","authors":"Rohit Mohan, Abhinav Valada","year":"2021","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Mu et al., 2021] Zongshen Mu, Siliang Tang, Jie Tan, Qiang Yu, and Yueting Zhuang. Disentangled motif-aware graph learning for phrase grounding. In AAAI, 2021.","title":"Disentangled motif-aware graph learning for phrase grounding","authors":"Mu","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Pang et al., 2021] Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, and Fisher Yu. Quasi-dense similarity learning for multiple object track- ing. In CVPR, 2021.","title":"Quasi-dense similarity learning for multiple object tracking","authors":"Pang","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Plummer et al., 2018] Bryan A Plummer, Paige Kordas, M Hadi Kiapour, Shuai Zheng, Robinson Piramuthu, and Svetlana Lazebnik. Conditional image-text embedding networks. In ECCV, 2018.","title":"Conditional image-text embedding networks","authors":"Paige Bryan A Plummer, M Kordas, Shuai Hadi Kiapour, Robinson Zheng, Svetlana Piramuthu, Lazebnik","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Pont-Tuset et al., 2020] Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, and Vittorio Ferrari. Connecting vision and language with localized narratives. In ECCV, 2020.","title":"Jordi Pont-Tuset, Jasper Uijlings, Soravit Changpinyo, Radu Soricut, and Vittorio Ferrari. Connecting vision and language with localized narratives","authors":"Pont-Tuset","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Radford et al., 2021] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agar- wal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from nat- ural language supervision. In ICML, 2021.","title":"Learning transferable visual models from natural language supervision","authors":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Raffel et al., 2020] Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 2020.","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","authors":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu","year":"2020","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Tan et al., 2020] Zhenxiong Tan, Tianrui Hui, Jinyu Chen, and Si Liu. Multi-granularity multimodal feature interac- tion for referring image segmentation. In PRCV, 2020.","title":"Multi-granularity multimodal feature interaction for referring image segmentation","authors":"Tan","year":"2020","venue":"PRCV","doi":null,"url":null,"internal_url":null},{"position":33,"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. NeurIPS, 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":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wang et al., 2018] Liwei Wang, Yin Li, Jing Huang, and Svetlana Lazebnik. Learning two-branch neural networks for image-text matching tasks. TPAMI, 2018.","title":"Learning two-branch neural networks for image-text matching tasks","authors":"Liwei Wang, Yin Li, Jing Huang, Svetlana Lazebnik","year":"2018","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wang et al., 2020] Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam, Alan Yuille, and Liang-Chieh Chen. Axial-deeplab: Stand-alone axial-attention for panoptic segmentation. In ECCV, 2020.","title":"Axial-deeplab: Stand-alone axial-attention for panoptic segmentation","authors":"Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam, Alan Yuille, Liang-Chieh Chen","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wang et al., 2022] Zhaoqing Wang, Yu Lu, Qiang Li, Xun- qiang Tao, Yandong Guo, Mingming Gong, and Tongliang Liu. Cris: Clip-driven referring image segmentation. In CVPR, 2022.","title":"Cris: Clip-driven referring image segmentation","authors":"Zhaoqing Wang, Yu Lu, Qiang Li, Xunqiang Tao, Yandong Guo, Mingming Gong, Tongliang Liu","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wu et al., 2022] Junfeng Wu, Qihao Liu, Yi Jiang, Song Bai, Alan Yuille, and Xiang Bai. In defense of online mod- els for video instance segmentation. In ECCV, 2022.","title":"In defense of online models for video instance segmentation","authors":"Junfeng Wu, Qihao Liu, Yi Jiang, Song Bai, Alan Yuille, Xiang Bai","year":"2022","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Yang et al., 2022] Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, and Philip HS Torr. Lavt: Language-aware vision transformer for referring image segmentation. In CVPR, 2022.","title":"Lavt: Language-aware vision transformer for referring image segmentation","authors":"Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip Hs Torr","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Ye et al., 2019] Linwei Ye, Mrigank Rochan, Zhi Liu, and Yang Wang. Cross-modal self-attention network for refer- ring image segmentation. In CVPR, 2019.","title":"Cross-modal self-attention network for referring image segmentation","authors":"Ye","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Yu et al., 2020] Tianyu Yu, Tianrui Hui, Zhihao Yu, Yue Liao, Sansi Yu, Faxi Zhang, and Si Liu. Cross-modal omni interaction modeling for phrase grounding. In ACM MM, 2020.","title":"Cross-modal omni interaction modeling for phrase grounding","authors":"Tianyu Yu, Tianrui Hui, Zhihao Yu, Yue Liao, Sansi Yu, Faxi Zhang, Si Liu","year":"2020","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zhang et al., 2021] Wenwei Zhang, Jiangmiao Pang, Kai Chen, and Chen Change Loy. K-net: Towards unified im- age segmentation. In NeurIPS, 2021.","title":"K-net: Towards unified image segmentation","authors":"Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhou et al., 2021] Qianli Zhou, Tianrui Hui, Rong Wang, Haimiao Hu, and Si Liu. Attentive excitation and aggre- gation for bilingual referring image segmentation. TIST, 2021.","title":"Attentive excitation and aggregation for bilingual referring image segmentation","authors":"Zhou","year":"2021","venue":"TIST","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Zhu et al., 2020] Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. Deformable detr: De- formable transformers for end-to-end object detection. In ICLR, 2020.","title":"Deformable detr: Deformable transformers for end-to-end object detection","authors":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}