第32届IEEE国际计算机视觉与模式识别会议 (IEEE Conference on Computer Vision and Pattern Recognition，CVPR 2019)将于2019年6月15日-20日在美国长滩召开。

作为计算机视觉和模式识别领域的顶级会议，CVPR 2019录取论文代表了计算机视觉领域在2019年最新和最高的科技水平以及未来发展潮流。本次会议共计提交5165篇论文，1300篇被接收，接受率为25.2%。

计算机所共有7篇论文被该会议录用，分别做了字体动态特效迁移、基于对象感知双向图的视频描述生成方法、无监督图像生成、视频去雨、文字风格化、无监督学习及安防视频人群计数与定位等的相关研究。论文的具体信息如下：

[1] Yifang Men, Zhouhui Lian, Yingmin Tang, Jianguo Xiao. DynTypo: Example-based Dynamic Text Effects Transfer

[2] Junchao Zhang and Yuxin Peng, "Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning"

[3] Chenchen Liu, Xinyu Weng, Yadong Mu. Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization

[4] Sijie Song, Wei Zhang, Jiaying Liu, Tao Mei. Unsupervised Person Image Generation with Semantic Parsing Transformation

[5] Wenhan Yang, Jiaying Liu, Jiashi Feng. Frame-Consistent Recurrent Video Deraining with Dual-Level Flow

[6] Wenjing Wang, Jiaying Liu, Shuai Yang, Zongming Guo. Typography with Decor: Intelligent Text Style Transfer

[7] Chen Wei, Lingxi Xie, Xutong Ren, Yingda Xia, Chi Su, Jiaying Liu, Qi Tian, Alan L. Yuille. Iterative Reorganization with Weak Spatial Constraints:Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning