【报告资料】多媒体顶级会议ACM Multimedia 2017 China Pre-conference论文宣讲报告分享

【导读】第25届ACM国际多媒体会议（ACM International Conference on Multimedia, 简称ACMMM）于2017年10月23日至27日在美国硅谷Mountain View隆重举行。自1993年首次召开以来，ACMMM每年召开一次，已经成为多媒体领域顶级会议，也是中国计算机学会推荐的A类国际学术会议热门方向有大规模图像视频分析、社会媒体研究、多模态人机交互、计算视觉、计算图像等等。

昨天ACM SIGMM China Chapter在北京举行ACM MM 2017 Pre-Conference，【学术盛宴 】多媒体顶级会议ACM Multimedia 2017 China Pre-conference论文宣讲研讨会，我们今天分享ACM MM论文宣讲者的报告Slide：

1. 1. Beyond Human-level License Plate Super-resolution with Progressive Vehicle Search and Domain Priori GAN
   Wu Liu (Beijing University of Posts and Telecommunications); Xinchen Liu (Beijing University of Posts and Telecommunications); Huadong Ma (Beijing University of Posts and Telecommunications); Peng Cheng (Beijing University of Posts and Telecommunications)

• 报告地址：链接: https://pan.baidu.com/s/1qYdriNE 密码: c96r

• 2. Deep Unsupervised Convolutional Domain Adaptation
  Junbao Zhuo (Key Lab of Intellectual Information Processing(CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China); Shuhui Wang (Key Lab of Intellectual Information Processing(CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China); Weigang Zhang (Harbin Institute of Technology (Weihai)); Qingming Huang (University of Chinese Academy of Sciences)

• 报告地址：链接: https://pan.baidu.com/s/1jIGdaaa 密码: speb

• 3. Finding the Secret of CNN Parameter Layout under Strict Size Constraint
  Liao Lixin (Beijing Jiaotong Universiy); Yao Zhao (Beijing Jiaotong Universiy); Shikui Wei (Beijing Jiaotong Universiy); Wang Jingdong (Microsoft Research Asia); Liu Ruoyu (Beijing Jiaotong Universiy)

• 报告地址：链接: https://pan.baidu.com/s/1b3RSqa 密码: e8ex

• 4. GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
  Longhui Wei (Peking University); Shiliang Zhang (Peking University); Hantao Yao (Institue of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences); Wen Gao (Peking University); Qi Tian (Department of Computer Science, University of Texas at San Antonio)

• 报告地址：链接: https://pan.baidu.com/s/1nuZtxoP 密码: xe8w

• 5. One-Shot Fine-Grained Instance Retrieval
  Hantao Yao (Institute of Computing Technology (ICT), Chinese Academy of Sciences; University of Chinese Academy of Sciences); Shiliang Zhang (Electronic Engineering and Computer Science,Peking University); Yongdong Zhang (Institute of Computing Technology (ICT), Chinese Academy of Sciences); Jintao Li (Institute of Computing Technology (ICT), Chinese Academy of Sciences); Qi Tian (Computer Science University of Texas at San Antonio)

• 报告地址：链接: https://pan.baidu.com/s/1skKsnBB 密码: vmms

• 6. Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN
  Xiangteng He (Peking University); Yuxin Peng (Peking University); Junjie Zhao (Peking University)

• 报告地址：链接: https://pan.baidu.com/s/1kVN214j 密码: kgng

• 7. Multi-Modal Knowledge Representation Learning via Webly-Supervised Relationships Mining
  Fudong Nian (Anhui University); Bingkun Bao (CASIA); Teng Li (Anhui University); Changsheng Xu (CASIA)

• 报告地址：链接: https://pan.baidu.com/s/1kUVZJuf 密码: dktt

• 8. Video Visual Relation Detection
  Xindi Shang (National University of Singapore); Tongwei Ren (Nanjing University); Jingfan Guo (Nanjing University); Hanwang Zhang (Columbia University); Tat-Seng Chua (National University of Singapore)

• 报告地址：链接: https://pan.baidu.com/s/1sl8xo77 密码: ikxc

• 9. A Unified Personalized Video Recommendation via Dynamic Recurrent Neural Networks
  Junyu Gao (Institute of Automation, Chinese Academy of Sciences); Tianzhu Zhang (Institute of Automation, Chinese Academy of Sciences); Changsheng Xu (Institute of Automation, Chinese Academy of Sciences)

• 报告地址：链接: https://pan.baidu.com/s/1dF5xR5B 密码: 4s75

• 10. RGB-D Scene Recognition with Object-to-Object Relation
  Xinhang Song (Institute of Computing Technology of Chinese Academy of Sciences (CAS)); Chengpeng Chen (Institute of Computing Technology of Chinese Academy of Sciences (CAS)); Shuqiang Jiang (Institute of Computing Technology of Chinese Academy of Sciences (CAS))

• 报告地址：链接: https://pan.baidu.com/s/1pKNKj39 密码: d7da

• 11. Mulit-scale Context based Attention for Dynamic Music Emotion Prediction
  Ye Ma (Tsinghua University); Xinxing Li (Tsinghua University); Mingxing Xu (Tsinghua University); Lianhong Cai (Tsinghua University)

• 报告地址：链接: https://pan.baidu.com/s/1bpgz3zD 密码: emgd

• 12. Multi-Networks Joint Learning for Large-Scale Cross-Modal Retrieval
  Liang Zhang (ucas); Bingpeng Ma (UCAS); Guorong Li (ucas); Qingming Huang (ucas); Qi Tian (University of Texas at San Antonio)

• 报告地址：链接: https://pan.baidu.com/s/1pL6z019 密码: wmre

-END-

欢迎使用专知

专知，一个新的认知方式！目前聚焦在人工智能领域为AI从业者提供专业可信的知识分发服务, 包括主题定制、主题链路、搜索发现等服务，帮你又好又快找到所需知识。

使用方法>>访问www.zhuanzhi.ai, 或点击文章下方“阅读原文”即可访问专知

中国科学院自动化研究所专知团队

@2017 专知

专 · 知

关注我们的公众号，获取最新关于专知以及人工智能的资讯、技术、算法、深度干货等内容。扫一扫下方关注我们的微信公众号。