【ICCV 2017论文集】计算机视觉顶级会议ICCV2017 Open Access Repository

点击上方“专知”关注获取更多AI知识!

在这里先整理一些主题系列论文：

ICCV 2017- 3D Vision Oral论文如下：

• Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence

• Robust Pseudo Random Fields for Light-Field Stereo Matching    

• A Lightweight Approach for On-The-Fly Reflectance Estimation

• Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus

• Practical Projective Structure From Motion (P2SfM)
  

ICCV 2017- Recognition 论文如下：

• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis    

• No Fuss Distance Metric Learning Using Proxies    

• Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation

• Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-Identification

• Fashion Forward: Forecasting Visual Style in Fashion
  

• Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

• Flow-Guided Feature Aggregation for Video Object Detection

• Reasoning About Fine-Grained Attribute Phrases Using Reference Games

  
  

  
  

ICCV 2017- Statistical Methods & Learning 论文如下：

• Towards Context-Aware Interaction Recognition for Visual Relationship Detection    

• When Unsupervised Domain Adaptation Meets Tensor Representations    

• Look, Listen and Learn    

• Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization

• Image-Based Localization Using LSTMs for Structured Feature Correlation

ICCV 2017- Video 论文如下：

• A Read-Write Memory Network for Movie Story Understanding    

• SegFlow: Joint Learning for Video Object Segmentation and Optical Flow  

• Unsupervised Action Discovery and Localization in Videos

• Dense-Captioning Events in Videos

• Learning Long-Term Dependencies for Action Recognition With a Biologically-Inspired Deep Network 

• Compressive Quantization for Fast Object Instance Search in Videos

• Complex Event Detection by Identifying Reliable Shots From Untrimmed Videos
  

ICCV 2017- Face & Gesture 论文如下：

• Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification

• Stepwise Metric Promotion for Unsupervised Video Person Re-Identification

• Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis   

• Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding

• Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification
  

原文地址：http://openaccess.thecvf.com/ICCV2017.py

请点击“阅读原文”，查看全部！

获取更多关于机器学习以及人工智能知识资料，请访问www.zhuanzhi.ai, 或者点击阅读原文，即可得到！

欢迎转发分享到微信群和朋友圈！

获取更多关于机器学习以及人工智能知识资料，请访问www.zhuanzhi.ai, 或者点击阅读原文，即可得到！

-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。

点击“阅读原文”，使用专知！