ICCV2017论文分类

Person ReID

• Neural Person Search Machines

• Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification

• SHaPE: A Novel Graph Theoretic Algorithm for Making Consensus-Based Decisions in Person Re-Identification Systems

• A Two Stream Siamese Convolutional Neural Network for Person Re-Identification

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

• Learning View-Invariant Features for Person Identification in Temporally Synchronized Videos Taken by Wearable Cameras

• Deeply-Learned Part-Aligned Representations for Person Re-Identification

• Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro

• Pose-Driven Deep Convolutional Model for Person Re-Identification

• Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-Identification

• RGB-Infrared Cross-Modality Person Re-Identification

• Multi-Scale Deep Learning Architectures for Person Re-Identification

Tracking

• Non-Markovian Globally Consistent Multi-Object Tracking

• CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos

• Online Multi-Object Tracking Using CNN-Based Single Object Tracker With Spatial-Temporal Attention Mechanism

• Tracking the Untrackable: Learning to Track Multiple Cues With Long-Term Dependencies

• Learning Dynamic Siamese Network for Visual Object Tracking

Pose estimation

• Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms

• Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation

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

• Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation

• Learning Feature Pyramids for Human Pose Estimation

• Making Minimal Solvers for Absolute Pose Estimation Compact and Robust

• RMPE: Regional Multi-Person Pose Estimation

• A Simple yet Effective Baseline for 3D Human Pose Estimation

• Robust Hand Pose Estimation During the Interaction With an Unknown Object

• Monocular 3D Human Pose Estimation by Predicting Depth on Joints

• Deep Globally Constrained MRFs for Human Pose Estimation

• Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment With Limited Resources

• Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

• Active Learning for Human Pose Estimation

• Human Pose Estimation Using Global and Local Normalization

Semantic Segmentation

• Predicting Deeper Into the Future of Semantic Segmentation

• Cascaded Feature Network for Semantic Segmentation of RGB-D Images

• Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel

• Adversarial Examples for Semantic Segmentation and Object Detection

• VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

• Bringing Background Into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation

• RDFNet: RGB-D Multi-Level Residual Feature Fusion for Indoor Semantic Segmentation

• 3D Graph Neural Networks for RGBD Semantic Segmentation

• Semi Supervised Semantic Segmentation Using Generative Adversarial Network

Instance Segmentation

• SGN: Sequential Grouping Networks for Instance Segmentation

• Mask R-CNN

Crowd counting

• Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs

• Spatiotemporal Modeling for Crowd Counting in Videos

Vehicle ReID

• Learning Deep Neural Networks for Vehicle Re-ID With Visual-Spatio-Temporal Path Proposals

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

GAN

• Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro

• Least Squares Generative Adversarial Networks

• Semi Supervised Semantic Segmentation Using Generative Adversarial Network

• StackGAN: Text to Photo-Realistic Image Synthesis With Stacked Generative Adversarial Networks

• Semantic Image Synthesis via Adversarial Learning

• Dual Motion GAN for Future-Flow Embedded Video Prediction

• GANs for Biological Image Synthesis

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

• CVAE-GAN: Fine-Grained Image Generation Through Asymmetric Training

• DualGAN: Unsupervised Dual Learning for Image-To-Image Translation

• Recurrent Topic-Transition GAN for Visual Paragraph Generation

• Realistic Dynamic Facial Textures From a Single Image Using GANs

video summarization

• Weakly Supervised Summarization of Web Videos

• Summarization and Classification of Wearable Camera Streams by Learning the Distributions Over Deep Features of Out-Of-Sample Image Sequences