Multi-Stream Siamese and Faster Region-Based Neural Network for Real-Time Object Tracking

Towards a Unified Middle Modality Learning for Visible-Infrared Person Re-Identification

D3Net: Dual-Branch Disturbance Disentangling Network for Facial Expression Recognition

Semantic-Guided Relation Propagation Network for Few-shot Action Recognition

Hierarchical Representation Via Message Propagation for Robust Model Fitting

Deep Correlation Filter Tracking With Shepherded Instance-Aware Proposals

Robust optical flow estimation via edge preserving filtering

Robust Geometric Model Fitting Based on Nonnegative Matrix Underapproximation with Pruning Techniques for Multi-Structure Data

Semantic-Aware Occlusion-Robust Network for Occluded Person Re-Identification

Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes

Learning intra-inter semantic aggregation for video object detection

Robust visual tracking via scale-aware localization and peak response strength

Single image super-resolution with multi-scale information cross-fusion network

Recurrent Context Aggregation Network for Single Image Dehazing

Segmentation by Continuous Latent Semantic Analysis for Multi-structure Model Fitting

Motion Consistency Guided Robust Geometric Model Fitting With Severe Outliers

Joint regularization and low-rank fusion for atmospheric turbulence removal

Learning Spatial-Semantic Relationship for Facial Attribute Recognition with Limited Labeled Data

Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition

Temporal Relation based Attentive Prototype Network for Few-shot Action Recognition

Small-Vote Sample Selection for Label-Noise Learning