Junjie Yan

Latest

• Dynamic Recursive Neural Network
• Fully Quantized Network for Object Detection
• Grid R-CNN
• IRLAS: Inverse Reinforcement Learning for Architecture Search
• Learning to Cluster Faces on an Affinity Graph
• P2SGrad: Refined Gradients for Optimizing Deep Face Models
• R3 Adversarial Network for Cross Model Face Recognition
• SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
• Video Generation from Single Semantic Label Map
• Accelerated Training for Massive Classification via Dynamic Class Selection
• Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher Accuracy
• Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
• Crafting GBD-Net for Object Detection
• Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift
• Distractor-Aware Siamese Networks for Visual Object Tracking
• Eliminating Background-Bias for Robust Person Re-Identification
• End-to-End Flow Correlation Tracking With Spatial-Temporal Attention
• Exploring Disentangled Feature Representation Beyond Face Identification
• FOTS: Fast Oriented Text Spotting With a Unified Network
• FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
• Fully Motion-Aware Network for Video Object Detection
• High Performance Visual Tracking With Siamese Region Proposal Network
• Jointly Learning Deep Features, Deformable Parts, Occlusion and Classification for Pedestrian Detection
• Localization Guided Learning for Pedestrian Attribute Recognition
• Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
• Practical Block-Wise Neural Network Architecture Generation
• Quantization Mimic: Towards Very Tiny CNN for Object Detection
• Synaptic Strength For Convolutional Neural Network
• T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos
• DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks
• HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
• Mimicking Very Efficient Network for Object Detection
• Object Detection in Videos with Tubelet Proposal Networks
• Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification
• Quality Aware Network for Set to Set Recognition
• Recurrent Scale Approximation for Object Detection in CNN
• Scale-Aware Face Detection
• Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion
• CRAFT Objects from Images
• Gated Bi-directional CNN for Object Detection
• Joint Training of Cascaded CNN for Face Detection
• Objectness-aware Semantic Segmentation
• Convolutional Channel Features
• Discriminative 3D morphable model fitting
• Fine-grained evaluation on face detection in the wild
• High-fidelity Pose and Expression Normalization for face recognition in the wild
• Object detection by labeling superpixels
• Aggregate channel features for multi-view face detection
• Face detection by structural models
• Multiple Target Tracking Based on Undirected Hierarchical Relation Hypergraph
• Salient Color Names for Person Re-identification
• Stacked Deformable Part Model with Shape Regression for Object Part Localization
• The Fastest Deformable Part Model for Object Detection
• Robust Multi-resolution Pedestrian Detection in Traffic Scenes
• Structural models for face detection
• Multi-pedestrian detection in crowded scenes: A global view