Abstract  Description  Claims  Drawing  Search report  Cited references 

You Only Look Once: Unified, Real-Time Object Detection   [0042] 
SSD: Single Shot MultiBox Detector   [0042] 
Faster R-CNN: Toward Real-Time Object Detection with Region Proposal Networks   [0042] 
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications   [0042] 
Simple Online and Realtime Tracking with a Deep Association Metric   [0043] 
Tracking without bells and whistles   [0043] 
Deep Learning in Video Multi-Object Tracking: A Survey   [0043] 
Extending IOU Based Multi-Object Tracking by Visual Information   [0043] 
Tracking Objects as Points   [0043] 
Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Association   [0043] 
Object Tracking using OpenCV (C++ / Python)   [0043] 
Deep Residual Learning for Image Recognition   [0046]  [0081] 
Rethinking the Inception Architecture for Computer Vision   [0046]  [0081] 
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks   [0046] 
EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search   [0046]  [0081] 
End-to-end deep learning-based autonomous driving control for high-speed environment   [0047] 
Toward End-to-End Control for UAV Autonomous Landing via Deep Reinforcement Learning   [0047] 
Deep Learning based Feature Extraction for Texture Classification   [0048] 
Spatial-Temporal Recurrent Neural Network for Emotion Recognition   [0063] 
A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection   [0063] 
VoxelMorph: A Learning Framework for Deformable Medical Image Registration   [0066] 
Convolutional neural network architecture for geometric matching   [0066] 
Spatial Transformer Networks   [0067] 
Attentive Semantic Alignment with Offset-Aware Correlation Kernels   [0067] 
Video Foreground Detection Algorithm Based on Fast Principal Component Pursuit and Motion Saliency   [0068]  [0106] 
Robust Principal Component Analysis?   [0068]  [0106] 
Good features to track   [0071] 
Machine learning for high-speed corner detection   [0071] 
Adaptive and generic corner detection based on the accelerated segment test   [0071] 
Scale & Affine Invariant Interest Point Detectors   [0071] 
CenSurE: Center surround extremas for real time feature detection and matching   [0071] 
Distinctive Image Features from Scale-Invariant Keypoints   [0071] 
ORB: An efficient alternative to SIFT or SURF   [0071] 
BRISK: Binary Robust invariant scalable keypoints   [0071] 
Fast explicit diffusion for accelerated features in nonlinear scale spaces   [0072] 
Kaze features   [0072] 
Freak: Fast retina keypoint   [0072] 
Brief: Computing a local binary descriptor very fast   [0072] 
Daisy: An Efficient Dense Descriptor Applied to Wide Baseline Stereo   [0072] 
Latch: Learned arrangements of three patch codes   [0072] 
Very deep convolutional networks for large-scale image recognition   [0072] 
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,สบ   [0081] 
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles   [0082] 
Uncertainty Quantification and Deep Ensembles   [0082] 
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization   [0083] 
Layer-Wise Relevance Propagation: An Overview   [0083] 
Axiomatic Attribution for Deep Networks   [0083] 
Learning How to Explain Neural Networks: PatternNet and PatternAttribution   [0083] 
The adoption of deep learning interpretability techniques on diabetic retinopathy analysis: a review   [0083] 
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps   [0083] 
Visualizing and Understanding Convolutional Networks   [0083] 
Robust Template Matching via Hierarchical Convolutional Features from a Shape Biased CNN   [0084]