Paper Review

Classification & Detection

• AlexNet — ImageNet Classification with Deep Convolutional Neural Networks
• VGG — Very Deep Convolutional Networks for Large-Scale Image Recognition
• GoogLeNet — Going Deeper with Convolutions
• ResNet — Deep Residual Learning for Image Recognition
• MobileNet — MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• ShuffleNet — ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• DenseNet — Densely Connected Convolutional Networks
• EfficientNet —EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• YOLOv1 — You Only Look Once: Unified, Real-Time Object Detection
• YOLOv2 — YOLO 9000: Better, Faster, Stronger
• FPN(Feature Pyramid Networks) — Feature Pyramid Networks for Object Detection
• Learning Rich Features at High-Speed for Single-shot Object Detection

Video Recognition

• C3D — Learning Spatiotemporal Features with 3D Convolutional networks
• T3D — Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification
• I3D — Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
• STM — STM: SpatioTemporal and Motion Encoding for Action Recognition

Speed Estimation

• Traffic Speed Estimation from Surveillance Video — (2018 AI City Challenge)