FFT(Flow-Fuse Tracker)[1] is an end-to-end DNN tracking approach, that jointly learns both target motions and associations for MOT(multiple object tracking). There are some details of reading and implementing it.

JRMOT[1] is a novel 3D MOT system that integrates information from 2D RGB images and 3D point clouds into a real-time performing framework. There are some details of reading and implementing it.

Pose-Assisted Multi-Camera Collaboration System[1] is a novel method, which enables a camera to cooperate with the others by sharing camera poses for AOT(active object tracking). There are some details of reading and implementing it.

GlobalTrack[1] is a pure global tracker for long-term tracking, without temporal consistency assumption making cumulative errors. There are some details of reading and implementing it.

SiamMask[1] is used to detect and segment objects from videos in each frame, initializing a single bounding box and outputing binary segmentation mask and rotated objects boxes. There are some details of reading and implementing it.

Tracktor[1] is used to detect objects from videos in each frame, while forming tracks by linking corresponding detections across time. There are some details of reading and implementing it.

Faster R-CNN[1] is used to detect objects in images, with outputing bounding box and class scores. There are some details of reading and implementing it.

ResNet[1] is used to classify images with deep residual learning. There are some details of reading and implementing it.

GoogLeNet[1] is used to classify images with inception v1. There are some details of reading and implementing it.

There are some details of reading and implementing the Network In Network for image classification.