The Continuous Convolution Operator Tracker (C-COT).

Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking (CVPR 2018)

Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016

[CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..

Non-maximum suppression for object detection in a neural network

Object Detection

Pelee: A Real-Time Object Detection System on Mobile Devices

Code for our CVPR 2018 paper "Optimizing Video Object Detection via a Scale-Time Lattice".

Train faster rcnn on imagine dataset, related blog post: https://andrewliao11.github.io/object/detection/2016/07/23/detection/

Video detection library