Gurkirt Singh's Projects
Train action classification model based on individual frames
3D-RetinaNet a baseline models on ROAD dataset
Action tracker from GTR
This repository is intended to host tools and demos for ActivityNet
Action Micro Tube Network (AMTNet) - Pytorch with linear heads
This repo provided utility tools to browse the videos and annotation files for DALY dataset.
Tensor-flow trainer for action classification and detection
Diffuse optical flow for 3D edits of images
Feature pyramid network (FPN) with online hard example mining (OHEM)
Download kinetics and prepare '.json' annotations for each subset
Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything
compute optical flow on GPU using opencv and set of image sequences rather than videos. Use ffmpeg for video to image sequence conversion
Compression free packing and unpacking of frames via tarballs
Preprocess the activityNet dataset for detection task
This repository host the code for real-time action detection paper
RetinaNet with different loss function types
Download and pre-processing of ROAD dataset
This copy of https://github.com/WongKinYiu/ScaledYOLOv4/tree/yolov4-large for Action detection
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
Simple example to train SVM using libSVM and liblinear
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
Real-time multi-camera multi-object tracker using YOLOv5 and StrongSORT with OSNet