Varun Ganjigunte Prakash's starred repositories
segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Awesome-LLMOps
An awesome & curated list of best LLMOps tools for developers
mmtracking
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
tracking_wo_bnw
Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"
TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
StrongSORT-YOLO
Real-time multi-camera multi-object tracker using (YOLOv5, YOLOv7,YOLOv8) and StrongSORT with OSNet
attention-target-detection
[CVPR2020] "Detecting Attended Visual Targets in Video"
Person-Re-identification
Detection, tracking and re-identification of people in a surveillance video to make a list of people that appeared in the video. If people leave the frame and re-appear later in the video, the model recognizes them from before and does not count them multiple times.
Instruct-ReID
A General-purpose Person Re-identification Task with Instructions
ByteTrack_ReID
ByteTrack with ReID module following the paradigm of FairMOT, tracking strategy is borrowed from FairMOT/JDE.
RandPerson
Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification
TRG-Release
Official PyTorch implementation of "6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry," ECCV 2024
keypoint_promptable_reidentification
[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity
Amodal-Expander
Official Training and Inference Code of Amodal Expander, Proposed in Tracking Any Object Amodally
MMGaze_VGS
KETI project
Face-And-ObjectDetection-With-Glasses-Overlay-And-Gender-Classification
A real-time face and object detection with gender classification and virtual glasses overlay.