An annotated implementation of the Transformer paper.

Grounded Language-Image Pre-training

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

CLIP + FFT/DWT/RGB = text to image/video

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.

End-to-End Object Detection with Transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

a cluster method for traffic

Contrastive Language-Image Forensic Search allows free text searching through videos using OpenAI's machine learning model CLIP

[ACM MM 2021] Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)

Vehicle Counting model that automatically detects the Region of Interest and Driving Trajectory. Uses YOLOv4 for object detection, DeepSORT for object tracking, k-means for clustering different tra…

we train UA_DETRAC dataset by yolox to achieve car detection

Extract vehicle trajectory/driver control information from a traffic video.

CODE OF HUI

You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery

This application written in Python is capable of fully automatic clustering of 2D trajectory data.