An efficient video loader for deep learning with smart shuffling that's super easy to digest

VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments

See the Future: A Semantic Segmentation Network Predicting Ego-vehicle Trajectory with a Single Monocular Camera

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

RT-GENE: Real-Time Eye Gaze and Blink Estimation in Natural Environments

The official PyTorch implementation of L2CS-Net for gaze estimation and tracking

This repository contains demos I made with the Transformers library by HuggingFace.

Dual Swin Transformer for video-time-series fusion

Access large language models from the command-line

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Refine high-quality datasets and visual AI models

Official repo for our paper: "What Matters in Autonomous Driving Anomaly Detection: A Weakly Supervised Horizon"

Annotation for reproducing the result of the paper "Cross-model temporal cooperation via saliency maps for efficient recognition and classification of relevant traffic lights" .

Software Development Kit for the Zenseact Open Dataset (ZOD)

A playbook for systematically maximizing the performance of deep learning models.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

A latent text-to-image diffusion model

Render JSON into collapsible HTML

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

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

Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).

[ICCV 2021] Deep Reinforced Accident Anticipation with Visual Explanation

GLIDE: a diffusion-based text-conditional image synthesis model

[ACM MM 2020] CCD dataset for traffic accident anticipation.

Optimization Models used in my e-book with the same title

This is the repo for our Detection of Traffic Anomaly (DoTA) dataset.

[ECCV 2020] Learning stereo from single images using monocular depth estimation networks