MOT using deepsort and yolov3 with pytorch

HaMeR: Reconstructing Hands in 3D with Transformers

FlashMLA: Efficient MLA decoding kernels

Fully open reproduction of DeepSeek-R1

This repo contains the resources for DeepSeek R1.

Inference Llama 2 in one file of pure C

[ICLR'23] AIM: Adapting Image Models for Efficient Video Action Recognition

3D-RetinaNet a baseline models on ROAD dataset

科技爱好者周刊，每周五发布

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

CVPR 2023: Official code for `Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting'

Argoverse 2: Next generation datasets for self-driving perception and forecasting.

[ICCV 2023] Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

CVPR2023-Occupancy-Prediction-Challenge

Online HD Map Construction CVPR2023

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

[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.

50%+ Faster Cylinder3D, compatible with current PyTorch, CUDA, and Spconv versions

Convert waymo open dataset 3D segmentation format to SemanticKITTI format.