Stars
[CVPR 2023] STMixer: A One-Stage Sparse Action Detector
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
torch models and primitives for birdseye view and voxel models for self driving tasks.
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
A collection of literature after or concurrent with Masked Autoencoder (MAE) (Kaiming He el al.).
Paper survey of efficient computation for large scale models.
[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio
Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline
[CVPR 2023] An academic alternative to Tesla's occupancy network for autonomous driving.
This is a Chinese translation of the CUDA programming guide
A playbook for systematically maximizing the performance of deep learning models.
Vision-Centric BEV Perception: A Survey
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
[CVPR 2022] Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection
Keras Temporal Convolutional Network. Supports Python and R.
A Python implementation of global optimization with gaussian processes.
MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips
[CVPR 2022] Task-specific Inconsistency Alignment for Domain Adaptive Object Detection
[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Repository containing all necessary codes to get started on the SoccerNet Tracking challenge. This repository also contains benchmark methods to get started.
[ICCV'21] Implementation of "Watch Only Once: An End-to-End Video Action Detection Framework"
Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.
Real-world Anomaly Detection in Surveillance Videos CVPR2018 UCF-Crime dataset
Code for our CVPR 2021 paper "Coarse-Fine Networks for Temporal Activity Detection in Videos"