zuble

actionformer_release

Code release for ActionFormer (ECCV 2022)

UniMD

UniMD: Towards Unifying Moment retrieval and temporal action Detection

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

DyFADet-pytorch

bypass-paywalls-chrome-clean

iterframes

Process quickly all videos in the world, one frame at time.

gtop

📊 A simple command-line script (wrapper for nvidia-smi) for monitoring NVIDIA GPUs

query2labels

Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".

ASL

Official Pytorch Implementation of: "Asymmetric Loss For Multi-Label Classification"(ICCV, 2021) paper

Feature-Extraction-for-Video-Anomaly-Detection

Activity Recognition Feature Extraction C3D / I3D for Weakly Supervised Video Anomaly Detection

research-xbm

XBM: Cross-Batch Memory for Embedding Learning

PyTorch-Hydra-Template

[WIP] PyTorch & Hydra Template

tinyCLAP

Implementation of tinyCLAP.

Learning-to-Adapt-to-Unseen-Abnormal-Activities

ONE-PEACE

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

pytorch-adapt

Domain adaptation made easy. Fully featured, modular, and customizable.

hear-eval-kit

Evaluation kit for the HEAR Benchmark

ViTamin

[CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"

EfficientAT_HEAR

Evaluate EfficientAT models on the Holistic Evaluation of Audio Representations Benchmark.

gameoflife

Game of Life in C++

lyrebird-wav2clip

Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP

passt_hear21

Inference code for PaSST, using the HEAR API.

FACE

Urban Sound Annotation and Classification

VAD-LLaMA

Official implement of VAD-LLaMA

EfficientTrain

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

slowfast_feature_extractor

Feature Extractor module for videos using the PySlowFast framework

TDN

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

GSM

Gate-Shift Networks for Video Action Recognition - CVPR 2020

MotionSqueeze

Official PyTorch Implementation of MotionSqueeze, ECCV 2020