ArrowLuo

CLIP4Clip

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

SegCLIP

PyTorch implementation of ICML 2023 paper "SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation"

DOER

The implementation of ACL 2019 paper DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction

VideoFeatureExtractor

Video Feature Extractor for S3D-HowTo100M

GRACE

The impletation of paper titled GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

FCMFrame

FCM visualization by Java awt

BiDTree

The implementation of TASLP 2019 paper Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation

allosaurus

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

Awesome-Video-Diffusion

A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

CLIP

Contrastive Language-Image Pretraining

ConvNeXt

Code release for ConvNeXt model

Deep3DFaceRecon_pytorch

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.

faceswap

Deepfakes Software For All

fast_pytorch_kmeans

This is a pytorch implementation of k-means clustering algorithm

frozen-in-time

Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]

GroupViT

Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.

IDE-3D

[SIGGRAPH Asia 2022] IDE-3D: Interactive Disentangled Editing For High-Resolution 3D-aware Portrait Synthesis

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

MMSA

CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotations of Modality (ACL2020)

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

ScreenToGif

🎬 ScreenToGif allows you to record a selected area of your screen, edit and save it as a gif or video.

sd-1click-colab

SLIP

Code release for SLIP Self-supervision meets Language-Image Pre-training

TempFiles

Text2Video

ICASSP 2022: "Text2Video: text-driven talking-head video synthesis with phonetic dictionary"

uda

Unsupervised Data Augmentation (UDA)

unilm

UniLM AI - Unified "Language" Model Pre-training across Tasks, Languages, and Modalities

UniVL

An official implementation for " UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation"

vision

Datasets, Transforms and Models specific to Computer Vision

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.