[ICLR'25] Official Implement of "Uni-Sign: Toward Unified Sign Language Understanding at Scale"

Self-supervised video pretraining for sign language translation.

Self-supervised video pretraining for sign language translation.

🎓Automatically Update Human Avatar and Gaussian Splatting Papers. Support Sending Notifications to Email.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

The official implementation of SEDS: Semantically Enhanced Dual-Stream Encoder for Sign Language Retrieval

Effortless data labeling with AI support from Segment Anything and other awesome models.

Documentation and background of sign language processing

This repository is the source code for MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition

This repository is the source code for Self-Supervised Representation Learning with Spatial-Temporal Consistency for Sign Language Recognition

Official PyTorch implementation of "Extract Free Dense Labels from CLIP" (ECCV 22 Oral)

SLTUNET: A Simple Unified Model for Sign Language Translation (ICLR 2023)

An open source implementation of CLIP.

A minimal implementation of diffusion models for text generation

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Reduce the size of pretrained Hugging Face models via vocabulary trimming.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Slovo: Russian Sign Language Dataset and Models

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

💫 Industrial-strength Natural Language Processing (NLP) in Python

NLTK Source

Semi-Supervised Learning, Object Detection, ICCV2021

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

Human pose estimation within one line

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"

LAVIS - A One-stop Library for Language-Vision Intelligence