Starred repositories
RAG Deploy -> Optimize -> Deploy again. Get high performance RAG service with less effort
[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Try out deep learning models online on Google Colab
This repository walks you through how to Build and Run YOLOv4 Object Detections with Darknet in the Cloud with Google Colab.
Official implementation for "InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition"
LSTM을 활용한 CCTV 절도 이상탐지
Keras Implementation of Video Swin Transformers for 3D Video Modeling
Video Swin Transformer - PyTorch
Automatic Depression Detection: a GRU/ BiLSTM-based Model and An Emotional Audio-Textual Corpus
Detecting depression in a conversation using Convolutional Neral Network
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
Implementation of ViViT: A Video Vision Transformer
This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Keypoint Detection Using Detectron2 and OpenCv.
taemin6697 / Llama-2-ko-7b-Chat-Official-Implementation
Forked from boostcampaitech5/level3_nlp_finalproject-nlp-08사용자가 채팅웹을 통해 자신이 처한 법률적 상황을 제시하면, 입력에 대한 문맥을 모델이 이해하여 가이드라인을 제시하고, 유사한 상황의 판례를 제공합니다.
This repository is used to store the code that uses the combination of mediapipe and yolov5, which realizes the detection of a specific area with yolo around the hand detected by mediapipe
Methods to automate movement-based assessments for infants using video analysis
Easily train a good VC model with voice data <= 10 mins!
Inference and training library for high-quality TTS models.