Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

A playbook for systematically maximizing the performance of deep learning models.

Mask-Free Video Instance Segmentation [CVPR 2023]

Official implementation of OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

A high-throughput and memory-efficient inference and serving engine for LLMs

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

This repository is a fork of https://github.com/joslefaure/HIT customized for the AVA dataset

Multi-modal Prompting for Open-vocabulary Video Visual Relationship Detection(AAAI2024)

This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]

Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

[NeurIPS 2023] Self-Chained Image-Language Model for Video Localization and Question Answering

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Authors official PyTorch implementation of the "ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning" [ICCV 2019]

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

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

This repository contains the source code for the paper First Order Motion Model for Image Animation

Official PyTorch implementation of the paper "Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring"

State-of-the-art 2D and 3D Face Analysis Project

S3D Text-Video model trained on HowTo100M using MIL-NCE

Simple code for generating a color-coded latex table from raw data

Code for the paper "Spot What Matters: Learning Context Using Graph Convolutional Networks for Weakly-Supervised Action Detection"