[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

High-resolution models for human tasks.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Official Implementation for "SCAPE: A Simple and Strong Category-Agnostic Pose Estimator", ECCV 2024.

Hiera: A fast, powerful, and simple hierarchical vision transformer.

[ECCV 2024] Beyond MOT: Semantic Multi-Object Tracking

This is the code of our paper "Video-Based Human Pose Regression via Decoupled Space-Time Aggregation".

A Visual Studio Code extension with support for the Ruff linter.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

MMPD Dataset from ECCV'2024 "When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset"

This repository contains implementations and illustrative code to accompany DeepMind publications

[ICLR 2024 & ECCV 2024] The All-Seeing Projects: Towards Panoptic Visual Recognition&Understanding and General Relation Comprehension of the Open World"

autoupdate paper list

In CVPR'2024. Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

Code for "LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model", CVPR 2024 Highlight

CAPE using text-graphs

A novel few-shot keypoint detector with uncertainty learning for unseen species (CVPR2022).

MLX: An array framework for Apple silicon

[ECCV2024] Official implementation of paper, "DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs".

The project is an official implementation of our paper "PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation".

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

[ICLR 2024] MogaNet: Efficient Multi-order Gated Aggregation Network

Transparent Image Layer Diffusion using Latent Transparency

[CVPR 2023] Code for PConv and FasterNet

Unofficial implementation of "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" (https://arxiv.org/abs/2103.14030)

This is the official code release for our work, Denoising Vision Transformers.