Official Implementation for ICCV'23 paper Coarse-to-Fine Amodal Segmentation with Shape Prior (C2F-Seg).

Constraint Satisfaction Visual Grounding

[CVPR 2024] Official implementation of the paper "Visual In-context Learning"

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Collection of 2D Datasets for Anatomy Segmentation

Python scripts to download Assembly101 from Google Drive

MASS: Multi-Attentional Semantic Segmentation ofLiDAR Data for Dense Top-View Understanding

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Code for OrthDNNs: Orthogonal Deep Neural Networks

Map (deep learning) model weights between different model implementations.

A framework for annotating 3D meshes using the predictions of a 2D semantic segmentation model.

Universal Tensor Operations in Einstein-Inspired Notation for Python.

Statewide Visual Geolocalization in the Wild (ECCV 2024)

The implementation of NoiseEraSAR in "Skeleton-Based Human Action Recognition with Noisy Labels"

Github repo for referring atomic video action recognition

[ICCV 2023] RLIPv2: Fast Scaling of Relational Language-Image Pre-training

🎥 Python and OpenCV-based scene cut/transition detection program & library.

VMamba: Visual State Space Models，code is based on mamba

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

A curated paper list of awesome skeleton-based action recognition.

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory wh…