Haoran Duan's Projects
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
[ICLR2024] GTA: A Geometry-Aware Attention Mechanism for Multiview Transformers
A guidance language for controlling large language models.
Free course that takes you from zero to Reinforcement Learning PRO π¦Έπ»βπ¦Έπ½
Config files for my GitHub profile.
Pytorch Human Activity Recognition based on wearable sensors
Mobile manipulation research tools for roboticists
(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"
A simple HTML visualization tool for computer vision research :hammer_and_wrench:
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
Make ID photo right in the browser.
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
Im2Flow: Motion Hallucination from Static Images for Action Recognition (CVPR 2018)
Using Adversarial Networks to Generate Faces from Depth Maps
Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.
ImageBind One Embedding Space to Bind Them All
This is an official Pytorch implementation of "Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach, CVPR 2020".
An AI code interpreter for sensitive data, powered by GPT-4 or Llama 2.
Inpaint anything using Segment Anything and inpainting models.
Query GPT in any input area.
Face Recognition Project on MXNet
InstantID : Zero-shot Identity-Preserving Generation in Seconds π₯
Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
InternGPT / InternChat allows you to interact with ChatGPT by clicking, dragging and drawing using a pointing device.
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Implementation of basic algorithm of machine learning using matlab or python
Code for intrusion detection system development using machine learning algorithms (Decision tree, random forest, extra trees, XGBoost, stacking, k-means, Bayesian optimization..)