Lists (4)
Sort Name ascending (A-Z)
Stars
A large scale video database for violence detection, which has 2,000 video clips containing violent or non-violent behaviours.
This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point or box annotation.
[CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans
Official Implement of ICCV 2019 oral paper Bayesian Loss for Crowd Count Estimation with Point Supervision
official implementation of the CVPR21 paper "A Generalized Loss Function for Crowd Counting and Localization"
Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything
(CVPR 2024) Point, Segment and Count: A Generalized Framework for Object Counting
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
Recent weakly supervised semantic segmentation paper
This is the pytorch implement of our paper "RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model"
[ICML 2024] Official repository of the paper: "Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset"
Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Effortless data labeling with AI support from Segment Anything and other awesome models.
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
CLAIRify: Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting
Training Faster R-CNN on ADD256 (Embrapa Apples by Drones Detection Dataset)
Implementation of the deepmind Flamingo vision-language model, based on Hugging Face language models and ready for training
An open-source framework for training large multimodal models.
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
[CVPR2021 Oral] FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation.
https://progress.eecs.umich.edu/projects/clearpose/
Recent LLM-based CV and related works. Welcome to comment/contribute!
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks