Localize 2D image object detection in 3D Scene with Yolo in Unity Barracuda and ARFoundation.

Attention-based Dropout Layer for Weakly Supervised Object Localization (CVPR 2019 Oral)

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.

Rotation & scale invariant template matching

PyTorch pipeline of MIT Driverless Computer Vision paper(2020)

ECCV24 - Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance

STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning, ICCV, 2023

Code for Look for the Change paper published at CVPR 2022

Our Solution of the Flipkart Grid Challenge

Python scripts for performing object detection with the 1000 labels of the ImageNet dataset in ONNX. The repository combines a class agnostic object localizer to first detect the objects in the image, and next a ResNet50 model trained on ImageNet is used to label each box.

Active object localization ( bounding boxes ) using deep reinforcement learning.

This repository is containing an object classification & localization project for SINGLE object.

Python scripts performing class agnostic object localization using the Object Localization Network model in ONNX.

A mobile robot equipped with a 6-DoF manipulator to pick up different bricks in a partially known environment: kinematics, trajectory planning & control, object localization & classification.

Use your classification neural network for object detection and localization

The iNaturalist Localization Dataset from "On Label Granularity and Object Localization" (ECCV 2022).

Deep learning project using Keras that aims to detect (localize) thyroid lesions on ultrasound scans

Code for the paper "Multi-Task Learning of Object States and State-Modifying Actions from Web Videos" published in TPAMI

This repository contains code and resources for performing object localization and classification using a single network on an Augmented MNIST dataset.

ChangeIt dataset with more than 2600 hours of video with state-changing actions published at CVPR 2022