Benchmarking protocol for visual localization and detection with natural language queries

Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)

Scaling Object Detection by Transferring Classification Weights

Deep learning for binary classification in Google Colaboratory with >97.5% accuracy on over 108,000 RGB images, including 3,000+ with dogs.

Python dictionary storing object tags for MS-COCO images. Data from 3 different sources (COCO ground truths, VG classifier and Microsoft's VinVL) are availible.

Multimodal Genome Dataset Creation Tool

This repository contains code and dataset splits for the paper "Classification by Attention: Scene Graph Classification with Prior Knowledge"

Convert RGB images of Visual-Genome dataset to Depth Maps.

Improving Visual Relation Detection using Depth Maps (ICPR 2020)

Code for "Learning Canonical Representations for Scene Graph to Image Generation", Herzig & Bar et al., ECCV2020

Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization.

Reproduction of LaVisE: Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention

NeuSyRE: A Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment

[WACV 2025] This is the official implementation of the paper "Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge" in PyTorch.