Visual Relationship Detection
36 papers with code • 5 benchmarks • 5 datasets
Visual relationship detection (VRD) is one newly developed computer vision task aiming to recognize relations or interactions between objects in an image. It is a further learning task after object recognition and is essential for fully understanding images, even the visual world.
Benchmarks
These leaderboards are used to track progress in Visual Relationship Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Visual Genome
VRD
Open Images V7
Visual Relationship Detection Dataset
TexRel
Most implemented papers
Visualization of Contributions to Open-Source Projects
We want to analyze visually, to what extend team members and external developers contribute to open-source projects.
LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos
praneeth11009/LIGHTEN-Learning-Interactions-with-Graphs-and-Hierarchical-TEmporal-Networks-for-HOI
•
•
Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video.
Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship Detection
deeplab-ai/grounding-consistent-vrd
•
•
ICCV 2021
Scene Graph Generators (SGGs) are models that, given an image, build a directed graph where each edge represents a predicted subject predicate object triplet.
RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
Vision-CAIR/RelTransformer
•
•
CVPR 2022
This paper shows that modeling an effective message-passing flow through an attention mechanism can be critical to tackling the compositionality and long-tail challenges in VRR.
2.5D Visual Relationship Detection
To enable progress on this task, we create a new dataset consisting of 220k human-annotated 2. 5D relationships among 512K objects from 11K images.
Recovering the Unbiased Scene Graphs from the Biased Ones
coldmanck/recovering-unbiased-scene-graphs
•
•
Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation.
Image Scene Graph Generation (SGG) Benchmark
microsoft/scene_graph_benchmark
•
•
There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection.
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
thunlp/pevl
•
•
We show that PEVL enables state-of-the-art performance of detector-free VLP models on position-sensitive tasks such as referring expression comprehension and phrase grounding, and also improves the performance on position-insensitive tasks with grounded inputs.
Neural Message Passing for Visual Relationship Detection
phyllish/nmp
•
•
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
