A Comprehensive Survey of Scene Graphs: Generation and Application

Abstract

Scene graph is a structured representation of a scene that can clearly express the objects, attributes, and relationships between objects in the scene. As computer vision technology continues to develop, people are no longer satisfied with simply detecting and recognizing objects in images; instead, people look forward to a higher level of understanding and reasoning about visual scenes. For example, given an image, we want to not only detect and recognize objects in the image, but also know the relationship between objects (visual relationship detection), and generate a text description (image captioning) based on the image content. Alternatively, we might want the machine to tell us what the little girl in the image is doing (Visual Question Answering (VQA)), or even remove the dog from the image and find similar images (image editing and retrieval), etc. These tasks require a higher level of understanding and reasoning for image vision tasks. The scene graph is just such a powerful tool for scene understanding. Therefore, scene graphs have attracted the attention of a large number of researchers, and related research is often cross-modal, complex, and rapidly developing. However, no relatively systematic survey of scene graphs exists at present. To this end, this survey conducts a comprehensive investigation of the current scene graph research. More specifically, we first summarized the general definition of the scene graph, then conducted a comprehensive and systematic discussion on the generation method of the scene graph (SGG) and the SGG with the aid of prior knowledge. We then investigated the main applications of scene graphs and summarized the most commonly used datasets. Finally, we provide some insights into the future development of scene graphs. We believe this will be a very helpful foundation for future research on scene graphs.

arXiv comment25 pages

References in corpus (35)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Estimation of Word Representations in Vector Space
• Neural Message Passing for Quantum Chemistry
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Conditional Random Fields as Recurrent Neural Networks
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Recurrent Models of Visual Attention
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Object Detection from Video Tubelets with Convolutional Neural Networks
• Pixels to Graphs by Associative Embedding
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Object Detection in Videos with Tubelet Proposal Networks
• PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation
• 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
• Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation
• PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
• Learning to generalize to new compositions in image understanding
• Context-Dependent Diffusion Network for Visual Relationship Detection
• On Support Relations and Semantic Scene Graphs
• From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge
• Unbiased Scene Graph Generation from Biased Training
• An Empirical Study on Leveraging Scene Graphs for Visual Question Answering
• Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators
• Interactive Image Generation Using Scene Graphs
• Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
• Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
• Learning to Detect Human-Object Interactions
• Natural Language Guided Visual Relationship Detection
• Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models
• Using Scene Graph Context to Improve Image Generation
• Scene Graph Generation via Conditional Random Fields
• TPsgtR: Neural-Symbolic Tensor Product Scene-Graph-Triplet Representation for Image Captioning
• Scene Graph based Image Retrieval -- A case study on the CLEVR Dataset
• Dual ResGCN for Balanced Scene GraphGeneration

Cited by in corpus (20)

• A Survey on Visual Transformer
• From SLAM to Situational Awareness: Challenges and Survey
• Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
• PlantoGraphy: Incorporating Iterative Design Process into Generative Artificial Intelligence for Landscape Rendering
• RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states
• Graph Neural Networks in Vision-Language Image Understanding: A Survey
• Artificial Intelligence-based algorithms in medical image scan seg-mentation and intelligent visual-content generation -- a concise overview
• GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and Optimization
• Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space
• A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI
• A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction
• Combining Optimal Path Search With Task-Dependent Learning in a Neural Network
• Information-Theoretic Detection of Bimanual Interactions for Dual-Arm Robot Plan Generation
• HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
• From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Robotics
• Automatic Cause Determination in Road Scene Understanding Using Qualitative Reasoning and Four-Valued Logic
• In-situ Value-aligned Human-Robot Interactions with Physical Constraints
• Implicit Shape Model Trees: Recognition of 3-D Indoor Scenes and Prediction of Object Poses for Mobile Robots