Papers Scene Graph Generation
“Scene Graph Generation” 태그가 달린 논문 365편 · 필터 해제
Contextual Associated Triplet Queries for Panoptic Scene Graph Generation
The Panoptic Scene Graph generation (PSG) task aims to extract the triplets composed of subject, object, and relation based on panoptic segmentation. For one-stage methods, PSGTR predicts the subject, object, and relatio…
Graph GenerationObjectPanoptic Scene Graph GenerationPanoptic Segmentation+3CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning
3D Scene Graph Generation (3DSGG) aims to classify objects and their predicates within 3D point cloud scenes. However current 3DSGG methods struggle with two main challenges. 1) The dependency on labor-intensive grou…
3d scene graph generationContrastive LearningGraph GenerationScene Graph GenerationALF: Adaptive Label Finetuning for Scene Graph Generation
Scene Graph Generation (SGG) endeavors to predict the relationships between subjects and objects in a given image. Nevertheless, the long-tail distribution of relations often leads to biased prediction on coarse labels, …
Graph GenerationRelationScene Graph GenerationUnbiased Scene Graph GenerationIndoor and Outdoor 3D Scene Graph Generation via Language-Enabled Spatial Ontologies
This paper proposes an approach to build 3D scene graphs in arbitrary indoor and outdoor environments. Such extension is challenging; the hierarchy of concepts that describe an outdoor environment is more complex than fo…
3d scene graph generationgraph constructionGraph GenerationLanguage Modelling+4GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives
Training Scene Graph Generation (SGG) models with natural language captions has become increasingly popular due to the abundant, cost-effective, and open-world generalization supervision signals that natural language off…
Graph GenerationLanguage ModellingLarge Language ModelScene Graph Generation+1HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
Visual interactivity understanding within visual scenes presents a significant challenge in computer vision. Existing methods focus on complex interactivities while leveraging a simple relationship model. These methods, …
DiversityGraph GenerationPositionRelation+2Panoptic Video Scene Graph Generation
Towards building comprehensive real-world visual perception systems, we propose and study a new problem called panoptic scene graph generation (PVSG). PVSG relates to the existing video scene graph generation (VidSGG) pr…
Graph GenerationPanoptic Scene Graph GenerationPanoptic SegmentationScene Graph Generation+4HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos
Group Activity Scene Graph (GASG) generation is a challenging task in computer vision, aiming to anticipate and describe relationships between subjects and objects in video sequences. Traditional Video Scene Graph Genera…
Graph GenerationScene Graph GenerationScene UnderstandingVideo scene graph generationVLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation
Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects. However, the long-tail problem among relations lead…
Graph GenerationPanoptic Scene Graph GenerationRelationRelation Prediction+1Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge
This work introduces an enhanced approach to generating scene graphs by incorporating both a relationship hierarchy and commonsense knowledge. Specifically, we begin by proposing a hierarchical relation head that exploit…
Large Language ModelMultimodal Deep LearningPredicate ClassificationRelation+4Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention
Scene Graph Generation (SGG) offers a structured representation critical in many computer vision applications. Traditional SGG approaches, however, are limited by a closed-set assumption, restricting their ability to rec…
Concept AlignmentGraph GenerationKnowledge DistillationObject+6Two Stream Scene Understanding on Graph Embedding
The paper presents a novel two-stream network architecture for enhancing scene understanding in computer vision. This architecture utilizes a graph feature stream and an image feature stream, aiming to merge the strength…
Graph AttentionGraph EmbeddingGraph Generationimage-classification+3NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment
Neuro-symbolic hybrid approaches are inevitable for seamless high-level understanding and reasoning about visual scenes. Scene Graph Generation (SGG) is a symbolic image representation approach based on deep neural netwo…
Caption GenerationCommon Sense ReasoningGraph GenerationImage Captioning+7Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection
Scene graph generation (SGG) and human-object interaction (HOI) detection are two important visual tasks aiming at localising and recognising relationships between objects, and interactions between humans and objects, re…
Graph GenerationHuman-Object Interaction DetectionObjectRelation+1Semantic Scene Graph Generation Based on an Edge Dual Scene Graph and Message Passing Neural Network
Along with generative AI, interest in scene graph generation (SGG), which comprehensively captures the relationships and interactions between objects in an image and creates a structured graph-based representation, has s…
Graph GenerationRelationScene Graph GenerationFloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing
Dynamic scene graph generation (SGG) from videos requires not only a comprehensive understanding of objects across scenes but also a method to capture the temporal motions and interactions with different objects. Moreove…
Graph GenerationScene Graph GenerationUnbiased Scene Graph GenerationVidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools
Building models that comprehends videos and responds specific user instructions is a practical and challenging topic, as it requires mastery of both vision understanding and knowledge reasoning. Compared to language and …
Caption GenerationDescriptiveGraph GenerationScene Graph Generation+1LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this regard, studies on WSSGG have utilized …
Few-Shot LearningLarge Language ModelScene Graph GenerationTriplet+1TextPSG: Panoptic Scene Graph Generation from Textual Descriptions
Panoptic Scene Graph has recently been proposed for comprehensive scene understanding. However, previous works adopt a fully-supervised learning manner, requiring large amounts of pixel-wise densely-annotated data, which…
Graph GenerationPanoptic Scene Graph GenerationScene Graph GenerationScene UnderstandingDomain-wise Invariant Learning for Panoptic Scene Graph Generation
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates). However, the presence of biased predicate annotations poses a significant chal…
Graph GenerationPanoptic Scene Graph GenerationScene Graph Generation