Papers with Code 아카이브
Scene Graph Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 7
- 보존된 평가 기록
- 31
A scene graph is a structured representation of an image, where nodes in a scene graph correspond to object bounding boxes with their object categories, and edges correspond to their pairwise relationships between objects. The task of Scene Graph Generation is to generate a visually-grounded scene graph that most accurately correlates with an image.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools
TextPSG: Panoptic Scene Graph Generation from Textual Descriptions
Domain-wise Invariant Learning for Panoptic Scene Graph Generation
Less is More: Toward Zero-Shot Local Scene Graph Generation via Foundation Models
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Logical Bias Learning for Object Relation Prediction
Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
Predicate Classification Using Optimal Transport Loss in Scene Graph Generation
Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention
STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation
Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction
RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation
Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes
Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding
Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation
RLIPv2: Fast Scaling of Relational Language-Image Pre-training
Vision Relation Transformer for Unbiased Scene Graph Generation
Compositional Feature Augmentation for Unbiased Scene Graph Generation
3D Scene Graph Prediction on Point Clouds Using Knowledge Graphs
Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation
Informative Scene Graph Generation via Debiasing
Generalized Unbiased Scene Graph Generation
Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation
Improving Scene Graph Generation with Superpixel-Based Interaction Learning
Interpretable End-to-End Driving Model for Implicit Scene Understanding
Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Panoptic Scene Graph Generation with Semantics-Prototype Learning
Pair then Relation: Pair-Net for Panoptic Scene Graph Generation
Unbiased Scene Graph Generation via Two-stage Causal Modeling
Open-Vocabulary Object Detection via Scene Graph Discovery
Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection
Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation
On Certified Generalization in Structured Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.