Papers Zero-Shot Scene Graph Generation
“Zero-Shot Scene Graph Generation” 태그가 달린 논문 3편 · 필터 해제
KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation
2025-02-21 · IEEE Transactions on Artificial Intelligence 2025 2
· M. Jaleed Khan, John G. Breslin, Edward Curry
A scene graph is a key image representation in visual reasoning. The generalisability of Scene Graph Generation (SGG) methods is crucial for reliable reasoning and real-world applicability. However, imbalanced training d…
Common Sense ReasoningGraph Generationobject-detectionObject Detection+4Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features
2025-01-01 · CVPR 2025 1
· Wenhuan Huang, Yi Ji, Guiqian Zhu, Li Ying 외
In scene graph generation (SGG), the accurate prediction of unseen triples is essential for its effectiveness in downstream vision-language tasks. We hypothesize that the predicates of unseen triples can be viewed as…
AttributeGraph GenerationScene Graph GenerationZero-Shot Scene Graph GenerationZero-Shot Scene Graph Generation via Triplet Calibration and Reduction
2023-09-07
· Jiankai Li, Yunhong Wang, Weixin Li
Scene Graph Generation (SGG) plays a pivotal role in downstream vision-language tasks. Existing SGG methods typically suffer from poor compositional generalizations on unseen triplets. They are generally trained on incom…
Graph GenerationScene Graph GenerationTripletZero-Shot Scene Graph Generation
1–3 / 3