Can Transformers Capture Spatial Relations between Objects?
원문 초록
Spatial relationships between objects represent key scene information for humans to understand and interact with the world. To study the capability of current computer vision systems to recognize physically grounded spatial relations, we start by proposing precise relation definitions that permit consistently annotating a benchmark dataset. Despite the apparent simplicity of this task relative to others in the recognition literature, we observe that existing approaches perform poorly on this benchmark. We propose new approaches exploiting the long-range attention capabilities of transformers for this task, and evaluating key design principles. We identify a simple "RelatiViT" architecture and demonstrate that it outperforms all current approaches. To our knowledge, this is the first method to convincingly outperform naive baselines on spatial relation prediction in in-the-wild settings. The code and datasets are available in \url{https://sites.google.com/view/spatial-relation}.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis
TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs
Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering
Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models
Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.