Localize, Assemble, and Predicate: Contextual Object Proposal Embedding for Visual Relation Detection.
Ruihai WuKehan XuChenchen LiuNan ZhuangYadong MuPublished in: AAAI (2020)
Keyphrases
- contextual cues
- object detection
- visual objects
- visual context
- automatic detection
- visual appearance
- detection method
- visual analysis
- spatial relations
- partial occlusion
- visual information
- detection algorithm
- contextual information
- visual properties
- d objects
- detection accuracy
- object detection and pose estimation
- visual features
- false positives
- detection rate
- complex objects
- low level
- visual scene
- bounding box
- false alarms
- object model
- object segmentation
- spatial relationships
- visual data
- object detectors
- first order logic
- cluttered background
- visual input
- contextual knowledge
- anomaly detection
- image retrieval
- moving objects