ScarfNet: Multi-scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection.
Jin Hyeok YooSeongHyeon ParkJun Won ChoiPublished in: CoRR (2019)
Keyphrases
- object detection
- multiscale
- semantic information
- formal semantics
- discriminatively trained
- feature vectors
- feature space
- low level
- support vector machine
- image features
- co occurrence
- feature set
- logic programming
- image representation
- video sequences
- spatial information
- information fusion
- feature extraction
- computer vision