Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection.
Nikolaos GkanatsiosVassilis PitsikalisPetros KoutrasAthanasia ZlatintsiPetros MaragosPublished in: ICIP (2019)
Keyphrases
- selective attention
- visual search
- automatic detection
- object detection
- detection method
- human vision
- detection rate
- semi supervised
- thermal images
- detection algorithm
- false alarms
- cross modal
- visual field
- low level
- detection accuracy
- multi modal
- machine learning
- visual analysis
- vector space
- face detection
- pre attentive
- multimodal information
- event detection
- audio visual
- unsupervised learning
- supervised learning
- input image
- high dimensional
- face recognition