MDL-CW: A Multimodal Deep Learning Framework with CrossWeights

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2601 - 2609
• Main Authors: Rastegar, Sarah, Baghshah, Mahdieh Soleymani, Rabiee, Hamid R., Shojaee, Seyed Mohsen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Cats; Data models; Dogs; Feature extraction; Machine learning; Random variables; Training

Deep learning has received much attention as of the most powerful approaches for multimodal representation learning in recent years. An ideal model for multimodal data can reason about missing modalities using the available ones, and usually provides more information when multiple modalities are bei...