Multimodal Sparse Coding for Event Detection

Autor:	Gwon, Youngjune, Campbell, William, Brady, Kevin, Sturim, Douglas, Cha, Miriam, Kung, H. T.
Rok vydání:	2016
Předmět:	Computer Science - Learning Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Unsupervised feature learning methods have proven effective for classification tasks based on a single modality. We present multimodal sparse coding for learning feature representations shared across multiple modalities. The shared representations are applied to multimedia event detection (MED) and evaluated in comparison to unimodal counterparts, as well as other feature learning methods such as GMM supervectors and sparse RBM. We report the cross-validated classification accuracy and mean average precision of the MED system trained on features learned from our unimodal and multimodal settings for a subset of the TRECVID MED 2014 dataset. Comment: Multimodal Machine Learning Workshop at NIPS 2015
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1605.05212 Zobrazit plný text záznamu View this record from Arxiv