61 citations · 174 across the 62 of their papers we have counts for
5 papers · 1 filter
Convolutional STN for Weakly Supervised Object Localization
Akhil Meethal, Marco Pedersoli, Soufiane Belharbi +1
Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance. State-of-the-art methods recycle the…
Emotion Recognition with Spatial Attention and Temporal Softmax Pooling
Masih Aminbeidokhti, Marco Pedersoli, Patrick Cardinal +1
Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to…
Adversarial Learning of General Transformations for Data Augmentation
Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed +1
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heur…
Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition
Juan D. S. Ortega, Mohammed Senoussaoui, Eric Granger +3
This paper presents a novel deep neural network (DNN) for multimodal fusion of audio, video and text modalities for emotion recognition. The proposed DNN architecture has independe…
Progressive Gradient Pruning for Classification, Detection and DomainAdaptation
Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran +2
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks…