Deep Reconstruction Models for Image Set Classification

172 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Video Representation Learning Using Discriminative Pooling (2018, methodology): “Successful methods following this approach are the two-stream models and their extensions [11, 12, 18, 20, 41].”
Deep learning approach for active classification of electrocardiogram signals (2016, background): “, handcrafted features fed as input to a kernel classifier), deep learning has shown outstanding results in many applications such as image classification [23], object recognition [6], face recognition [29], medical image analysis [10], and time series data [16, 24, 36].”
Attention-Aware Deep Reinforcement Learning for Video Face Recognition (2017, unknown): “0 DRM-WV [12] 88.”
Using convolutional features and a sparse autoencoder for land-use scene classification (2016, methodology): “…features fed as input to a kernel classi ﬁ er), deep learning has shown outstanding results in many applications such as image classi ﬁ cation (Hayat, Bennamoun, and An 2015), object recognition (Bai et al. 2015), face recognition (Gao et al. 2015), medical image analysis (Brosch and Tam…”
A Comprehensive Look at Coding Techniques on Riemannian Manifolds (2018, methodology): “For our evaluation, we followed the widely used setup in deep reconstruction models (DRM) [20].”
Pattern Recognition (2015, unknown): “For frame level, we follow the standard protocol used by PASCAL VOC object classes challenge [33] and report the average precision (AP) using an IoU threshold of 0.5.”