Search Results for author:
Found 4 papers, 0 papers with code
Player Identification in Hockey Broadcast Videos
We propose an end-to-end trainable ResNet+LSTM network, with a residual network (ResNet) base and a long short-term memory (LSTM) layer, to discover spatio-temporal features of jersey numbers over time and learn long-term dependencies.
Video Anomaly Detection and Localization via Gaussian Mixture Fully Convolutional Variational Autoencoder
The method is based on Gaussian Mixture Variational Autoencoder, which can learn feature representations of the normal samples as a Gaussian Mixture Model trained using deep learning.
Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained "Hard Faces"
The second stage is a Boosted Forests classifier, which utilizes deep facial features pooled from inside the candidate face regions as well as deep contextual features pooled from a larger region surrounding the candidate face regions.
Online Dominant and Anomalous Behavior Detection in Videos
We do not employ any models of the entities in the scene in order to detect these two kinds of behaviors.
