Understanding human actions in visual data is tied to advances in complementary research
areas including object recognition, human dynamics, domain adaptation and semantic …

In this work, we introduce a new video representation for action classification that
aggregates local convolutional features across the entire spatio-temporal extent of the video …

We present VideoLSTM for end-to-end sequence learning of actions in video. Rather than
adapting the video to the peculiarities of established recurrent or convolutional architectures …

Video classification has achieved remarkable success in recent years, driven by advanced
deep learning models that automatically categorize video content. This paper provides a …

Current methods for video analysis often extract frame-level features using pre-trained
convolutional neural networks (CNNs). Such features are then aggregated over time eg, by …

We introduce the concept of dynamic image, a novel compact representation of videos
useful for video analysis, particularly in combination with convolutional neural networks …

General human action recognition requires understanding of various visual cues. In this
paper, we propose a network architecture that computes and integrates the most important …

Actions are more than just movements and trajectories: we cook to eat and we hold a cup to
drink from it. A thorough understanding of videos requires going beyond appearance …

Deep learning for human action recognition in videos is making significant progress, but is
slowed down by its dependency on expensive manual labeling of large video collections. In …

Video processing and analysis have become an urgent task, as a huge amount of videos
(eg, YouTube, Hulu) are uploaded online every day. The extraction of representative key …