Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

Most natural videos contain numerous events. For example, in a video of a" man playing a
piano", the video might also contain" another man dancing" or" a crowd clap**". We …

Adversarial learning has been successfully embedded into deep networks to learn
transferable features, which reduce distribution discrepancy between the source and target …

In this work we introduce a fully end-to-end approach for action detection in videos that
learns to directly predict the temporal bounds of actions. Our intuition is that the process of …

We present a multi-stream bi-directional recurrent neural network for fine-grained action
detection. Recently, two-stream convolutional neural networks (CNNs) trained on stacked …

This work targets human action recognition in video. While recent methods typically
represent actions by statistics of local video features, here we argue for the importance of a …

In this work we improve training of temporal deep models to better learn activity progression
for activity detection and early detection. Conventionally, when training a Recurrent Neural …

Every moment counts in action recognition. A comprehensive understanding of human
activity in video requires labeling every frame according to the actions occurring, placing …

With advances in data-driven machine learning research, a wide variety of prediction
models have been proposed to capture spatio-temporal features for the analysis of video …

Joint segmentation and classification of fine-grained actions is important for applications of
human-robot interaction, video surveillance, and human skill evaluation. However, despite …