Standard approaches for video action recognition usually operate on full input videos, which
is inefficient due to the widespread spatio-temporal redundancy in videos. The recent …

The long-term action in untrimmed video generally contains multiple sub-actions, among
which various semantic patterns exist (eg, the co-occurrence or sequentiality between sub …

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object
detector together with a Vision Transformer (ViT) backbone network to derive object and …

In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-
up (object) information, a new frame sampling policy and a gating mechanism is proposed …

Action recognition provides an application for human action classification utilizing datasets
captured by various sensor cameras. However, how to capture the key semantic features …

Recognizing video actions in the wild is challenging for visual control systems. In-the-wild
videos show actions not seen in training data, recorded from various angles and scenes with …

Despite the great progresses achieved by commonly-used 3D CNNs and two-stream
methods in action recognition, they cause heavy computational burden which are inefficient …