Egocentric vision (aka first-person vision–FPV) applications have thrived over the past few
years, thanks to the availability of affordable wearable cameras and large annotated …

Over the past few years, research on animal pose estimation in computer vision field has
grown in many aspects such as 2D and 3D pose estimation, 3D mesh reconstruction, and …

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor
triggers in DNNs by poisoning training data. A backdoored model behaves normally on …

This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions
(AVA). The AVA dataset densely annotates 80 atomic visual actions in 437 15-minute video …

Weakly-supervised temporal action localization (WS-TAL) aims to localize actions in
untrimmed videos with only video-level labels. Most existing models follow the" localization …

Anomalous events detection in real-world video scenes is a challenging problem due to the
complexity of" anomaly" as well as the cluttered backgrounds, objects and motions in the …

Motion blur from camera shake is a major problem in videos captured by hand-held devices.
Unlike single-image deblurring, video-based approaches can take advantage of the …

The deep two-stream architecture exhibited excellent performance on video based action
recognition. The most computationally expensive step in this approach comes from the …

Real-time video deblurring still remains a challenging task due to the complexity of spatially
and temporally varying blur itself and the requirement of low computational cost. To improve …

In this paper, we propose to guide the video caption generation with Part-of-Speech (POS)
information, based on a gated fusion of multiple representations of input videos. We …