The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

Skeleton sequence representation learning has shown great advantages for action
recognition due to its promising ability to model human joints and topology. However, the …

We target at the task of weakly-supervised action localization (WSAL), where only video-
level action labels are available during model training. Despite the recent progress, existing …

Procedural activity understanding requires perceiving human actions in terms of a broader
task, where multiple keysteps are performed in sequence across a long video to reach a …

In this paper we tackle the problem of self-supervised video alignment and activity progress
prediction using in-the-wild videos. Our proposed self-supervised representation learning …

We address the problem of online action segmentation for egocentric procedural task
videos. While previous studies have mostly focused on offline action segmentation where …

Instructional videos are an important resource to learn procedural tasks from human
demonstrations. However, the instruction steps in such videos are typically short and sparse …

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet
invariant representations to link them are essential for many potential applications in …

In this work, we consider the problem of sequence-to-sequence alignment for signals
containing outliers. Assuming the absence of outliers, the standard Dynamic Time War** …

Prior works on action representation learning mainly focus on designing various
architectures to extract the global representations for short video clips. In contrast, many …