Temporal action segmentation (TAS) in videos aims at densely identifying video frames in
minutes-long videos with multiple action classes. As a long-range video understanding task …

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

This paper presents a 2D skeleton-based action segmentation method with applications in
fine-grained human activity recognition. In contrast with state-of-the-art methods which …

This paper presents a simple yet effective approach for the poorly investigated task of global
action segmentation, aiming at grou** frames capturing the same action across videos of …

This paper presents a self-supervised temporal video alignment framework which is useful
for several fine-grained human activity understanding applications. In contrast with the state …

This paper introduces TemporalVLM, a video large language model capable of effective
temporal reasoning and fine-grained understanding in long videos. At the core, our …

In this work, we address unsupervised temporal action segmentation, which segments a set
of long, untrimmed videos into semantically meaningful segments that are consistent across …

A common challenge in Computer Vision is applying algorithms developed on controlled
datasets to real-world problems, where videos are unscripted or uncontrolled. This …

This dissertation presents a novel approach for action segmentation, the task of recognizing
and segmenting in time atomic actions across videos of a given goal-oriented activity. Our …