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 present a new egocentric procedural error dataset containing videos with various types
of errors as well as normal videos and propose a new framework for procedural error …

We study supervised action segmentation whose goal is to predict framewise action labels
of a video. To capture temporal dependencies over long horizons prior works either improve …

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 an unsupervised transformer-based framework for temporal activity
segmentation which leverages not only frame-level cues but also segment-level cues. This …

When data labels are scarce, contrastive learning is often used to learn representations in a
weakly-supervised or unsupervised way. In contrastive learning, not only the learning …

Data replay is a successful incremental learning technique for images. It prevents
catastrophic forgetting by keeping a reservoir of previous data original or synthesized to …

The onset of long-form egocentric datasets such as Ego4D and EPIC-Kitchens presents a
new challenge for the task of Temporal Sentence Grounding (TSG). Compared to traditional …

Weakly-supervised action segmentation is a task of learning to partition a long video into
several action segments where training videos are only accompanied by transcripts …

Human activity recognition (HAR) with wearables is one of the serviceable technologies in
ubiquitous and mobile computing applications. The sliding-window scheme is widely …