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 …

Understanding human behavior and activity facilitates advancement of numerous real-world
applications, and is critical for video analysis. Despite the progress of action recognition …

Assembly101 is a new procedural activity dataset featuring 4321 videos of people
assembling and disassembling 101" take-apart" toy vehicles. Participants work without fixed …

Learning text-video embeddings usually requires a dataset of video clips with manually
provided captions. However, such datasets are expensive and time consuming to create and …

We introduce a self-supervised representation learning method based on the task of
temporal alignment between videos. The method trains a network using temporal cycle …

Medical image analysis has two important research areas: disease grading and fine-grained
lesion segmentation. Although the former problem often relies on the latter, the two are …

In this paper we investigate learning visual models for the steps of ordinary tasks using weak
supervision via instructional narrations and an ordered list of steps instead of strong …

Future prediction, especially in long-range videos, requires reasoning from current and past
observations. In this work, we address questions of temporal extent, scaling, and level of …

Temporal relations among multiple action segments play an important role in action
segmentation especially when observations are limited (eg, actions are occluded by other …

YouTube users looking for instructions for a specific task may spend a long time browsing
content trying to find the right video that matches their needs. Creating a visual summary …