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 VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot
video and text understanding, without using any labels on downstream tasks. VideoCLIP …

In this paper, we introduce ActBERT for self-supervised learning of joint video-text
representations from unlabeled data. First, we leverage global action information to catalyze …

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-
KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M …

With the recent success of the pre-training technique for NLP and image-linguistic tasks,
some video-linguistic pre-training works are gradually developed to improve video-text …

Contrastive learning has been widely used to train transformer-based vision-language
models for video-text alignment and multi-modal representation learning. This paper …

This paper introduces a unified framework for video action segmentation via sequence to
sequence (seq2seq) translation in a fully and timestamp supervised setup. In contrast to …

Difficulty in collecting and annotating large-scale video data raises a growing interest in
learning models which can recognize novel classes with only a few training examples. In …

We present a simplified, task-agnostic multi-modal pre-training approach that can accept
either video or text input, or both for a variety of end tasks. Existing pre-training are task …

There are substantial instruction videos on the Internet, which enables us to acquire
knowledge for completing various tasks. However, most existing datasets for instruction …