This paper targets unsupervised skeleton-based action representation learning and
proposes a new Hierarchical Contrast (HiCo) framework. Different from the existing …

Audio and vision are two main modalities in video data. Multimodal learning, especially for
audiovisual learning, has drawn considerable attention recently, which can boost the …

Few-shot video classification (video FSL), which learns classifiers for novel concepts, has
gained increasing attention in the last few years from only a few samples. The existing …

We address the problem of extracting key steps from unlabeled procedural videos,
motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training …

With the rapid growth of social media platforms, the volume of video content on the internet
has increased exponentially. YouTube, the most popular social networking platform …

In this paper, we propose a new task named incremental few-shot action recognition
(IFSAR), which aims to learn new action classes incrementally with limited samples. Existing …

Open set action recognition (OSAR) is a rising research domain that simultaneously
identifies all videos from known classes and rejects videos from unknown classes. Existing …

We introduce Vinci, a real-time embodied smart assistant built upon an egocentric vision-
language model. Designed for deployment on portable devices such as smartphones and …

This paper addresses video highlight detection which aims to select a small subset of frames
according to user's major or special interest. The performances of conventional methods …

We aim to address a new task named few-shot early action prediction (FS-EAP) that learns
classifiers for novel actions from only a few partially observed videos. We argue that the task …