With the advent of deep learning, many dense prediction tasks, ie, tasks that produce pixel-
level predictions, have seen significant performance improvements. The typical approach is …

In this paper, we introduce a novel visual representation learning which relies on a handful
of adaptively learned tokens, and which is applicable to both image and video …

Recent years have seen remarkable advances in visual understanding. However, how to
understand a story-based long video with artistic styles, eg movie, remains challenging. In …

In this paper, we introduce a novel visual representation learning which relies on a handful
of adaptively learned tokens, and which is applicable to both image and video …

Neighboring frames are more correlated compared to frames from further temporal
distances. In this paper, we aim to explore the temporal correlations among neighboring …

How can we collect and use a video dataset to further improve spatiotemporal 3D
Convolutional Neural Networks (3D CNNs)? In order to positively answer this open question …

Despite the recent progress in deep learning, most approaches still go for a silo-like
solution, focusing on learning each task in isolation: training a separate neural network for …

Learning to represent videos is a very challenging task both algorithmically and
computationally. Standard video CNN architectures have been designed by directly …

Human activity recognition is an emerging and important area in computer vision which
seeks to determine the activity an individual or group of individuals are performing. The …

Interactions between people are often governed by their relationships. On the flip side,
social relationships are built upon several interactions. Two strangers are more likely to …