Related papers: Collaborative Spatio-temporal Feature Learning for…

Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically…

The self-supervised pretraining paradigm has achieved great success in learning 3D action representations for skeleton-based action recognition using contrastive learning. However, learning effective representations for skeleton-based…

Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognition methods have achieved promising performance through the…

Spatio-temporal action detection in videos requires localizing the action both spatially and temporally in the form of an "action tube". Nowadays, most spatio-temporal action detection datasets (e.g. UCF101-24, AVA, DALY) are annotated with…

Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown…

In this paper, we tackle the problem of video alignment, the process of matching the frames of a pair of videos containing similar actions. The main challenge in video alignment is that accurate correspondence should be established despite…

Recognizing human actions in untrimmed videos is an important challenging task. An effective 3D motion representation and a powerful learning model are two key factors influencing recognition performance. In this paper we introduce a new…

The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational…

Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant…

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit…

Video data is with complex temporal dynamics due to various factors such as camera motion, speed variation, and different activities. To effectively capture this diverse motion pattern, this paper presents a new temporal adaptive module…

Facial expressions are one of the most powerful ways for depicting specific patterns in human behavior and describing human emotional state. Despite the impressive advances of affective computing over the last decade, automatic video-based…

In this contribution, a novel spatio-temporal prediction algorithm for video coding is introduced. This algorithm exploits temporal as well as spatial redundancies for effectively predicting the signal to be encoded. To achieve this, the…

The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally,…

As moving objects always draw more attention of human eyes, the temporal motive information is always exploited complementarily with spatial information to detect salient objects in videos. Although efficient tools such as optical flow have…

This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D…

Semantic segmentation in surgical videos has applications in intra-operative guidance, post-operative analytics and surgical education. Segmentation models need to provide accurate and consistent predictions since temporally inconsistent…

Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial…

Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes. It has also been shown that 2D Convolutional Neural Networks (CNNs) tend to be biased toward texture rather than…

A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to…