Related papers: Efficient Human Vision Inspired Action Recognition…
Efficiently modeling spatial-temporal information in videos is crucial for action recognition. To achieve this goal, state-of-the-art methods typically employ the convolution operator and the dense interaction modules such as non-local…
In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…
This work explores the performance of a large video understanding foundation model on the downstream task of human fall detection on untrimmed video and leverages a pretrained vision transformer for multi-class action detection, with…
Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed to aggregate fixed temporal ranges of invisible but…
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays. It has high practical impacts for many applications across robotics, security, healthcare,…
Visual saliency, which predicts regions in the field of view that draw the most visual attention, has attracted a lot of interest from researchers. It has already been used in several vision tasks, e.g., image classification, object…
Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal…
While most existing neural image compression (NIC) and neural video compression (NVC) methodologies have achieved remarkable success, their optimization is primarily focused on human visual perception. However, with the rapid development of…
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent…
Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the…
Capturing and processing video is increasingly common as cameras become cheaper to deploy. At the same time, rich video understanding methods have progressed greatly in the last decade. As a result, many organizations now have massive…
Recognizing human actions is fundamentally a spatio-temporal reasoning problem, and should be, at least to some extent, invariant to the appearance of the human and the objects involved. Motivated by this hypothesis, in this work, we take…
Perception and decision-making in high-speed dynamic scenarios remain challenging for current robots. In contrast, humans and animals can rapidly perceive and make decisions in such environments. Taking table tennis as a typical example,…
Event-based data are commonly encountered in edge computing environments where efficiency and low latency are critical. To interface with such data and leverage their rich temporal features, we propose a causal spatiotemporal convolutional…
Many compelling video processing effects can be achieved if per-pixel depth information and 3D camera calibrations are known. However, the success of such methods is highly dependent on the accuracy of this "scene-space" information. We…
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifying the architecture of 2D networks (e.g. by including filters…
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size…
Within the scope of this contribution we propose a novel efficient spatio-temporal prediction algorithm for video coding. The algorithm operates in two stages. First, motion compensation is performed on the block to be predicted in order to…
This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…