Related papers: Learning Comprehensive Motion Representation for A…
Skeleton-based action recognition has garnered significant attention due to the utilization of concise and resilient skeletons. Nevertheless, the absence of detailed body information in skeletons restricts performance, while other…
Action recognition with 3D skeleton sequences is becoming popular due to its speed and robustness. The recently proposed Convolutional Neural Networks (CNN) based methods have shown good performance in learning spatio-temporal…
Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference…
In light of the success of contrastive learning in the image domain, current self-supervised video representation learning methods usually employ contrastive loss to facilitate video representation learning. When naively pulling two…
Human action recognition has become one of the most active field of research in computer vision due to its wide range of applications, like surveillance, medical, industrial environments, smart homes, among others. Recently, deep learning…
One central question for video action recognition is how to model motion. In this paper, we present hierarchical contrastive motion learning, a new self-supervised learning framework to extract effective motion representations from raw…
Fine-grained action recognition is a challenging task in computer vision. As fine-grained datasets have small inter-class variations in spatial and temporal space, fine-grained action recognition model requires good temporal reasoning and…
Considering the close connection between action recognition and human pose estimation, we design a Collaboratively Self-supervised Video Representation (CSVR) learning framework specific to action recognition by jointly factoring in…
This chapter aims to aid the development of Cyber-Physical Systems (CPS) in automated understanding of events and activities in various applications of video-surveillance. These events are mostly captured by drones, CCTVs or novice and…
Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN). In this paper, we propose a novel convolutional neural networks (CNN) based framework for both action…
We study the video super-resolution (SR) problem for facilitating video analytics tasks, e.g. action recognition, instead of for visual quality. The popular action recognition methods based on convolutional networks, exemplified by…
Video activity recognition has become increasingly important in robots and embodied AI. Recognizing continuous video activities poses considerable challenges due to the fast expansion of streaming video, which contains multi-scale and…
Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and…
Video understanding usually requires expensive computation that prohibits its deployment, yet videos contain significant spatiotemporal redundancy that can be exploited. In particular, operating directly on the motion vectors and residuals…
Feature tracking Cardiac Magnetic Resonance (CMR) has recently emerged as an area of interest for quantification of regional cardiac function from balanced, steady state free precession (SSFP) cine sequences. However, currently available…
Action recognition is computationally expensive. In this paper, we address the problem of frame selection to improve the accuracy of action recognition. In particular, we show that selecting good frames helps in action recognition…
Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents for learning video features. However, learning video…
This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition. In contrast with state-of-the-art methods which directly take sequences of 3D skeleton coordinates as inputs…
Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them.…
Motivation: Recognizing human actions in a video is a challenging task which has applications in various fields. Previous works in this area have either used images from a 2D or 3D camera. Few have used the idea that human actions can be…