Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Zia, M. Zeeshan"'
Autor:
Hyder, Syed Waleed, Usama, Muhammad, Zafar, Anas, Naufil, Muhammad, Fateh, Fawad Javed, Konin, Andrey, Zia, M. Zeeshan, Tran, Quoc-Huy
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 and apply Gr
Externí odkaz:
http://arxiv.org/abs/2309.06462
Autor:
Tran, Quoc-Huy, Mehmood, Ahmed, Ahmed, Muhammad, Naufil, Muhammad, Zafar, Anas, Konin, Andrey, Zia, M. Zeeshan
This paper presents an unsupervised transformer-based framework for temporal activity segmentation which leverages not only frame-level cues but also segment-level cues. This is in contrast with previous methods which often rely on frame-level inform
Externí odkaz:
http://arxiv.org/abs/2305.19478
Autor:
Tran, Quoc-Huy, Ahmed, Muhammad, Popattia, Murad, Ahmed, M. Hassan, Konin, Andrey, Zia, M. Zeeshan
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 skeleton coordina
Externí odkaz:
http://arxiv.org/abs/2305.19480
Autor:
Khan, Hamza, Haresh, Sanjay, Ahmed, Awais, Siddiqui, Shakeeb, Konin, Andrey, Zia, M. Zeeshan, Tran, Quoc-Huy
We introduce a novel approach for temporal activity segmentation with timestamp supervision. Our main contribution is a graph convolutional network, which is learned in an end-to-end manner to exploit both frame features and connections between neigh
Externí odkaz:
http://arxiv.org/abs/2206.15031
We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where representatio
Externí odkaz:
http://arxiv.org/abs/2105.13353
Inexpensive sensing and computation, as well as insurance innovations, have made smart dashboard cameras ubiquitous. Increasingly, simple model-driven computer vision algorithms focused on lane departures or safe following distances are finding their
Externí odkaz:
http://arxiv.org/abs/2004.05261
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We demonstra
Externí odkaz:
http://arxiv.org/abs/1803.07231
Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both human and m
Externí odkaz:
http://arxiv.org/abs/1801.03399
Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network (CNN) architecture to localize semantic parts in 2D image and 3D spac
Externí odkaz:
http://arxiv.org/abs/1612.02699
Autor:
Zia, M. Zeeshan, Nardi, Luigi, Jack, Andrew, Vespa, Emanuele, Bodin, Bruno, Kelly, Paul H. J., Davison, Andrew J.
SLAM has matured significantly over the past few years, and is beginning to appear in serious commercial products. While new SLAM systems are being proposed at every conference, evaluation is often restricted to qualitative visualizations or accuracy
Externí odkaz:
http://arxiv.org/abs/1509.04648