期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (9)
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detec......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (10)
As an emerging imaging modality, transient imaging that records the transient information of light transport has significantly shaped our understandin......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (5)
Multi-way or tensor data analysis has attracted increasing attention recently, with many important applications in practice. This article develops a t......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (6)
This paper presents regional attraction of line segment maps, and hereby poses the problem of line segment detection (LSD) as a problem of region colo......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (8)
Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (9)
Automated machine learning (AutoML) has achieved remarkable progress on various tasks, which is attributed to its minimal involvement of manual featur......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (9)
One-shot neural architecture search (NAS) has recently become mainstream in the NAS community because it significantly improves computational efficien......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (5)
We present a structure-from-motion (SfM) framework based on a special type of multi-perspective camera called the cross-slit or XSlit camera. Traditio......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (6)
Despite the promising results, tensor robust principal component analysis (TRPCA), which aims to recover underlying low-rank structure of clean tensor......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (10)
Despite significant effort and notable success of neural style transfer, it remains challenging for highly abstract styles, in particular line drawing......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (10)
Traditional video compression approaches build upon the hybrid coding framework with motion-compensated prediction and residual transform coding. In t......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (8)
Estimating depth from multi-view images captured by a localized monocular camera is an essential task in computer vision and robotics. In this study, ......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (10)
This paper addresses the problem of multiple graph matching (MGM) by considering both offline batch mode and online setting. We explore the concept of......
期刊: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021; 43 (10)
In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust a......