AIMC Journal:
IEEE transactions on pattern analysis and machine intelligence

Showing 201 to 210 of 300 articles

Multi-Task Head Pose Estimation in-the-Wild.

IEEE transactions on pattern analysis and machine intelligence Jul 1, 2021
We present a deep learning-based multi-task approach for head pose estimation in images. We contribute with a network architecture and training strategy that harness the strong dependencies among face pose, alignment and visibility, to produce a top ...
Neural Networks, Computer Algorithms Image Processing, Computer-Assisted Face
View on PubMed DOI

Multi-Task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition.

IEEE transactions on pattern analysis and machine intelligence Jul 1, 2021
Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately. In this ar...
Humans Software Algorithms Deep Learning
View on PubMed DOI

Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization.

IEEE transactions on pattern analysis and machine intelligence Jul 1, 2021
Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potential for improving representation and generalization abilities of deep C...
Neural Networks, Computer Algorithms Animals Image Processing, Computer-Assisted Pattern Recognition, Automated
View on PubMed DOI

Non-line-of-Sight Imaging via Neural Transient Fields.

IEEE transactions on pattern analysis and machine intelligence Jun 8, 2021
We present a neural modeling framework for non-line-of-sight (NLOS) imaging. Previous solutions have sought to explicitly recover the 3D geometry (e.g., as point clouds) or voxel density (e.g., within a pre-defined volume) of the hidden scene. In con...
Neural Networks, Computer Algorithms Imaging, Three-Dimensional Monte Carlo Method
View on PubMed DOI

BlockQNN: Efficient Block-Wise Neural Network Architecture Generation.

IEEE transactions on pattern analysis and machine intelligence Jun 8, 2021
Convolutional neural networks have gained a remarkable success in computer vision. However, most popular network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generat...
Neural Networks, Computer Algorithms
View on PubMed DOI

Text-Guided Neural Network Training for Image Recognition in Natural Scenes and Medicine.

IEEE transactions on pattern analysis and machine intelligence Apr 1, 2021
Convolutional neural networks (CNNs) are widely recognized as the foundation for machine vision systems. The conventional rule of teaching CNNs to understand images requires training images with human annotated labels, without any additional instruct...
Humans Neural Networks, Computer Algorithms Diagnostic Imaging
View on PubMed DOI

Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification.

IEEE transactions on pattern analysis and machine intelligence Mar 4, 2021
Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep learning neural networks, especially the Convolutional Neural Networks (CNNs). Most of the existing works focused on classif...
Neural Networks, Computer Algorithms Databases, Factual Image Processing, Computer-Assisted
View on PubMed DOI

Orthogonal Deep Neural Networks.

IEEE transactions on pattern analysis and machine intelligence Mar 4, 2021
In this paper, we introduce the algorithms of Orthogonal Deep Neural Networks (OrthDNNs) to connect with recent interest of spectrally regularized deep learning methods. OrthDNNs are theoretically motivated by generalization analysis of modern DNNs, ...
Neural Networks, Computer Algorithms
View on PubMed DOI

Appearance and Pose-Conditioned Human Image Generation Using Deformable GANs.

IEEE transactions on pattern analysis and machine intelligence Mar 4, 2021
In this paper, we address the problem of generating person images conditioned on both pose and appearance information. Specifically, given an image x of a person and a target pose P(x), extracted from an image x, we synthesize a new image of that per...
Humans Neural Networks, Computer Algorithms Image Processing, Computer-Assisted
View on PubMed DOI

Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition.

IEEE transactions on pattern analysis and machine intelligence Feb 4, 2021
In this work, we aim to address the problem of human interaction recognition in videos by exploring the long-term inter-related dynamics among multiple persons. Recently, Long Short-Term Memory (LSTM) has become a popular choice to model individual d...
Humans Neural Networks, Computer Algorithms Motion Recognition, Psychology
View on PubMed DOI
Popular Topics
Popular Journals