AIMC Journal:
IEEE transactions on pattern analysis and machine intelligence

Showing 211 to 220 of 300 articles

Deep Differentiable Random Forests for Age Estimation.

IEEE transactions on pattern analysis and machine intelligence Jan 8, 2021
Age estimation from facial images is typically cast as a label distribution learning or regression problem, since aging is a gradual progress. Its main challenge is the facial feature space w.r.t. ages is inhomogeneous, due to the large variation in ...
Learning Face Neural Networks, Computer Algorithms
View on PubMed DOI

Revisiting Video Saliency Prediction in the Deep Learning Era.

IEEE transactions on pattern analysis and machine intelligence Dec 4, 2020
Predicting where people look in static scenes, a.k.a visual saliency, has received significant research interest recently. However, relatively less effort has been spent in understanding and modeling visual attention over dynamic scenes. This work ma...
Algorithms Deep Learning Humans
View on PubMed DOI

Towards Safe Weakly Supervised Learning.

IEEE transactions on pattern analysis and machine intelligence Dec 4, 2020
In this paper, we study weakly supervised learning where a large amount of data supervision is not accessible. This includes i) incomplete supervision, where only a small subset of labels is given, such as semi-supervised learning and domain adaptati...
Algorithms Supervised Machine Learning
View on PubMed DOI

Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning.

IEEE transactions on pattern analysis and machine intelligence Nov 3, 2020
In this paper, the problem of describing visual contents of a video sequence with natural language is addressed. Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstru...
Algorithms Image Processing, Computer-Assisted Video Recording Humans Machine Learning
View on PubMed DOI

Gravitational Laws of Focus of Attention.

IEEE transactions on pattern analysis and machine intelligence Nov 3, 2020
The understanding of the mechanisms behind focus of attention in a visual scene is a problem of great interest in visual perception and computer vision. In this paper, we describe a model of scanpath as a dynamic process which can be interpreted as a...
Algorithms Eye Movements Machine Learning Attention Gravitation Image Processing, Computer-Assisted Models, Statistical Humans Fixation, Ocular
View on PubMed DOI

Guided Attention Inference Network.

IEEE transactions on pattern analysis and machine intelligence Nov 3, 2020
With only coarse labels, weakly supervised learning typically uses top-down attention maps generated by back-propagating gradients as priors for tasks such as object localization and semantic segmentation. While these attention maps are intuitive and...
Supervised Machine Learning Semantics Neural Networks, Computer Pattern Recognition, Automated Image Processing, Computer-Assisted
View on PubMed DOI

Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification.

IEEE transactions on pattern analysis and machine intelligence Jul 15, 2019
Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences i...
Biometric Identification Deep Learning Image Processing, Computer-Assisted Video Recording Pattern Recognition, Automated Humans Databases, Factual
View on PubMed DOI

Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences.

IEEE transactions on pattern analysis and machine intelligence Jun 6, 2019
Statistical models of the human body surface are generally learned from thousands of high-quality 3D scans in predefined poses to cover the wide variety of human body shapes and articulations. Acquisition of such data requires expensive equipment, ca...
Imaging, Three-Dimensional Posture Models, Statistical Models, Biological Humans Male Movement Female Machine Learning Infant
View on PubMed DOI

Robust RGB-D Face Recognition Using Attribute-Aware Loss.

IEEE transactions on pattern analysis and machine intelligence May 27, 2019
Existing convolutional neural network (CNN) based face recognition algorithms typically learn a discriminative feature mapping, using a loss function that enforces separation of features from different classes and/or aggregation of features within th...
Neural Networks, Computer Female Humans Automated Facial Recognition Male Algorithms Face
View on PubMed DOI

Recomputation of the Dense Layers for Performance Improvement of DCNN.

IEEE transactions on pattern analysis and machine intelligence May 20, 2019
Gradient descent optimization of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing other learning strategies in the training process of the DCNN has rarely been explored by the deep learning (DL...
Algorithms Databases, Factual Neural Networks, Computer Deep Learning Image Processing, Computer-Assisted
View on PubMed DOI
Popular Topics
Popular Journals