Results 11 to 20 of about 311,283 (352)
Spatio-Temporal Saliency Networks for Dynamic Saliency Prediction [PDF]
IEEE Transactions on Multimedia, 2018 Computational saliency models for still images have gained significant popularity in recent years. Saliency prediction from videos, on the other hand, has received relatively little interest from the community. Motivated by this, in this work, we study the use of deep learning for dynamic saliency prediction and propose the so-called spatio-temporal ...
Cagdas Bak +3 more
openaire +4 more sources
Anomaly Detection in Natural Scene Images Based on Enhanced Fine-Grained Saliency and Fuzzy Logic
IEEE Access, 2021 This paper proposes a simple yet effective method for anomaly detection in natural scene images improving natural scene text detection and recognition.
Hamam Mokayed +5 more
doaj +1 more source
Saliency Tree: A Novel Saliency Detection Framework [PDF]
IEEE Transactions on Image Processing, 2014 This paper proposes a novel saliency detection framework termed as saliency tree. For effective saliency measurement, the original image is first simplified using adaptive color quantization and region segmentation to partition the image into a set of primitive regions. Then, three measures, i.e., global contrast, spatial sparsity, and object prior are
Liu, Zhi, Zou, Wenbin, Le Meur, Olivier
openaire +4 more sources
Eight-Channel Multispectral Image Database for Saliency Prediction
Sensors, 2021 Saliency prediction is a very important and challenging task within the computer vision community. Many models exist that try to predict the salient regions on a scene from its RGB image values.
Miguel Ángel Martínez-Domingo +2 more
doaj +1 more source
A Unified Transformer Framework for Group-Based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection [PDF]
IEEE transactions on multimedia, 2022 Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. In the computer vision area, many researchers focus on co-segmentation (CoS), co-saliency detection (CoSD) and video salient ...
Yukun Su +4 more
semanticscholar +1 more source
Gaze Mapping for Immersive Virtual Environments Based on Image Retrieval
Frontiers in Virtual Reality, 2022 In this paper, we introduce a novel gaze mapping approach for free viewing conditions in dynamic immersive virtual environments (VEs), which projects recorded eye fixation data of users, who viewed the VE from different perspectives, to the current view.
Tim Rolff +3 more
doaj +1 more source
Proceedings of the 20th annual meeting on Association for Computational Linguistics -, 1982 We argue that in domains where a strong notion of salience can be defined, it can be used to provide: (1) an elegant solution to the selection problem, i.e. the problem of how to decide whether a given fact should or should not be mentioned in the text; and (2) a simple and direct control framework for the entire deep generation process, coordinating ...
E. Jeffrey Conklin, David D. McDonald
openaire +1 more source
XAITK: The explainable AI toolkit
Applied AI Letters, 2021 Recent advances in artificial intelligence (AI), driven mainly by deep neural networks, have yielded remarkable progress in fields, such as computer vision, natural language processing, and reinforcement learning.
Brian Hu +5 more
doaj +1 more source
Pyramid Feature Attention Network for Saliency Detection [PDF]
Computer Vision and Pattern Recognition, 2019 Saliency detection is one of the basic challenges in computer vision. Recently, CNNs are the most widely used and powerful techniques for saliency detection, in which feature maps from different layers are always integrated without distinction.
Ting Zhao, Xiangqian Wu
semanticscholar +1 more source
Information, 2022 The manual observation of sputum smears by fluorescence microscopy for the diagnosis and treatment monitoring of patients with tuberculosis (TB) is a laborious and subjective task.
Marios Zachariou +4 more
doaj +1 more source