Results 31 to 40 of about 427,913 (167)

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

AI
Few-shot fine-grained image classification (FSFGIC) methods refer to the classification of images (e.g., birds, flowers, and airplanes) belonging to different subclasses of the same species by a small number of labeled samples.
Jie Ren, Changmiao Li, Yaohui An, Weichuan Zhang, Changming Sun   +4 more
doaj   +1 more source

GPSR: Gradient-Prior-Based Network for Image Super-Resolution

Applied Sciences, 2023
Recent deep learning has shown great potential in super-resolution (SR) tasks. However, most deep learning-based SR networks are optimized via pixel-level loss (i.e., L1, L2, and MSE), which forces the networks to output the average of all possible ...
Xiancheng Zhu, Detian Huang, Xiaorui Li, Danlin Cai, Daxin Zhu   +4 more
doaj   +1 more source

Feature Representations for Neuromorphic Audio Spike Streams [PDF]

Frontiers in Neuroscience, 2018
ISSN:1662 ...
Anumula, Jithendar, Neil, Daniel, Delbruck, Tobi, Liu, Shih-Chii   +3 more
openaire   +4 more sources

A Multisource Image Matching Method Based on Contrastive Network With Similarity Weighting

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Multisource remote sensing (MRS) image matching can provide more accurate data support for a variety of remote sensing tasks, but the disparities in imaging characteristics among different sensors bring significant challenges for effective image matching.
Zhen Han, Ning Lv, Tao Su, Yoong Choon Chang, Chen Chen   +4 more
doaj   +1 more source

Face Imagery Is Based on Featural Representations [PDF]

Experimental Psychology, 2008
Abstract. The effect of imagery on featural and configural face processing was investigated using blurred and scrambled faces. By means of blurring, featural information is reduced; by scrambling a face into its constituent parts configural information is lost. Twenty-four participants learned ten faces together with the sound of a name.
Lobmaier, Janek S., Mast, Fred W.
openaire   +4 more sources

RST-YOLOv8: An Improved Chip Surface Defect Detection Model Based on YOLOv8

Sensors
Surface defect detection in chips is crucial for ensuring product quality and reliability. This paper addresses the challenge of low identification accuracy in chip surface defect detection, which arises from the similarity of defect characteristics ...
Wenjie Tang, Yangjun Deng, Xu Luo
doaj   +1 more source

Multi‐level cross‐modality learning framework for text‐based person re‐identification

Electronics Letters, 2023
The target of text‐based person re‐identification (Re‐ID) is to retrieve the corresponding image of a person through the given text information. However, due to the homogeneous variety and modality heterogeneity, it is challenging to simultaneously learn
Tinghui Wu, Shuhe Zhang, Dihu Chen, Haifeng Hu   +3 more
doaj   +1 more source

Contrastive-Learning-Based Time-Series Feature Representation for Parcel-Based Crop Mapping Using Incomplete Sentinel-2 Image Sequences

Remote Sensing, 2023
Parcel-based crop classification using multi-temporal satellite optical images plays a vital role in precision agriculture. However, optical image sequences may be incomplete due to the occlusion of clouds and shadows.
Ya’nan Zhou, Yan Wang, Na’na Yan, Li Feng, Yuehong Chen, Tianjun Wu, Jianwei Gao, Xiwang Zhang, Weiwei Zhu   +8 more
doaj   +1 more source

M6AMRFS: Robust Prediction of N6-Methyladenosine Sites With Sequence-Based Features in Multiple Species

Frontiers in Genetics, 2018
As one of the well-studied RNA methylation modifications, N6-methyladenosine (m6A) plays important roles in various biological progresses, such as RNA splicing and degradation, etc.
Xiaoli Qiang, Huangrong Chen, Xiucai Ye, Ran Su, Leyi Wei   +4 more
doaj   +1 more source

Inverse Feature Learning: Feature Learning Based on Representation Learning of Error

IEEE Access, 2020
This paper proposes inverse feature learning (IFL) as a novel supervised feature learning technique that learns a set of high-level features for classification based on an error representation approach. The key contribution of this method is to learn the
Behzad Ghazanfari, Fatemeh Afghah, Mohammadtaghi Hajiaghayi   +2 more
doaj   +1 more source