Visual Tracking Based on Discriminative Compressed Features by Wei Liu, Hui Wang

“…In this paper, we propose a novel visual tracking method, which uses compressed features to model target’s appearances and then uses SVM to distinguish the target from its background. …”
Get full text

Modeling and optimization of dynamic isothermal compressibility features on flowability of Canarium schweinfurthii Engl nutshell powder by James Chinaka Ehiem, Victor Ifeanyichukwu Obiora Ndirika, Udochukwu Nelson Onwuka, Raghavan Vijayan

“…The compressibility features (bulk density, tapped bulk density, porosity, coefficient of compressibility and Hauser ratio) of Canarium schweinfurthii engl. nutshell powder as it affects flowability during densification process were investigated. …”
Get full text

Analysis of archive formats and program solutions for compression of text files by Artem Perepelitsyn, Alona Chepelevych, Andrii Litvinov

“…The subject of study in this article and research is widely used archive formats for file compression, features of their implementation, text compression rates, and the time required for existing programs for different platforms. …”
Get full text

A Super-Resolution-Based Feature Map Compression for Machine-Oriented Video Coding by Jung-Heum Kang, Muhammad Salman Ali, Hye-Won Jeong, Chang-Kyun Choi, Younhee Kim, Se Yoon Jeong, Sung-Ho Bae, Hui Yong Kim

“…Especially, compressing features has advantages in terms of privacy protection and computation off-loading. …”
Get full text

Video tamper detection method based on nonnegative tensor factorization by Xue-li ZHANG, Tian-qiang HUANG, Jing LIN, Wei HUANG

“…The authenticity and integrity of video authentication is one of the important contents in information security field.A video tampering detection method based on non-negative tensor decomposition was proposed for video inter-frame tampering.First of all,spectral feature of video frame was extracted quickly.The video was described by a three-dimensional tensor which created by the main compression feature.The tensor was factorized by Tucker non-negative decomposition method and then the time dimension matrix was extracted to calculate correlation.Finally,the tampering position was determined by using the Chebyshev’s inequality.Experiments show that this method can detect the video inter-frame tampering quickly and robustly.…”
Get full text

Streamflow prediction using artificial neural networks and soil moisture proxies by Robert Edwin Rouse, Doran Khamis, Scott Hosking, Allan McRobie, Emily Shuckburgh

“…In this paper, using data from the Centre for Ecology & Hydrology’s National River Flow Archive and from the European Centre for Medium-Range Weather Forecasts, we present a study that focuses on the input variable set for a neural network streamflow model to demonstrate how certain variables can be internalized, leading to a compressed feature set. By highlighting this capability to learn effectively using proxy variables, we demonstrate a more transferable framework that minimizes sensing requirements and that enables a route toward generalizing models.…”
Get full text

Complex Dynamic Rupture of an Mw5.8 Intermediate‐Depth Earthquake in the Hellenic Slab by F. Gallovič, V. Plicka, Ľ. Valentová, E. Sokos, J. Zahradník

“…We study a 2014 Mw5.8 left‐lateral strike‐slip earthquake originating at a depth of ∼90 km under arc‐parallel compression, featuring a small implosive component of the moment tensor. …”
Get full text

GPR-Based Leakage Reconstruction of Shallow-Buried Water Supply Pipelines Using an Improved UNet++ Network by Qingqi Xu, Qinghua Liu, Shan Ouyang

“…The network employs an encoder–decoder architecture, in which the encoder incorporates multi-scale directional convolutions with coordinate attention to extract and compress features across different scales effectively. …”
Get full text

Transformer-based latency prediction for stream processing task by Zheng Chu, Baozhu Li, Changtian Ying

“…The Auto-encoder is utilized to reduce the dimensionality of the extensive features and generate a compressed feature representation. Subsequently, the Transformer is employed to extract spatio-temporal dependencies and predict the latency of SPTs. …”
Get full text

Fault Diagnosis for Rotating Machinery Based on Convolutional Neural Network and Empirical Mode Decomposition by Yuan Xie, Tao Zhang

“…Frequency spectrum of the signal obtained through fast Fourier transform process is trained in a designed CNN structure to extract compressed features with spatial information. To solve the nonstationary characteristic, we also apply EMD technique to the original vibration signals. …”
Get full text

K0 test and particle flow simulation of coral sands with different gradations by Ruiyuan Zhang, Yongtao Zhang, Peishuai Chen, Fuquan Ji, Huiwu Luo, Yu Zhong, Yu Zhong

“…The displacement field of coral sand with a narrower gradation is revealed to be more prone to exhibit a horizontally stratified compression feature at the meso-scale. The coral sand with a wider gradation exhibits a more obvious gradient distribution of internal contact forces with more uniform directional distribution and better compaction. …”
Get full text

Enhancing Long-Term Flood Forecasting with SageFormer: A Cascaded Dimensionality Reduction Approach Based on Satellite-Derived Data by Fatemeh Ghobadi, Amir Saman Tayerani Charmchi, Doosun Kang

“…SageFormer captures inter- and intra-dependencies within a compressed feature space, making it particularly effective for long-term forecasting. …”
Get full text

Classification Model of Clock Drawing Test Based on Contrastive Learning Using Multi-Channel Features With Channel-Spatial Attention by Changsu Kang, Bohyun Wang, J. S. Lim

“…The pooling layers of a convolutional neural network (CNN) compress features by reducing dimensionality, which tends to focus on a single dominant element. …”
Get full text

A Recommendation Algorithm Incorporating Adaptive Gating Mechanisms and Knowledge Graph Enhancements by Yi Yu, Teng Lv

“…First, GAKR uses a Multilayer Perceptron (MLP) in the recommendation module to process the user’s initial feature vector and extract potentially compressible features. Then, for the item feature vector, the model dynamically adjusts the weights of Collaborative Filtering (CF) and Knowledge Graph (KG) through the gating mechanism, generating a more expressive item representation. …”
Get full text

Latent Space Classification for Cardiovascular Disease Detection: A Deep Convolutional Autoencoder-Based Approach for Telemedicine Applications by G Antoni Gracy, Sheena Christabel Pravin

“…The proposed LSCS encompasses a deep convolutional autoencoder trained on the MIT-BIH arrhythmia database that compresses ECG signals. The compressed features are classified using seven ML models: K-Nearest Neighbors (KNN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Histogram Gradient Boosting Trees (HGBT), and three Support Vector Machine variants (SVML, SVMP, SVMR). …”
Get full text

Stability-Enhanced Ternary Solid Dispersions of Glyburide: Effect of Preparation Method on Physicochemical Properties by Leila Barghi, Afshin Vekalati, Azin Jahangiri

“…Solid dispersions prepared by SE, in addition to increasing the dissolution properties and the possibility of improving the bioavailability of the drug, showed acceptable long-term physical stability with remarkably improved flowability and compressibility features.…”
Get full text

Coronary Artery Disease Detection Based on a Novel Multi-Modal Deep-Coding Method Using ECG and PCG Signals by Chengfa Sun, Changchun Liu, Xinpei Wang, Yuanyuan Liu, Shilong Zhao

“…To remove irrelevant information while preserving discriminative features, we add an autoencoder network to compress feature dimension. Final CAD classification is conducted by combining support vector machine and optimal multi-modal features. …”
Get full text

TCL: Time-Dependent Clustering Loss for Optimizing Post-Training Feature Map Quantization for Partitioned DNNs by Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Irida Shallari, Silvia Krug, Isaac Sanchez Leal, Mattias O'Nils

“…The autoencoder compresses feature maps at the partitioning point before quantization, effectively reducing data size and preserving accuracy. …”
Get full text

GLIHamba: global–local context image harmonization based on Mamba by Jinsheng SUN, Jiao PAN, Yu GUO, Chao YAO

“…In contrast, GFSE compresses features across all spatial dimensions to maintain the overall style consistency of the image. …”
Get full text

Unlocking the potential of digital pathology: Novel baselines for compression by Maximilian Fischer, Peter Neher, Peter Schüffler, Sebastian Ziegler, Shuhan Xiao, Robin Peretzke, David Clunie, Constantin Ulrich, Michael Baumgartner, Alexander Muckenhuber, Silvia Dias Almeida, Michael Gőtz, Jens Kleesiek, Marco Nolden, Rickmer Braren, Klaus Maier-Hein

Get full text