Implicit embedding based multi modal attention network for Cricket video summarization

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 148, P. 110428 - 110428

Published: March 6, 2025

Language: Английский

---

Incorporating Symmetric Smooth Regularizations into Sparse Logistic Regression for Classification and Feature Extraction

Symmetry, Journal Year: 2025, Volume and Issue: 17(2), P. 151 - 151

Published: Jan. 21, 2025

This paper introduces logistic regression with sparse and smooth regularizations (LR-SS), a novel framework that simultaneously enhances both classification feature extraction capabilities of standard regression. By incorporating family symmetric smoothness constraints into regression, LR-SS uniquely preserves underlying structures inherent in structured data, distinguishing it from existing approaches. Within the minorization–maximization (MM) framework, we develop an efficient optimization algorithm combines coordinate descent soft-thresholding techniques. Through extensive experiments on simulated real-world datasets, including time series image demonstrate significantly outperforms conventional tasks while providing more interpretable extraction. The results highlight LR-SS’s ability to leverage for capturing intrinsic data structures, making particularly valuable machine learning applications requiring predictive accuracy model interpretability.

Language: Английский

---

Solution of Bin Packing Instances in Falkenauer T Class: Not So Hard

Algorithms, Journal Year: 2025, Volume and Issue: 18(2), P. 115 - 115

Published: Feb. 19, 2025

In this work, the Bin Packing combinatorial optimization problem is studied from practical side. The focus on Falkenauer T benchmark class, which a collection of 80 instances that are considered hard to handle algorithmically. Contrary widely accepted view, we show class can be solved relatively easily, without applying any sophisticated methods like metaheuristics. A new algorithm proposed, operate in two modes: either using backtrack or local search find optimal packing. theory, both operating modes guaranteed solution. Computational results all total 1.18 s and 2.39 with alone, 0.2 when running parallel.

Language: Английский

---

Pursuit–Evasion Game Theoretic Decision Making for Collision Avoidance in Automated Vehicles

Dynamic Games and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 7, 2025

Language: Английский

---

An off-policy deep reinforcement learning-based active learning for crime scene investigation image classification

Information Sciences, Journal Year: 2025, Volume and Issue: unknown, P. 122074 - 122074

Published: March 1, 2025

Language: Английский

---