Rock image classification based on improved EfficientNet by Kai Bai, Zhaoshuo Zhang, Siyi Jin, Shengsheng Dai

Subjects: Get full text

LiteMP-VTON: A Knowledge-Distilled Diffusion Model for Realistic and Efficient Virtual Try-On by Shufang Zhang, Lei Wang, Wenxin Ding

Get full text

SDPSNet: An Efficient 3D Object Detection Based on Spatial Dynamic Pruning Sparse Convolution and Self-Attention Feature Diffusion by Meng Wang, Qianlei Yu, Haipeng Liu

“…SDPSNet introduces a spatial dynamic pruning sparse convolution strategy to optimise the inference efficiency and data redundancy of the detector. Meanwhile, the self-attention feature diffusion module is used to effectively diffuse the features of the object edges to the central region, providing a richer and more accurate representation for modelling the centre of large objects. …”
Get full text

Enhancing Diffusion-Based Music Generation Performance with LoRA by Seonpyo Kim, Geonhui Kim, Shoki Yagishita, Daewoon Han, Jeonghyeon Im, Yunsick Sung

Get full text

An Efficient and Low-Complexity Transformer-Based Deep Learning Framework for High-Dynamic-Range Image Reconstruction by Josue Lopez-Cabrejos, Thuanne Paixão, Ana Beatriz Alvarez, Diodomiro Baldomero Luque

“…The computational cost indicated that the architecture was significantly more efficient than other Transformer-based approaches for reconstruction. …”
Get full text

An Efficient Weed Detection Method Using Latent Diffusion Transformer for Enhanced Agricultural Image Analysis and Mobile Deployment by Yuzhuo Cui, Yingqiu Yang, Yuqing Xia, Yan Li, Zhaoxi Feng, Shiya Liu, Guangqi Yuan, Chunli Lv

“…This paper presents an efficient weed detection method based on the latent diffusion transformer, aimed at enhancing the accuracy and applicability of agricultural image analysis. …”
Get full text

Cross-attention swin-transformer for detailed segmentation of ancient architectural color patterns by Lv Yongyin, Yu Caixia

“…Traditional approaches, including convolutional neural networks (CNNs) and standard transformer-based models, have achieved significant success; however, they often face challenges in capturing fine-grained details and maintaining efficiency across diverse datasets. These methods struggle with balancing precision and computational efficiency, especially when dealing with complex patterns and high-resolution images.MethodsTo address these limitations, we propose a novel segmentation model that integrates a hierarchical vision transformer backbone with multi-scale self-attention, cascaded attention decoding, and diffusion-based robustness enhancement. …”
Get full text

SADiff: Coronary Artery Segmentation in CT Angiography Using Spatial Attention and Diffusion Model by Ruoxuan Xu, Longhui Dai, Jianru Wang, Lei Zhang, Yuanquan Wang

“…We propose SADiff, a hybrid framework that integrates a dilated attention network (DAN) for ROI extraction, a diffusion-based subnet for noise suppression in low-contrast regions, and a striped attention network (SAN) to refine tubular structures affected by morphological variations. …”
Get full text

Hybrid deep learning framework based on EfficientViT for classification of gastrointestinal diseases by Vishesh Tanwar, Bhisham Sharma, Dhirendra Prasad Yadav, Abolfazl Mehbodniya

“…At the same time, it includes the capacity of the ViT model to recognize the context of images of the GI tract for the detection of slight disease patterns and precursors of disease diffusion. Furthermore, we designed a dual-block in which input is divided into two parts (q1, q2) to better optimize the model q1 processed through an EfficientNet for local details and a q2 through encoder block for capturing the global dependencies, which enables EfficientViT to pay attention to multiple image regions simultaneously. …”
Get full text

A Semi-Supervised Diffusion-Based Framework for Weed Detection in Precision Agricultural Scenarios Using a Generative Attention Mechanism by Ruiheng Li, Xuaner Wang, Yuzhuo Cui, Yifei Xu, Yuhao Zhou, Xuechun Tang, Chenlu Jiang, Yihong Song, Hegan Dong, Shuo Yan

“…To address these issues, a weed detection model based on a semi-supervised diffusion generative network is proposed. This model integrates a generative attention mechanism and semi-diffusion loss to enable the efficient utilization of both labeled and unlabeled data. …”
Get full text

DiffBTS: A Lightweight Diffusion Model for 3D Multimodal Brain Tumor Segmentation by Zuxin Nie, Jiahong Yang, Chengxuan Li, Yaqin Wang, Jun Tang

“…DiffBTS replaces the conventional self-attention module in the traditional diffusion models by introducing an efficient 3D self-attention mechanism. …”
Get full text

Timescale correlation of shallow trap states increases electrochemiluminescence efficiency in carbon nitrides by Yanfeng Fang, Hong Yang, Yuhua Hou, Wang Li, Yanfei Shen, Songqin Liu, Yuanjian Zhang

“…Among them, electrochemiluminescence, an emission of light excited by electrochemical reactions, has drawn attention as a powerful tool for bioassays. Nonetheless, the large differences in timescale among diverse charge-transfer pathways from picoseconds to seconds significantly limit the electrochemiluminescence efficiency and hamper their broad applications. …”
Get full text

Application of physics-informed neural networks for two-phase flow model with variable diffusion and experimental validation by Daulet Kalesh, Timur Merembayev, Sagyn Omirbekov, Yerlan Amanbek

“…The study analyzes the PINNs using different approaches, including diffusion term and modification flux function to convex hull, employing both Multi-Layer Perceptron (MLP) and Attention-based neural network architectures. …”
Get full text

A Diffusion–Attention-Enhanced Temporal (DATE-TM) Model: A Multi-Feature-Driven Model for Very-Short-Term Household Load Forecasting by Yitao Zhao, Jiahao Li, Chuanxu Chen, Quansheng Guan

“…Further, the real-time data processing requirement calls for both the high forecasting accuracy and improved computational efficiency. Thus, we propose a diffusion–attention-enhanced temporal (DATE-TM) model with multi-feature fusion to address the above issues. …”
Get full text

Sodium Chloride‐Assisted Crystalline Graphitic Carbon Nitride for Efficient Photocatalytic Hydrogen Evolution by Xueze Chu, C. I. Sathish, Jae‐Hun Yang, Wei Li, Dongchen Qi, Xinwei Guan, Xiaojiang Yu, Mark B. H. Breese, Liang Qiao, Jiabao Yi

“…The resulting g‐C3N4 has an optimum band structure that benefits enhanced light absorption and charge separation efficiency. The intimate contact between sodium chloride and carbon nitride in the pressed pellet facilitates the diffusion of sodium ions and increases the material's resistance to high annealing temperatures, leading to improved crystallinity. …”
Get full text

De Novo Design of Large Polypeptides Using a Lightweight Diffusion Model Integrating LSTM and Attention Mechanism Under Per-Residue Secondary Structure Constraints by Sisheng Liao, Gang Xu, Li Jin, Jianpeng Ma

“…By integrating a lightweight LSTM-attention neural network as the denoiser within a diffusion framework, PPD offers an innovative and efficient approach to polypeptide generation. …”
Get full text

Use of Anionic Surfactant-Modified Activated Carbon for Efficient Adsorptive Removal of Crystal Violet Dye by Rumi Goswami, Amit Kumar Dey

Get full text

ETIA: Enhancing Text2Image Surround View Scene Generation With Semantic Annotation via Diffusion for Autonomous Driving by Ramyashree, S. Raghavendra, S. K. Abhilash, Venu Madhav Nookala, P. V. Arun Kumar, P. Malashree

“…Generating high-fidelity surround view images from text prompts is a complex task that requires balancing contextual coherence with computational efficiency. The proposed work introduces a novel methodology that combines recurrent attention-based encoder-decoder architectures with text-to-image diffusion models to produce coherent and continuous surround view images. …”
Get full text

The influence of service information systems on strengthening competitiveness and efficiency of business of small and medium-sized enterprises (SMEs) by Dimitrijević Dragan, Dimitrijević Natalija, Adamović Živoslav

“…The fact that today nuances or millionths of some value in business bring an advantage in quality or economic valorization and decide on advantages in strengthening competitiveness or efficient optimization of business, require greater attention and critical consideration of the importance of implementation and efficient exploitation of the so-called service information systems (e-administration, e-education, e-health). …”
Get full text

Carbon coated titanium dioxide (CC-TiO2) as an efficient anode material for sodium- ion batteries by Rahul Kumar, Anagha Pradeep, Parag Bhargava

“…Abstract TiO2 has attracted a lot of attention as anode material for sodium-ion batteries due to its higher operating voltage, safely and low lost material, but TiO2 has two main issues, low electronic conductivity and slow solid-state ion diffusion. …”
Get full text