Deep Learning Methods for Microstructural Image Analysis: The State-of-the-Art and Future Perspectives

K Alrfou, T Zhao, A Kordijazi - Integrating Materials and Manufacturing …, 2024 - Springer
Finding quantitative descriptors representing the microstructural features of a given material
is an ongoing research area in the paradigm of Materials-by-Design. Historically, the …

Study of mechanical degradation of freestanding ALD Al 2 O 3 by a hygrothermal environment and a facile protective method for environmentally stable Al 2 O 3 …

S Lee, Y Jeon, SJ Oh, SW Lee, KC Choi, TS Kim… - Materials …, 2023 - pubs.rsc.org
Al2O3 deposited via atomic layer deposition (ALD) has been used as an insulating and
barrier film for thin-film transistors, organic electronics, and microelectromechanical systems …

Integrated and Automated: Liquid Metal‐based System for Full Cycle CO2‐to‐Carbon Conversion

X Chen, Q Wang, K Wu, Y Li, J Chen… - Advanced Energy …, 2024 - Wiley Online Library
The urgency for carbon neutrality is driving the need for cost‐effective Carbon Capture and
Conversion (iCCC) technology, but the lack of a unified platform for capture, release, and the …

A generic shared attention mechanism for various backbone neural networks

Z Huang, S Liang, M Liang - Neurocomputing, 2025 - Elsevier
The self-attention mechanism is crucial for enhancing various backbone neural networks'
performance. However, current methods add self-attention modules (SAMs) to each network …

Neural clustering based visual representation learning

G Chen, X Li, Y Yang, W Wang - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
We investigate a fundamental aspect of machine vision: the measurement of features by
revisiting clustering one of the most classic approaches in machine learning and data …

Rgbt tracking via frequency-aware feature enhancement and unidirectional mixed attention

J Zhang, J Yang, Z Liu, J Wang - Neurocomputing, 2025 - Elsevier
RGBT object tracking is widely used due to the complementary nature of RGB and TIR
modalities. However, RGBT trackers based on Transformer or CNN face significant …

Overcoming language priors in visual question answering with cumulative learning strategy

A Mao, F Chen, Z Ma, K Lin - Neurocomputing, 2024 - Elsevier
The performance of visual question answering (VQA) has witnessed great progress over the
last few years. However, many current VQA models tend to rely on superficial linguistic …

SMART-vision: survey of modern action recognition techniques in vision

AK AlShami, R Rabinowitz, K Lam, Y Shleibik… - Multimedia Tools and …, 2024 - Springer
Abstract Human Action Recognition (HAR) is a challenging domain in computer vision,
involving recognizing complex patterns by analyzing the spatiotemporal dynamics of …

Robust domain adaptive object detection with unified multi-granularity alignment

L Zhang, W Zhou, H Fan, T Luo… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Domain adaptive detection aims to improve the generalization of detectors on target domain.
To reduce discrepancy in feature distributions between two domains, recent approaches …

Improving visual grounding with multi-modal interaction and auto-regressive vertex generation

X Qin, F Li, C He, R Pei, X Zhang - Neurocomputing, 2024 - Elsevier
We propose a concise and consistent network focusing on multi-task learning of Referring
Expression Comprehension (REC) and Segmentation (RES) within Visual grounding (VG) …