Image-driven prediction system: Automatic extraction of aggregate gradation of pavement core samples integrating deep learning and interactive image processing …

HC Dan, Z Huang, B Lu, M Li - Construction and Building Materials, 2024 - Elsevier
Aggregate gradation plays a crucial role in determining the asphalt pavement performance,
necessitating assessment post-construction. Additionally, efficient gradation measurement is …

Exploring diverse methods in visual question answering

P Li, Q Yang, X Geng, W Zhou, Z Ding… - 2024 5th International …, 2024 - ieeexplore.ieee.org
This study explores innovative methods for improving Visual Question Answering (VQA)
using Generative Adversarial Networks (GANs), autoencoders, and attention mechanisms …

A comparative study on enhancing prediction in social network advertisement through data augmentation

Q Yang, P Li, X Xu, Z Ding, W Zhou… - 2024 4th International …, 2024 - ieeexplore.ieee.org
In the ever-evolving landscape of social network advertising, the volume and accuracy of
data play a critical role in the performance of predictive models. However, the development …

Few-shot name entity recognition on stackoverflow

X Chen, K Li, T Song, J Guo - 2024 9th International …, 2024 - ieeexplore.ieee.org
StackOverflow, with its vast question repository and limited labeled examples, raise an
annotation challenge for us. We address this gap by proposing RoBERTa+ MAML, a few …

Llamaf: An efficient llama2 architecture accelerator on embedded fpgas

H Xu, Y Li, S Ji - 2024 IEEE 10th World Forum on Internet of …, 2024 - ieeexplore.ieee.org
Large language models (LLMs) have demonstrated remarkable abilities in natural language
processing. However, their deployment on resource-constrained embedded devices …

Ad-aligning: Emulating human-like generalization for cognitive domain adaptation in deep learning

Z Li, B Wan, C Mu, R Zhao, S Qiu… - 2024 5th International …, 2024 - ieeexplore.ieee.org
Domain adaptation is pivotal for enabling deep learning models to generalize across
diverse domains, a task complicated by variations in presentation and cognitive nuances. In …

Network alignment with transferable graph autoencoders

J He, CI Kanatsoulis, A Ribeiro - arxiv preprint arxiv:2310.03272, 2023 - arxiv.org
Network alignment is the task of establishing one-to-one correspondences between the
nodes of different graphs and finds a plethora of applications in high-impact domains …

Confidence trigger detection: Accelerating real-time tracking-by-detection systems

Z Ding, Z Lai, S Li, P Li, Q Yang… - 2024 5th International …, 2024 - ieeexplore.ieee.org
Real-time object tracking necessitates a delicate balance between speed and accuracy, a
challenge exacerbated by the computational demands of deep learning methods. In this …

Restful-llama: Connecting user queries to restful apis

H Xu, R Zhao, J Wang, H Chen - Proceedings of the 2024 …, 2024 - aclanthology.org
Abstract Recent advancements in Large Language Models (LLMs) have showcased
exceptional performance in zero-shot learning and reasoning tasks. However, integrating …

Style Transfer: From Stitching to Neural Networks

X Xu, Z Wang, Y Zhang, Y Liu, Z Wang… - … Conference on Big …, 2024 - ieeexplore.ieee.org
This article compares two style transfer methods in image processing: the traditional method,
which synthesizes new images by stitching together small patches from existing pattern …