Generative image inpainting with enhanced gated convolution and Transformers

M Wang, W Lu, J Lyu, K Shi, H Zhao - Displays, 2022 - Elsevier
Image inpainting is widely used to fill the damaged or masked area in an image with realistic
visual contents. However, most existing inpainting methods have limitations in …

Real-time detection of drones using channel and layer pruning, based on the yolov3-spp3 deep learning algorithm

X Zhang, K Fan, H Hou, C Liu - Micromachines, 2022 - mdpi.com
Achieving a real-time and accurate detection of drones in natural environments is essential
for the interception of drones intruding into high-security areas. However, a rapid and …

Online Professional-Creative Fusion Music Major Students' Classroom State Recognition Based on the Integration of DSC and LeNet-5 Models

HB Lin - Journal of Artificial Intelligence and Technology, 2024 - ojs.istp-press.com
Online professional-creative fusion education in music majors is becoming increasingly
prevalent, but accurately identifying students' classroom states remains a challenge. This …

轻量化YOLO-v7 的数显仪表检测及读数.

章芮宁, 闫坤, 叶进 - Journal of Computer Engineering & …, 2024 - search.ebscohost.com
由于较大的参数体量和较高的计算复杂度, 通用检测及识别模型直接在移动端部署的难度较高.
为解决这个困难, 研究了移动设备上使用计算机视觉的仪表检测及读数方法 …

TEG: image theme recognition using text-embedding-guided few-shot adaptation

J Wang, W Lu, Y Wang, K Shi… - Journal of Electronic …, 2024 - spiedigitallibrary.org
Grouping images into different themes is a challenging task in photo book curation. Unlike
image object recognition, image theme recognition focuses on the understanding of the …

Detecting Blinks from Wearable Cameras using Spatial-Temporal-Aware Deep Network Learning

Y Wang, W Lu, H Zhao, X Jiang, B Zheng… - Proceedings of the 2023 …, 2023 - dl.acm.org
Blinks have been widely studied in various fields including medical and human computer
interactions, and in driver fatigue. Automatic detection of blinks has valuable practical …

DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism

C Park, M Park, H Moon, MK Yoon, S Go, S Kim… - The Thirty-eighth Annual … - openreview.net
Depth-wise Separable Convolution (DSConv) has a powerful representation even with
fewer parameters and computation, leading to its adoption by almost all of the state-of-the …