U2-Net: Going deeper with nested U-structure for salient object detection

X Qin, Z Zhang, C Huang, M Dehghan, OR Zaiane… - Pattern recognition, 2020 - Elsevier
In this paper, we design a simple yet powerful deep network architecture, U 2-Net, for salient
object detection (SOD). The architecture of our U 2-Net is a two-level nested U-structure. The …

Efficient and accurate arbitrary-shaped text detection with pixel aggregation network

W Wang, E Xie, X Song, Y Zang… - Proceedings of the …, 2019 - openaccess.thecvf.com
Scene text detection, an important step of scene text reading systems, has witnessed rapid
development with convolutional neural networks. Nonetheless, two main challenges still …

A survey on attention mechanisms for medical applications: are we moving toward better Algorithms?

T Gonçalves, I Rio-Torto, LF Teixeira… - IEEE Access, 2022 - ieeexplore.ieee.org
The increasing popularity of attention mechanisms in deep learning algorithms for computer
vision and natural language processing made these models attractive to other research …

Toward fast and accurate human pose estimation via soft-gated skip connections

A Bulat, J Kossaifi, G Tzimiropoulos… - 2020 15th IEEE …, 2020 - ieeexplore.ieee.org
This paper is on highly accurate and highly efficient human pose estimation. Recent works
based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this …

[HTML][HTML] EfficientPose: Scalable single-person pose estimation

D Groos, H Ramampiaro, EAF Ihlen - Applied intelligence, 2021 - Springer
Single-person human pose estimation facilitates markerless movement analysis in sports, as
well as in clinical applications. Still, state-of-the-art models for human pose estimation …

Neounet: Towards accurate colon polyp segmentation and neoplasm detection

P Ngoc Lan, NS An, DV Hang, DV Long… - Advances in visual …, 2021 - Springer
Automatic polyp segmentation has proven to be immensely helpful for endoscopy
procedures, reducing the missing rate of adenoma detection for endoscopists while …

Learning feature-to-feature translator by alternating back-propagation for generative zero-shot learning

Y Zhu, J Xie, B Liu, A Elgammal - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
We investigate learning feature-to-feature translator networks by alternating back-
propagation as a general-purpose solution to zero-shot learning (ZSL) problems. It is a …

Complex image processing with less data—Document image binarization by integrating multiple pre-trained U-Net modules

S Kang, BK Iwana, S Uchida - Pattern Recognition, 2021 - Elsevier
Artificial neural networks have been shown significant performance in various image-to-
image conversion tasks. However, complex conversions often require a large number of …

Learning to forecast and refine residual motion for image-to-video generation

L Zhao, X Peng, Y Tian, M Kapadia… - Proceedings of the …, 2018 - openaccess.thecvf.com
We consider the problem of image-to-video translation, where an input image is translated
into an output video containing motions of a single object. Recent methods for such …

Blazeneo: Blazing fast polyp segmentation and neoplasm detection

NS An, PN Lan, DV Hang, DV Long, TQ Trung… - IEEE …, 2022 - ieeexplore.ieee.org
In recent years, computer-aided automatic polyp segmentation and neoplasm detection
have been an emerging topic in medical image analysis, providing valuable support to …