Deep learning-based detection from the perspective of small or tiny objects: A survey

K Tong, Y Wu - Image and Vision Computing, 2022 - Elsevier
Detecting small or tiny objects is always a difficult and challenging issue in computer vision.
In this paper, we provide a latest and comprehensive survey of deep learning-based …

A complete review on image denoising techniques for medical images

A Kaur, G Dong - Neural Processing Letters, 2023 - Springer
Medical imaging methods, such as CT scans, MRI scans, X-rays, and ultrasound imaging,
are widely used for diagnosis in the healthcare domain. However, these methods are often …

Oneformer: One transformer to rule universal image segmentation

J Jain, J Li, MT Chiu, A Hassani… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Universal Image Segmentation is not a new concept. Past attempts to unify image
segmentation include scene parsing, panoptic segmentation, and, more recently, new …

Peco: Perceptual codebook for bert pre-training of vision transformers

X Dong, J Bao, T Zhang, D Chen, W Zhang… - Proceedings of the …, 2023 - ojs.aaai.org
This paper explores a better prediction target for BERT pre-training of vision transformers.
We observe that current prediction targets disagree with human perception judgment. This …

OpenCap: Human movement dynamics from smartphone videos

SD Uhlrich, A Falisse, Ł Kidziński… - PLoS computational …, 2023 - journals.plos.org
Measures of human movement dynamics can predict outcomes like injury risk or
musculoskeletal disease progression. However, these measures are rarely quantified in …

Open graph benchmark: Datasets for machine learning on graphs

W Hu, M Fey, M Zitnik, Y Dong, H Ren… - Advances in neural …, 2020 - proceedings.neurips.cc
Abstract We present the Open Graph Benchmark (OGB), a diverse set of challenging and
realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine …

A mutually supervised graph attention network for few-shot segmentation: The perspective of fully utilizing limited samples

H Gao, J **ao, Y Yin, T Liu, J Shi - IEEE Transactions on neural …, 2022 - ieeexplore.ieee.org
Fully supervised semantic segmentation has performed well in many computer vision tasks.
However, it is time-consuming because training a model requires a large number of pixel …

Yolov7-sea: Object detection of maritime uav images based on improved yolov7

H Zhao, H Zhang, Y Zhao - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Object detection algorithms play an important role in maritime search and rescue missions,
where they are designed to detect people, boats and other objects in open water. However …

Semantic image synthesis with spatially-adaptive normalization

T Park, MY Liu, TC Wang… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing
photorealistic images given an input semantic layout. Previous methods directly feed the …

3d human pose estimation in video with temporal convolutions and semi-supervised training

D Pavllo, C Feichtenhofer… - Proceedings of the …, 2019 - openaccess.thecvf.com
In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully
convolutional model based on dilated temporal convolutions over 2D keypoints. We also …