Results 11 to 20 of about 25,505 (263)
Transformers in Vision: A Survey [PDF]
ACM Computing Surveys, 2022 Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks, e.g.,
Salman H. Khan 0001 +5 more
openaire +4 more sources
Advances in Neural Information Processing Systems 35, 2022 Human vision possesses a special type of visual processing systems called peripheral vision. Partitioning the entire visual field into multiple contour regions based on the distance to the center of our gaze, the peripheral vision provides us the ability to perceive various visual features at different regions.
Juhong Min +3 more
openaire +3 more sources
CSiT: A Multiscale Vision Transformer for Hyperspectral Image Classification
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022 The hyperspectral image (HSI) has nearly continuous spectral information; thus, the target of interest can be accurately identified by the subtle details of spectral properties.
Wenxuan He +4 more
doaj +1 more source
Sensors, 2023 Semantic segmentation with deep learning networks has become an important approach to the extraction of objects from very high-resolution remote sensing images.
Jia Song, A-Xing Zhu, Yunqiang Zhu
doaj +1 more source
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure into regional and local feature extraction procedures that each incurs a much smaller computational complexity.
Ting Yao 0003 +5 more
openaire +3 more sources
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding a model's scaling properties is a key to designing future generations effectively.
Xiaohua Zhai +3 more
openaire +4 more sources
A Review of Transformer-Based Approaches for Image Captioning
Applied Sciences, 2023 Visual understanding is a research area that bridges the gap between computer vision and natural language processing. Image captioning is a visual understanding task in which natural language descriptions of images are automatically generated using ...
Oscar Ondeng, Heywood Ouma, Peter Akuon
doaj +1 more source
STHarDNet: Swin Transformer with HarDNet for MRI Segmentation
Applied Sciences, 2022 In magnetic resonance imaging (MRI) segmentation, conventional approaches utilize U-Net models with encoder–decoder structures, segmentation models using vision transformers, or models that combine a vision transformer with an encoder–decoder model ...
Yeonghyeon Gu +2 more
doaj +1 more source
Vision Transformer with Progressive Sampling [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 Accepted to ICCV ...
Xiaoyu Yue +6 more
openaire +4 more sources
Building Extraction With Vision Transformer [PDF]
IEEE Transactions on Geoscience and Remote Sensing, 2022 Submitted to ...
Libo Wang +3 more
openaire +2 more sources