☆ 4.7 Article

SwinWave-SR: Multi-scale lightweight underwater image super-resolution

INFORMATION FUSION (2024)

Related references

Note: Only part of the references are listed.

Article Computer Science, Information Systems

Energy-Aware AI-Driven Framework for Edge-Computing-Based IoT Applications

Muhammad Zawish et al.

Summary: The significant growth of IoT devices has led to the development of edge computing, and energy harvestable wearable devices are expected to enhance edge intelligence in IoT applications. However, intermittent energy supply and limited network connectivity in remote or hard-to-reach areas can affect the performance of edge computing-based IoT applications. Existing model compression methods are not suitable for energy-constrained devices with intermittent energy sources. In this study, a pruning scheme based on deep reinforcement learning is proposed to compress the CNN model according to energy management policies and accuracy requirements for IoT applications.

IEEE INTERNET OF THINGS JOURNAL (2023)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution

Haram Choi et al.

Summary: In this article, a low-level image super-resolution method based on N-Gram context is proposed. By introducing N-Gram correlation and using window self-attention mechanism, the field of view is expanded, and the degraded pixels are restored. The experiments show that this method is competitive in terms of performance and efficiency, and it improves upon other Swin-based SR methods.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

FuzzyAct: A Fuzzy-Based Framework for Temporal Activity Recognition in IoT Applications Using RNN and 3D-DWT

Fayaz Ali Dharejo et al.

Summary: This article presents a method that combines discrete wavelet transform (DWT) and recurrent neural network (RNN) for accurate classification and detection of human activities. The proposed approach extracts features using 3D-DWT and produces output labels using RNN. A rank-based fuzzy method is also used to accurately segregate activities. In experiments, the method achieves good performance on the ActivityNet dataset.

IEEE TRANSACTIONS ON FUZZY SYSTEMS (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images

Kai Yan et al.

Summary: The quality of underwater images is heavily degraded by various factors, posing challenges for object recognition. To address this, a new method utilizing a media transmission map for image enhancement has been introduced, achieving promising results and improved underwater perception.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Computer Science, Software Engineering

PVT v2: Improved baselines with Pyramid Vision Transformer

Wenhai Wang et al.

Summary: This work presents the improved Pyramid Vision Transformer v2 (PVT v2) by adding three designs, achieving significant improvements in fundamental vision tasks. PVT v2 performs comparably or better than recent work such as the Swin transformer.

COMPUTATIONAL VISUAL MEDIA (2022)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Towards Resource-aware DNN Partitioning for Edge Devices with Heterogeneous Resources

Muhammad Zawish et al.

Summary: This article proposes a resource-aware partitioning method for accelerating collaborative inference between edge and cloud. Unlike existing technologies, this method considers the heterogeneity and inconsistent resource levels and types of edge devices. Experimental results show that in bandwidth-constrained scenarios, this method achieves 40% higher efficiency compared to offline benchmarking methods.

2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Uformer: A General U-Shaped Transformer for Image Restoration

Zhendong Wang et al.

Summary: This paper introduces Uformer, an image restoration architecture based on Transformer, with a hierarchical encoder-decoder network and novel designs including locally-enhanced window Transformer block and learnable multi-scale restoration modulator. Uformer demonstrates high capability for image restoration tasks and achieves superior performance in various experiments.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection

Yong Zhang et al.

Summary: This paper proposes a novel Transformer-based HOI detector, STIP, which decomposes the process of HOI set prediction into two stages: interaction proposal generation and transforming the proposals using a structure-aware Transformer. By encoding the semantic and spatial structure of interaction proposals, STIP outperforms state-of-the-art HOI detectors.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Stand-Alone Inter-Frame Attention in Video Models

Fuchen Long et al.

Summary: This paper introduces a novel interframe attention block called Stand-alone Inter-Frame Attention (SIFA), which examines the deformation across frames to estimate local self-attention on each spatial location. It demonstrates the superiority of the SIFA-Net and SIFA-Transformer as stronger backbones for video understanding models, achieving an accuracy of 83.1% on the Kinetics-400 dataset.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

Conformer and Blind Noisy Students for Improved Image Quality Assessment

Marcos Conde et al.

Summary: Generative models have improved the quality of generated images for image restoration, enhancement, and generation. Despite producing more visually pleasing images, these models may receive lower perceptual quality scores using traditional metrics. Therefore, it is important to develop a quantitative metric that aligns well with human perception. This study explores transformer-based full-reference IQA models and proposes a method for IQA based on semi-supervised knowledge distillation, achieving competitive results in the NTIRE 2022 Perceptual Image Quality Assessment Challenge.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022 (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Plug-and-Play Image Restoration With Deep Denoiser Prior

Kai Zhang et al.

Summary: Recent works have shown that using a denoiser as the image prior can improve the performance of plug-and-play image restoration methods. However, existing methods are limited by the lack of suitable denoiser priors. In this study, we propose a deep denoiser prior that significantly outperforms other state-of-the-art model-based and learning-based methods for various image restoration tasks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

TWIST-GAN: TowardsWavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution

Fayaz Ali Dharejo et al.

Summary: The study proposes a frequency domain-based spatio-temporal remote sensing single image super-resolution technique combined with generative adversarial networks (GANs) to reconstruct high-resolution images. By splitting the LR image into different frequency bands and using transferred GANs for prediction, the high-frequency components are generated to produce a reconstructed image with super-resolution.

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Exploring Sparsity in Image Super-Resolution for Efficient Inference

Longguang Wang et al.

Summary: This study introduces a Sparse Mask SR network to improve inference efficiency of SR networks by learning sparse masks to prune redundant computation while maintaining comparable performance.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification

Marcos Conde et al.

Summary: This research uses the CLIP model to train a neural network on various art images and text pairs, aiming to solve the challenges of fine-grained artwork attribute recognition. The model's zero-shot capability allows it to predict the most relevant natural language description for a given image, even without direct task optimization.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

KernelNet: A Blind Super-Resolution Kernel Estimation Network

Mehmet Yamac et al.

Summary: Recently developed deep neural network methods have shown remarkable performance in the super resolution problem, but their performance drops significantly on real-world images. Techniques for blind super resolution kernel estimation, such as KernelGAN, show promise but are limited by complexity for real-time applications.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding

Chongyi Li et al.

Summary: The Ucolor network enhances underwater images by incorporating multiple color spaces embedding and utilizing both physical model-based and learning-based methods. Experimental results show superior performance in visual quality and quantitative metrics compared to state-of-the-art methods.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Add to Collection

Article Environmental Sciences

PelagiCam: a novel underwater imaging system with computer vision for semi-automated monitoring of mobile marine fauna at offshore structures

Emma V. Sheehan et al.

ENVIRONMENTAL MONITORING AND ASSESSMENT (2020)

Add to Collection

Article Engineering, Civil

Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network

Yecai Guo et al.

IEEE JOURNAL OF OCEANIC ENGINEERING (2020)

Add to Collection

Article Robotics

Fast Underwater Image Enhancement for Improved Visual Perception

Md Jahidul Islam et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

An Underwater Image Enhancement Benchmark Dataset and Beyond

Chongyi Li et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Sea-thru: A Method For Removing Water From Underwater Images

Derya Akkaynak et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Kai Zhang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study

Eirikur Agustsson et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Scaling the Scattering Transform: Deep Hybrid Networks

Edouard Oyallon et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification

Woong Bae et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Wei-Sheng Lai et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Image-to-Image Translation with Conditional Adversarial Networks

Phillip Isola et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Deep Wavelet Prediction for Image Super-resolution

Tiantong Guo et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Christian Ledig et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Secure Communication for Underwater Acoustic Sensor Networks

Guangjie Han et al.

IEEE COMMUNICATIONS MAGAZINE (2015)

Add to Collection

Article Engineering, Marine

Experiments on vision guided docking of an autonomous underwater vehicle using one camera

Jin-Yeong Park et al.

OCEAN ENGINEERING (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

Image quality assessment: From error visibility to structural similarity

Z Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2004)

Add to Collection

Article Computer Science, Artificial Intelligence

Eigenface-domain super-resolution for face recognition

BK Gunturk et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2003)

Add to Collection

© Peeref 2019-2024. All rights reserved.