| 1. |
- Li, Dayi, et al.
(författare)
-
Adaptive weighted multiscale retinex for underwater image enhancement
- 2023
-
Ingår i: Engineering applications of artificial intelligence. - Amsterdam : Elsevier. - 0952-1976 .- 1873-6769. ; 123
-
Tidskriftsartikel (refereegranskat)abstract
- Vision-dependent underwater vehicles are widely used in seabed resource exploration. The visual perception system of underwater vehicles relies heavily on high-quality images for its regular operation. However, underwater images taken underwater often have color distortion, blurriness, and poor contrast. To address these degradation issues, we develop an adaptive weighted multiscale retinex (AWMR) method for enhancing underwater images. To utilize the local detail features, we first divide the image into multiple sub-blocks and calculate the detail sparsity index for each one. Then, we combine the global detail sparsity index with the local detail sparsity indices to determine the optimal scale parameter and corresponding weights for each sub-block. We apply retinex processing to each sub-block using these parameters and then subject the processed sub-blocks to detail enhancement, color correction, and saturation correction. Finally, we use a gradient domain fusion method based on structure tensors to fuse the corrected and enhanced sub-blocks and obtain the final output image. Our approach improves underwater images through comparisons with current state-of-the-art (SOTA) techniques on several open-source datasets, both quality, and performance. © 2023 Elsevier Ltd
|
|
| 2. |
- Ning, Xin, et al.
(författare)
-
ICGNet : An intensity-controllable generation network based on covering learning for face attribute synthesis
- 2024
-
Ingår i: Information Sciences. - New York : Elsevier. - 0020-0255 .- 1872-6291. ; 660
-
Tidskriftsartikel (refereegranskat)abstract
- Face-attribute synthesis is a typical application of neural network technology. However, most current methods suffer from the problem of uncontrollable attribute intensity. In this study, we proposed a novel intensity-controllable generation network (ICGNet) based on covering learning for face attribute synthesis. Specifically, it includes an encoder module based on the principle of homology continuity between homologous samples to map different facial images onto the face feature space, which constructs sufficient and effective representation vectors by extracting the input information from different condition spaces. It then models the relationships between attribute instances and representational vectors in space to ensure accurate synthesis of the target attribute and complete preservation of the irrelevant region. Finally, the progressive changes in the facial attributes by applying different intensity constraints to the representation vectors. ICGNet achieves intensity-controllable face editing compared to other methods by extracting sufficient and effective representation features, exploring and transferring attribute relationships, and maintaining identity information. The source code is available at https://github.com/kllaodong/-ICGNet.•We designed a new encoder module to map face images of different condition spaces into face feature space to obtain sufficient and effective face feature representation.•Based on feature extraction, we proposed a novel Intensity-Controllable Generation Network (ICGNet), which can realize face attribute synthesis with continuous intensity control while maintaining identity and semantic information.•The quantitative and qualitative results showed that the performance of ICGNet is superior to current advanced models.© 2024 Elsevier Inc.
|
|
| 3. |
- Pandey, Sachi, et al.
(författare)
-
Do-It-Yourself Recommender System: Reusing and Recycling with Blockchain and Deep Learning
- 2022
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 10, s. 90056-90067
-
Tidskriftsartikel (refereegranskat)abstract
- Due to aggressive urbanization (with population size), waste increases exponentially, resulting in environmental damage. Even though it looks challenging, such an issue can be controlled if we can reuse them. To handle this, in our work, we design a machine learning and blockchain-oriented system that identifies thewaste objects/products and recommends to the user multiple ’Do-It-Yourself’ (DIY) ideas to reuse or recycle. Blockchain records every transaction in the shared ledger to enable transaction verifiability and supports better decision-making. In this study, a Deep Neural Network (DNN) trained on about 11700 images is developed using ResNet50 architecture for object recognition (training accuracy of 94%).We deploy several smart contracts in the Hyperledger Fabric (HF) blockchain platform to validate recommended DIY ideas by blockchain network members. HF is a decentralized ledger technology platform that executes the deployed smart contracts in a secured Docker container to initialize and manage the ledger state. The complete model is delivered on a web platform using Flask, where our recommendation system works on a web scraping script written using Python. Fetching DIY ideas using web-scraping takes nearly 1 second on a desktop machine with an Intel Core-i7 processor with 8 cores, 16 GB RAM, installed with Ubuntu 18.04 64-bit operating system, and Python 3.6 package. Further, we evaluate blockchain-based smart contracts’ latencies and throughput performances using the hyperledger caliper benchmark. To the best of our knowledge, this is the first work that integrates blockchain technology and deep learning for the DIY recommender system.
|
|
| 4. |
- Saeed, Uzair, et al.
(författare)
-
One-shot many-to-many facial reenactment using Bi-Layer Graph Convolutional Networks
- 2022
-
Ingår i: Neural Networks. - Oxford : Elsevier. - 0893-6080 .- 1879-2782. ; 156, s. 193-204
-
Tidskriftsartikel (refereegranskat)abstract
- Facial reenactment is aimed at animating a source face image into a new place using a driving facial picture. In a few shot scenarios, the present strategies are designed with one or more identities or identity-sustained suffering protection challenges. These current solutions are either developed with one or more identities in mind, or face identity protection issues in one or more shot situations. Multiple pictures from the same entity have been used in previous research to model facial reenactment. In contrast, this paper presents a novel model of one-shot many-to-many facial reenactments that uses only one facial image of a face. The proposed model produces a face that represents the objective representation of the same source identity. The proposed technique can simulate motion from a single image by decomposing an object into two layers. Using bi-layer with Convolutional Neural Network (CNN), we named our model Bi-Layer Graph Convolutional Layers (BGCLN) which utilized to create the latent vector’s optical flow representation. This yields the precise structure and shape of the optical stream. Comprehensive studies suggest that our technique can produce high-quality results and outperform most recent techniques in both qualitative and quantitative data comparisons. Our proposed system can perform facial reenactment at 15 fps, which is approximately real time. Our code is publicly available at https://github.com/usaeed786/BGCLN
|
|
| 5. |
- Zeyu, He, et al.
(författare)
-
Causal embedding of user interest and conformity for long-tail session-based recommendations
- 2023
-
Ingår i: Information Sciences. - Philadelphia, PA : Elsevier. - 0020-0255 .- 1872-6291. ; 644
-
Tidskriftsartikel (refereegranskat)abstract
- Session-based recommendation is misleading by popularity bias and always favors short-head items with more popularity. This paper studies a new causal-based framework CauTailReS to increase the diversity of session recommendations. We first propose a new causal graph and then use the do-calculus in order to understand how popularity influences the process of making recommendations from the user's point of view. Popularity only misleads users temporarily, rather than in a long term and globally. Second, we believe that user clicks on popular products demonstrate their high quality and reputation. CauTailReS only eliminates ‘bad’ biases and retains ‘good’ effects through interest and consistent causal embedding mechanisms. To determine how similar various users are on various target items, CauTailReS also employs a re-ranking technique known as ‘conformity-aware re-ranking’. To discover interactions based on what actual users want, CauTailReS also employs counterfactual reasoning. Extensive comparative experiments on four real world datasets have shown CauTailReS can well capture the true interests and consistency of users. As compared to the current state-of-the-art, CauTailReS enhances long-tail performance (APLT is increased by 8.14%) and recommendation accuracy (MRR is increased by 2.75%). This proves that introducing causal embeddings helps to reasonably enhance the diversity of recommendations. © 2023 Elsevier Inc.
|
|
