Showing papers in "Neurocomputing in 2022"

TL;DR: Wang et al. as discussed by the authors proposed an Efficient Intersection over Union (EIOU) loss, which explicitly measures the discrepancies of three geometric factors in BBR, i.e., the overlap area, the central point and the side length.

TL;DR: A survey of the application of deep learning techniques in NLP, with a focus on the various tasks where deep learning is demonstrating stronger impact.

TL;DR: In this paper , Li et al. reviewed the state-of-the-art technologies of semantic segmentation based on deep learning and analyzed the key factors affecting the real-time performance of the segmentation model.

TL;DR: This paper proposed a bidirectional emotional recurrent unit for conversational sentiment analysis, where a generalized neural tensor block followed by a two-channel classifier is designed to perform context compositionality and sentiment classification, respectively.

TL;DR: This article proposed a party-ignorant framework based on emotional recurrent unit for conversational sentiment analysis, which is suitable for different structures to perform context compositionality and sentiment classification, respectively.

TL;DR: In this article , a fuzzy logic based deep learning (DL) approach was proposed to differentiate between CXR images of patients with Covid-19 pneumonia and with interstitial pneumonias not related to Covid19.

TL;DR: Wang et al. as mentioned in this paper proposed a multi-scale superpixel fusion network (MFGCN), where two different convolutional networks are utilized in two branches, separately, for hyperspectral image (HSI) classification.

TL;DR: A survey of dynamic network embedding can be found in this article , where the authors inspect the data model, representation learning technique, evaluation and application of current related works and derive common patterns from them.

TL;DR: In this paper , a survey of the application of deep learning techniques in NLP, with a focus on the various tasks where deep learning is demonstrating stronger impact, is presented, including software, hardware, and popular corpora.

TL;DR: Mai et al. as discussed by the authors compare state-of-the-art methods such as Maximally Interfered Retrieval (MIR), iCARL, and GDumb (a very strong baseline) and determine which works best at different memory and data settings.

TL;DR: In this paper , a large number of researches have proposed evolutionary deep learning (EDL) algorithms to optimize deep learning, so called EDL, which have obtained promising results.

TL;DR: In this article , the authors provide a clear understanding of the state-of-the-art ML models implemented for GWL modeling and the milestones achieved in this domain, as well as recommendations for possible future research directions to improve the accuracy of GWL prediction models and enhance the related knowledge.

TL;DR: In this article , an advanced shuffled frog leaping algorithm (DSSRLFLA) is developed for model evaluation and feature selection, which incorporates a dynamic step size adjustment strategy based on historical information, a specular reflection learning mechanism, and a simulated annealing mechanism based on chaotic mapping and levy flight.

TL;DR: The most outstanding recent metaheuristic feature selection algorithms of the last two decades in terms of their performance in exploration/exploitation operators, selection methods, transfer functions, fitness value evaluations, and parameter setting techniques are surveyed in this paper .

TL;DR: A comprehensive review on digital image watermarking methods that were published in recent years illustrating the conventional schemes in different domains can be found in this article , where the authors provide an overview of geometric invariant techniques and emerging watermark-based methods for novel medias, such as depth image based rendering (DIBR), high dynamic range (HDR), screen content images (SCIs), and point cloud model.

TL;DR: In this article , a comprehensive review of GAN-based anomaly detection is presented, focusing on the theoretical and technological evolution, theoretical basis, applicable tasks, and practical application of generative adversarial networks.

TL;DR: In this paper , the Polarized Self-Attention (PSA) block was proposed to solve the pixel-wise mapping problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks.

TL;DR: In this article , a comprehensive overview and survey is presented for activation functions in neural networks for deep learning, including Logistic Sigmoid, Tanh, ReLU, ELU, Swish and Mish.

TL;DR: A comprehensive survey of transfer learning on medical image analysis can be found in this article , where the authors provide a systematic knowledge about deep learning and transfer learning for beginners, and readers with different backgrounds can easily catch up with the interdisciplinary knowledge and new trends of transferring learning via this survey.

TL;DR: In this paper , the authors used a deep learning model to predict the spread of the COVID-19 outbreak to and throughout Malaysia, Morocco and Saudi Arabia, and achieved a 98.58% precision and 93.45% precision, respectively.

TL;DR: A graph convolutional network based representation learning method, namely multi-perspective social recommendation (MPSR), to construct hierarchical user preferences and assign friends’ influences with different levels of trust at varying perspectives is proposed.

TL;DR: In this article, the authors used a deep learning model to predict the spread of the COVID-19 outbreak to and throughout Malaysia, Morocco and Saudi Arabia, and achieved a 98.58% precision and 93.45% precision, respectively.

TL;DR: In this article , a CLIP4Clip model is proposed to transfer the knowledge of the image-text pretrained CLIP model to video-text tasks in an end-to-end manner.

TL;DR: Zhang et al. as mentioned in this paper proposed an end-to-end unified framework based on deep learning that does not include normalization in order to achieve improved accuracy in iris segmentation and recognition.

TL;DR: Wang et al. as discussed by the authors proposed a graph convolutional network based representation learning method, namely multi-perspective social recommendation (MPSR), to construct hierarchical user preferences and assign friends' influences with different levels of trust from varying perspectives.

TL;DR: Zhang et al. as discussed by the authors proposed a path planning with dynamic obstacle avoidance method of the manipulator based on a deep reinforcement learning algorithm soft actor-critic (SAC) to avoid the moving obstacle in the environment and make real-time planning.

TL;DR: A high-level overview of brain disorder diagnosis with fMRI images from the perspective of deep learning applications is provided to provide a high- level overview of feature engineering requirements and hence reduce domain knowledge requirements to some extent.

TL;DR: Weakly-Supervised Object Detection (WSOD) and Localization (WSOL) are long-standing and challenging tasks in object detection as discussed by the authors , and numerous techniques have been proposed in the deep learning era.

TL;DR: In this article , the authors proposed a new type of neural networks, Kronecker neural networks (KNNs), which form a general framework for neural networks with adaptive activation functions.

TL;DR: In this paper, the authors proposed a new type of neural networks, Kronecker neural networks (KNNs), which form a general framework for neural networks with adaptive activation functions.