18 June 2019 in Computational Intelligence
18 December 2019 in IEEE Access
Generative adversarial networks (GANs) have shown significant progress in generating highquality visual samples, however they are still well known both for being unstable to train and for the problem of mode collapse, particularly when trained on data collections containing a diverse set of visual objects. In this paper, we propose an Adaptive k-step Generative Adversarial Network (Ak-GAN), which is designed to mitigate the impact of instability and saturation in the original by dynamically adjusting the ratio of the training steps of both the generator and discriminator. To accomplish this, we track and analyze stable training curves of relatively narrow datasets and use them as the target fitting lines when training more diverse data collections. Furthermore, we conduct experiments on the proposed procedure using several optimization techniques (e.g., supervised guiding from previous stable learning curves with and without momentum) and compare their performance with that of state-of-the-art models on the task of image synthesis from datasets consisting of diverse images. Empirical results demonstrate that Ak-GAN works well in practice and exhibits more stable behavior than regular GANs during training. A quantitative evaluation has been conducted on the Inception Score (IS) and the relative inverse Inception Score (RIS); compared with regular GANs, the former has been improved by 61% and 83%, and the latter by 21% and 60%, on the CelebA and the Anime datasets, respectively.
4 April 2022 in Computational Intelligence
7 September 2020 in IEEE Access
Target tracking based on Siamese network has reached the state-of-the-art performance. However is still limited in semantic feature extraction. In this paper, we propose a novel method to distinguish positive and negative samples. Taking deep neural network as the backbone, we fuse the feature maps from different layers and feed it to RPN (Region Proposal Network). In addition, we use a loss term for loss function to achieve self-adjusting and learn more discriminative embedding features of target objects with similar semantics. In the tracking stage, one-shot detection is used as the reference, fix the first frame as the weight of tracking to track the subsequent frames. Our method has achieved outstanding performance on several benchmark data set,such as: OTB2015, VOT2016, VOT2018, and VOT2019 et al.
1 January 2016 in Mobile Information Systems
Ak-range nearest neighbor (kRNN) query in a spatial network finds thekclosest objects to each point in the query region. The essential nature of thekRNN query is significant in location-based services (LBSs), where location-aware queries with query regions such askRNN queries are frequently used because of the issue of location privacy and the imprecision of the associated positioning techniques. Existing studies focus on reducing computation costs at the server side while processingkRNN queries. They also consider snapshot queries that are evaluated once and terminated, as opposed to moving queries that require constant updating of their results. However, little attention has been paid to evaluating movingkRNN queries in directed and dynamic spatial networks where every edge is directed and its weight changes in accordance with the traffic conditions. In this paper, we propose an efficient algorithm called MORAN that evaluates movingk-range nearest neighbor (MkRNN) queries in directed and dynamic spatial networks. The results of a simulation conducted using real-life roadmaps indicate that MORAN is more effective than a competitive method based on a shared execution approach.
8 March 2024 in IET Computer Vision
Sign Language Production (SLP) refers to the task of translating textural forms of spoken language into corresponding sign language expressions. Sign languages convey meaning by means of multiple asynchronous articulators, including manual and non‐manual information channels. Recent deep learning‐based SLP models directly generate the full‐articulatory sign sequence from the text input in an end‐to‐end manner. However, these models largely down weight the importance of subtle differences in the manual articulation due to the effect of regression to the mean. To explore these neglected aspects, an efficient cascade dual‐decoder Transformer (CasDual‐Transformer) for SLP is proposed to learn, successively, two mappings SLP
hand
: Text → Hand pose and SLP sign : Text → Sign pose , utilising an attention‐based alignment module that fuses the hand and sign features from previous time steps to predict more expressive sign pose at the current time step. In addition, to provide more efficacious guidance, a novel spatio‐temporal loss to penalise shape dissimilarity and temporal distortions of produced sequences is introduced. Experimental studies are performed on two benchmark sign language datasets from distinct cultures to verify the performance of the proposed model. Both quantitative and qualitative results show that the authors’ model demonstrates competitive performance compared to state‐of‐the‐art models, and in some cases, achieves considerable improvements over them.