Related papers: Intrapersonal Parameter Optimization for Offline H…
In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation…
Photorealistic avatars are human avatars that look, move, and talk like real people. The performance of photorealistic avatars has significantly improved recently based on objective metrics such as PSNR, SSIM, LPIPS, FID, and FVD. However,…
The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models. However, these tissue properties are spatially varying across the underlying anatomical model,…
Interest in automatic people re-identification systems has significantly grown in recent years, mainly for developing surveillance and smart shops software. Due to the variability in person posture, different lighting conditions, and…
The 'signature method' refers to a collection of feature extraction techniques for multivariate time series, derived from the theory of controlled differential equations. There is a great deal of flexibility as to how this method can be…
In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…
Representing a space of handwriting stroke styles includes the challenge of representing both the style of each character and the overall style of the human writer. Existing VRNN approaches to representing handwriting often do not…
Collective variable (CV) or order parameter based enhanced sampling algorithms have achieved great success due to their ability to efficiently explore the rough potential energy landscapes of complex systems. However, the degeneracy of…
This paper presents a new voice impersonation attack using voice conversion (VC). Enrolling personal voices for automatic speaker verification (ASV) offers natural and flexible biometric authentication systems. Basically, the ASV systems do…
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most methods mainly focus on the instance level information (\ie,…
While many algorithms for diversity maximization under imitation constraints are online in nature, many applications require offline algorithms without environment interactions. Tackling this problem in the offline setting, however,…
As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. In previous DG…
This research introduces an innovative approach to explore the cognitive and biologically inspired underpinnings of feature vector splitting for analyzing the significance of different attributes in e-security biometric signature…
End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition…
Audio-visual speech recognition has received a lot of attention due to its robustness against acoustic noise. Recently, the performance of automatic, visual, and audio-visual speech recognition (ASR, VSR, and AV-ASR, respectively) has been…
The augmentation parameters matter to few-shot semantic segmentation since they directly affect the training outcome by feeding the networks with varying perturbated samples. However, searching optimal augmentation parameters for few-shot…
In the past, optimization-based registration models have used spatially-varying regularization to account for deformation variations in different image regions. However, deep learning-based registration models have mostly relied on…
Generative adversarial networks (GANs) have made remarkable achievements in synthesizing images in recent years. Typically, training GANs requires massive data, and the performance of GANs deteriorates significantly when training data is…
Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…
Handwriting recognition is one of the desirable attributes of document comprehension and analysis. It is concerned with the documents writing style and characteristics that distinguish the authors. The diversity of text images, notably in…