Search Results for author:
Found 19 papers, 7 papers with code
Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training
To address this challenge, we propose a novel approach that utilizes only an image during inference while utilizing an image and LiDAR intensity during training.
Deep Attentive Time Warping
Unlike other learnable models using DTW for warping, our model predicts all local correspondences between two time series and is trained based on metric learning, which enables it to learn the optimal data-dependent warping for the target task.
Selective Scene Text Removal
Scene text removal (STR) is the image transformation task to remove text regions in scene images.
Deep Quantigraphic Image Enhancement via Comparametric Equations
Most recent methods of deep image enhancement can be generally classified into two types: decompose-and-enhance and illumination estimation-centric.
Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals
Aiming to capture subtle sound changes to reveal detailed pose information, we explicitly extract phase features from the acoustic signals together with typical spectrum features and feed them into our human pose estimation network.
Reflectance-Oriented Probabilistic Equalization for Image Enhancement
Despite recent advances in image enhancement, it remains difficult for existing approaches to adaptively improve the brightness and contrast for both low-light and normal-light images.
ConceptBeam: Concept Driven Target Speech Extraction
We use it to bridge modality-dependent information, i. e., the speech segments in the mixture, and the specified, modality-independent concept.
Font Generation with Missing Impression Labels
Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels.
Font Shape-to-Impression Translation
The versatility of Transformer allows us to realize two very different approaches for the analysis, i. e., multi-label classification and translation.
Permuton-induced Chinese Restaurant Process
Our main contribution is to introduce the notion of permutons into the well-known Chinese restaurant process (CRP) for sequence partitioning: a permuton is a probability measure on $[0, 1]\times [0, 1]$ and can be regarded as a geometric interpretation of the scaling limit of permutations.
Attention to Warp: Deep Metric Learning for Multivariate Time Series
This approach adapts a parameterized attention model to time warping for greater and more adaptive temporal invariance.
Which Parts Determine the Impression of the Font?
Various fonts give different impressions, such as legible, rough, and comic-text. This paper aims to analyze the correlation between the local shapes, or parts, and the impression of fonts.
Shared Latent Space of Font Shapes and Their Noisy Impressions
The difficulty is that the impression words attached to a font are often very noisy.
Impressions2Font: Generating Fonts by Specifying Impressions
Various fonts give us various impressions, which are often represented by words.
Baxter Permutation Process
Compared with conventional BNP models for arbitrary RPs, the proposed model is simpler and has a high affinity with Bayesian inference.
Weakly supervised collective feature learning from curated media
Through these insights, we can define human curated groups as weak labels from which our proposed framework can learn discriminative features as a representation in the space of semantic concepts the users intended when creating the groups.
Few-shot learning of neural networks from scratch by pseudo example optimization
In this paper, we propose a simple but effective method for training neural networks with a limited amount of training data.
Single-epoch supernova classification with deep convolutional neural networks
Our method first builds a convolutional neural network for estimating the luminance of supernovae from telescope images, and then constructs another neural network for the classification, where the estimated luminance and observation dates are used as features for classification.
Denoising random forests
A denoising autoencoder can be trained with indicator vectors produced from clean and noisy input samples, and non-leaf nodes where incorrect decisions are made can be identified by comparing the input and output of the trained denoising autoencoder.
