相关论文: Spatial Features for Multi-Font/Multi-Size Kannada…

Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, their shared latent spaces are prone to structural anomalies and act as repositories for non-semantic, multi-modal noise. To address this…

Inspired by the success of Deep Learning based approaches to English scene text recognition, we pose and benchmark scene text recognition for three Indic scripts - Devanagari, Telugu and Malayalam. Synthetic word images rendered from…

Technological advancements and innovations are advancing our daily life in all the ways possible but there is a larger section of society who are deprived of accessing the benefits due to their physical inabilities. To reap the real…

With the emergence of advanced spatial transcriptomic technologies, there has been a surge in research papers dedicated to analyzing spatial transcriptomics data, resulting in significant contributions to our understanding of biology. The…

Scene text recognition has attracted great interests from the computer vision and pattern recognition community in recent years. State-of-the-art methods use concolutional neural networks (CNNs), recurrent neural networks with long…

One-dimensional convolution is a widely used deep learning technique in prestack amplitude variation with offset (AVO) inversion; however, it lacks lateral continuity. Although two-dimensional convolution improves lateral continuity, due to…

Most of the recent successful methods in accurate object detection build on the convolutional neural networks (CNN). However, due to the lack of scale normalization in CNN-based detection methods, the activated channels in the feature space…

The powerful character variety techniques of Culler and Shalen can be used to find essential surfaces in knot manifolds. We show that module structures on the coordinate ring of the character variety can be used to identify detected…

The recent progress in sparse coding and deep learning has made unsupervised feature learning methods a strong competitor to hand-crafted descriptors. In computer vision, success stories of learned features have been predominantly reported…

Handwritten character recognition is getting popular among researchers because of its possible applications in facilitating technological search engines, social media, recommender systems, etc. The Devanagari script is one of the oldest…

Multi-channel speech enhancement extracts speech using multiple microphones that capture spatial cues. Effectively utilizing directional information is key for multi-channel enhancement. Deep learning shows great potential on multi-channel…

Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale…

When approaching the semantic segmentation of overhead imagery in the decimeter spatial resolution range, successful strategies usually combine powerful methods to learn the visual appearance of the semantic classes (e.g. convolutional…

We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content. The sparse feature…

This paper presents a robust multi-channel speaker extraction algorithm designed to handle inaccuracies in reference information. While existing approaches often rely solely on either spatial or spectral cues to identify the target speaker,…

When comparing speech sounds across languages, scholars often make use of feature representations of individual sounds in order to determine fine-grained sound similarities. Although binary feature systems for large numbers of speech sounds…

Multi-stroke characters in scripts such as Chinese and Japanese can be highly complex, posing significant challenges for both native speakers and, especially, non-native learners. If these characters can be simplified without degrading…

The problem of identifying voice commands has always been a challenge due to the presence of noise and variability in speed, pitch, etc. We will compare the efficacies of several neural network architectures for the speech recognition…

Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. We propose a multilingual text detection model to address the issues of…

An end-to-end architecture for multi-script document retrieval using handwritten signatures is proposed in this paper. The user supplies a query signature sample and the system exclusively returns a set of documents that contain the query…