English
Related papers

Related papers: VOLTAGE: A Versatile Contrastive Learning based OC…

200 papers

Dialect differences caused by regional, social, and economic factors cause performance discrepancies for many groups of language technology users. Inclusive and equitable language technology must critically be dialect invariant, meaning…

Computation and Language · Computer Science 2023-05-31 Caleb Ziems , William Held , Jingfeng Yang , Jwala Dhamala , Rahul Gupta , Diyi Yang

In this work, we propose a new pooling strategy for language identification by considering Indian languages. The idea is to obtain utterance level features for any variable length audio for robust language recognition. We use the GhostVLAD…

Computation and Language · Computer Science 2020-02-06 Krishna D N , Ankita Patil , M. S. P Raj , Sai Prasad H S , Prabhu Aashish Garapati

We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Yulong Zhang

Optical Character Recognition (OCR) on contemporary and historical data is still in the focus of many researchers. Especially historical prints require book specific trained OCR models to achieve applicable results (Springmann and…

Computer Vision and Pattern Recognition · Computer Science 2021-01-15 Christoph Wick , Christian Reul , Frank Puppe

Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-09 Mehmet Can Yavuz , Berrin Yanikoglu

We propose a post-OCR text correction approach for digitising texts in Romanised Sanskrit. Owing to the lack of resources our approach uses OCR models trained for other languages written in Roman. Currently, there exists no dataset…

Computation and Language · Computer Science 2018-09-10 Amrith Krishna , Bodhisattwa Prasad Majumder , Rajesh Shreedhar Bhat , Pawan Goyal

The natural language generation domain has witnessed great success thanks to Transformer models. Although they have achieved state-of-the-art generative quality, they often neglect generative diversity. Prior attempts to tackle this issue…

Computation and Language · Computer Science 2024-03-20 Yueen Ma , Dafeng Chi , Jingjing Li , Kai Song , Yuzheng Zhuang , Irwin King

Phoneme recognition is a largely unsolved problem in NLP, especially for low-resource languages like Urdu. The systems that try to extract the phonemes from audio speech require hand-labeled phonetic transcriptions. This requires expert…

Computation and Language · Computer Science 2022-04-19 Saad Naeem , Omer Beg

Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-28 Dongji Gao , Hainan Xu , Desh Raj , Leibny Paola Garcia Perera , Daniel Povey , Sanjeev Khudanpur

Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lead to performance bottlenecks and unsatisfactory…

Computation and Language · Computer Science 2024-10-29 Xun Guo , Shan Zhang , Yongxin He , Ting Zhang , Wanquan Feng , Haibin Huang , Chongyang Ma

In this paper, an efficient fragile blind quad watermarking scheme for image tamper detection and recovery based on lifting wavelet transform and genetic algorithm is proposed. TRLG generates four compact digests with super quality based on…

Cryptography and Security · Computer Science 2018-03-09 Behrouz Bolourian Haghighi , Amir Hossein Taherinia , Amir Hossein Mohajerzadeh

Optical character recognition (OCR) is a process of converting analogue documents into digital using document images. Currently, many commercial and non-commercial OCR systems exist for both handwritten and printed copies for different…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Farisa Benta Safir , Abu Quwsar Ohi , M. F. Mridha , Muhammad Mostafa Monowar , Md. Abdul Hamid

Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across…

Sound · Computer Science 2026-03-24 Ro-hoon Oh , Jihwan Seol , Bugeun Kim

Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the \textit{de-facto} standard for knowledge graph completion. Most existing KGE methods suffer from the sparsity challenge, where…

Artificial Intelligence · Computer Science 2023-02-14 Zhaoxuan Tan , Zilong Chen , Shangbin Feng , Qingyue Zhang , Qinghua Zheng , Jundong Li , Minnan Luo

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

Machine Learning · Computer Science 2022-01-04 Yihang Yin , Qingzhong Wang , Siyu Huang , Haoyi Xiong , Xiang Zhang

Sign languages, often categorised as low-resource languages, face significant challenges in achieving accurate translation due to the scarcity of parallel annotated datasets. This paper introduces Select and Reorder (S&R), a novel approach…

Computation and Language · Computer Science 2024-04-18 Harry Walsh , Ben Saunders , Richard Bowden

Recognizing characters from low-resolution (LR) text images poses a significant challenge due to the information deficiency as well as the noise and blur in low-quality images. Current solutions for low-resolution text recognition (LTR)…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Hang Guo , Tao Dai , Mingyan Zhu , Guanghao Meng , Bin Chen , Zhi Wang , Shu-Tao Xia

Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Junyuan Zhang , Qintong Zhang , Bin Wang , Linke Ouyang , Zichen Wen , Ying Li , Ka-Ho Chow , Conghui He , Wentao Zhang

Contrary to popular belief, Optical Character Recognition (OCR) remains a challenging problem when text occurs in unconstrained environments, like natural scenes, due to geometrical distortions, complex backgrounds, and diverse fonts. In…

Computer Vision and Pattern Recognition · Computer Science 2019-06-06 Marcin Namysl , Iuliu Konya

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Bichen Wu , Ruizhe Cheng , Peizhao Zhang , Tianren Gao , Peter Vajda , Joseph E. Gonzalez
‹ Prev 1 3 4 5 6 7 10 Next ›