English
Related papers

Related papers: Bridging the Gap Between End-to-End and Two-Step T…

200 papers

An unconstrained end-to-end text localization and recognition method is presented. The method detects initial text hypothesis in a single pass by an efficient region-based method and subsequently refines the text hypothesis using a more…

Computer Vision and Pattern Recognition · Computer Science 2015-04-15 Lukáš Neumann , Jiří Matas

We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2017-04-05 Siyang Qin , Roberto Manduchi

In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training…

Computation and Language · Computer Science 2024-06-03 Liang Wang , Nan Yang , Xiaolong Huang , Linjun Yang , Rangan Majumder , Furu Wei

Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Renlang Huang , Yufan Tang , Jiming Chen , Liang Li

Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established learning models, such…

Machine Learning · Computer Science 2024-10-31 Wei Wu , Liang Tang , Zhongjie Zhao , Chung-Piaw Teo

Spotting user-defined/flexible keywords represented in text frequently uses an expensive text encoder for joint analysis with an audio encoder in an embedding space, which can suffer from heterogeneous modality representation (i.e., large…

Sound · Computer Science 2023-08-15 Kumari Nishu , Minsik Cho , Paul Dixon , Devang Naik

Recent works on multi-modal emotion recognition move towards end-to-end models, which can extract the task-specific features supervised by the target task compared with the two-phase pipeline. However, previous methods only model the…

Computation and Language · Computer Science 2022-09-21 Yang Wu , Pai Peng , Zhenyu Zhang , Yanyan Zhao , Bing Qin

Text simplification is a common task where the text is adapted to make it easier to understand. Similarly, text elaboration can make a passage more sophisticated, offering a method to control the complexity of reading comprehension tests.…

Computation and Language · Computer Science 2024-05-29 Asma Farajidizaji , Vatsal Raina , Mark Gales

In recent years, text-to-video retrieval methods based on CLIP have experienced rapid development. The primary direction of evolution is to exploit the much wider gamut of visual and textual cues to achieve alignment. Concretely, those…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Kaibin Tian , Yanhua Cheng , Yi Liu , Xinglin Hou , Quan Chen , Han Li

In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST) task. Utilizing…

Computation and Language · Computer Science 2023-09-22 Chen Xu , Xiaoqian Liu , Erfeng He , Yuhao Zhang , Qianqian Dong , Tong Xiao , Jingbo Zhu , Dapeng Man , Wu Yang

Sparse events, such as malign attacks in real-time network traffic, have caused big organisations an immense hike in revenue loss. This is due to the excessive growth of the network and its exposure to a plethora of people. The standard…

Cryptography and Security · Computer Science 2021-12-08 Nasreen Fathima , Akshara Pramod , Yash Srivastava , Anusha Maria Thomas , Syed Ibrahim S P , Chandran K R

Multiple object tracking (MOT) depends heavily on selection of true positive detected bounding boxes. However, this aspect of the problem is mostly overlooked or mitigated by employing two-stage association and utilizing low confidence…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Vukašin Stanojević , Branimir Todorović

Keyword Spotting (KWS) remains challenging to achieve the trade-off between small footprint and high accuracy. Recently proposed metric learning approaches improved the generalizability of models for the KWS task, and 1D-CNN based KWS…

Sound · Computer Science 2021-08-13 Li Wang , Rongzhi Gu , Nuo Chen , Yuexian Zou

Recent learning-based approaches show promising performance improvement for scene text removal task. However, these methods usually leave some remnants of text and obtain visually unpleasant results. In this work, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Xuewei Bian , Chaoqun Wang , Weize Quan , Juntao Ye , Xiaopeng Zhang , Dong-Ming Yan

In recent times, with the exception of sporadic cases, the trend in Computer Vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Antonio Bruno , Davide Moroni , Massimo Martinelli

Bilevel optimization is an important class of optimization problems where one optimization problem is nested within another. While various methods have emerged to address unconstrained general bilevel optimization problems, there has been a…

Optimization and Control · Mathematics 2024-03-15 Nazanin Abolfazli , Ruichen Jiang , Aryan Mokhtari , Erfan Yazdandoost Hamedani

We highlight a practical yet rarely discussed problem in dialogue state tracking (DST), namely handling unknown slot values. Previous approaches generally assume predefined candidate lists and thus are not designed to output unknown values,…

Computation and Language · Computer Science 2018-05-07 Puyang Xu , Qi Hu

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which…

Computation and Language · Computer Science 2022-10-19 Chen Wang , Yuchen Liu , Boxing Chen , Jiajun Zhang , Wei Luo , Zhongqiang Huang , Chengqing Zong

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…

Image and Video Processing · Electrical Eng. & Systems 2023-04-27 Xuhao Jiang , Weimin Tan , Tian Tan , Bo Yan , Liquan Shen

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

Computation and Language · Computer Science 2025-10-10 Jing Li , Zhijie Sun , Dachao Lin , Xuan He , Binfan Zheng , Yi Lin , Rongqian Zhao , Xin Chen
‹ Prev 1 8 9 10 Next ›