FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296902001> ?p ?o ?g. }

• W4296902001 endingPage "414" @default.
• W4296902001 startingPage "385" @default.
• W4296902001 abstract "Purpose. Handwriting is one of the most frequently occurring patterns in everyday life and with it come challenging applications such as handwriting recognition (HWR), writer identification, and signature verification. In contrast to offline HWR that only uses spatial information (i.e., images), online HWR (OnHWR) uses richer spatio-temporal information (i.e., trajectory data or inertial data). While there exist many offline HWR datasets, there is only little data available for the development of OnHWR methods on paper as it requires hardware-integrated pens. Methods. This paper presents data and benchmark models for real-time sequence-to-sequence (seq2seq) learning and single character-based recognition. Our data is recorded by a sensor-enhanced ballpoint pen, yielding sensor data streams from triaxial accelerometers, a gyroscope, a magnetometer and a force sensor at 100 Hz. We propose a variety of datasets including equations and words for both the writer-dependent and writer-independent tasks. Our datasets allow a comparison between classical OnHWR on tablets and on paper with sensor-enhanced pens. We provide an evaluation benchmark for seq2seq and single character-based HWR using recurrent and temporal convolutional networks and Transformers combined with a connectionist temporal classification (CTC) loss and cross-entropy (CE) losses. Results. Our convolutional network combined with BiLSTMs outperforms Transformer-based architectures, is on par with InceptionTime for sequence-based classification tasks, and yields better results compared to 28 state-of-the-art techniques. Time-series augmentation methods improve the sequence-based task, and we show that CE variants can improve the single classification task." @default.
• W4296902001 created "2022-09-24" @default.
• W4296902001 creator A5023277657 @default.
• W4296902001 creator A5035080679 @default.
• W4296902001 creator A5048067051 @default.
• W4296902001 creator A5049110928 @default.
• W4296902001 creator A5067248213 @default.
• W4296902001 creator A5069072700 @default.
• W4296902001 creator A5073940195 @default.
• W4296902001 date "2022-09-22" @default.
• W4296902001 modified "2023-10-18" @default.
• W4296902001 title "Benchmarking online sequence-to-sequence and character-based handwriting recognition from IMU-enhanced pens" @default.
• W4296902001 cites W1483628210 @default.
• W4296902001 cites W1901129140 @default.
• W4296902001 cites W1988305328 @default.
• W4296902001 cites W1989411205 @default.
• W4296902001 cites W1999019778 @default.
• W4296902001 cites W2003190201 @default.
• W4296902001 cites W2009781111 @default.
• W4296902001 cites W2012616030 @default.
• W4296902001 cites W2018970719 @default.
• W4296902001 cites W2024925205 @default.
• W4296902001 cites W2025563211 @default.
• W4296902001 cites W2053317383 @default.
• W4296902001 cites W2065546971 @default.
• W4296902001 cites W2066792529 @default.
• W4296902001 cites W2077863651 @default.
• W4296902001 cites W2081018036 @default.
• W4296902001 cites W2084547331 @default.
• W4296902001 cites W2084859622 @default.
• W4296902001 cites W2106132157 @default.
• W4296902001 cites W2116881180 @default.
• W4296902001 cites W2122585011 @default.
• W4296902001 cites W2127141656 @default.
• W4296902001 cites W2139975583 @default.
• W4296902001 cites W2142069714 @default.
• W4296902001 cites W2147393756 @default.
• W4296902001 cites W2147510700 @default.
• W4296902001 cites W2149872361 @default.
• W4296902001 cites W2152550252 @default.
• W4296902001 cites W2153873029 @default.
• W4296902001 cites W2165391559 @default.
• W4296902001 cites W2169848562 @default.
• W4296902001 cites W2172090196 @default.
• W4296902001 cites W2198918026 @default.
• W4296902001 cites W2396666837 @default.
• W4296902001 cites W2507888814 @default.
• W4296902001 cites W2526425061 @default.
• W4296902001 cites W2551393996 @default.
• W4296902001 cites W2573601984 @default.
• W4296902001 cites W2754051771 @default.
• W4296902001 cites W2782808446 @default.
• W4296902001 cites W2783323081 @default.
• W4296902001 cites W2786974559 @default.
• W4296902001 cites W2791089502 @default.
• W4296902001 cites W2796208452 @default.
• W4296902001 cites W2808955427 @default.
• W4296902001 cites W2895359355 @default.
• W4296902001 cites W2904388869 @default.
• W4296902001 cites W2904714269 @default.
• W4296902001 cites W2906383034 @default.
• W4296902001 cites W2906436882 @default.
• W4296902001 cites W2963351448 @default.
• W4296902001 cites W2963855133 @default.
• W4296902001 cites W2963924711 @default.
• W4296902001 cites W2964274690 @default.
• W4296902001 cites W2964325005 @default.
• W4296902001 cites W2965301120 @default.
• W4296902001 cites W2967141048 @default.
• W4296902001 cites W2981873476 @default.
• W4296902001 cites W2993065570 @default.
• W4296902001 cites W2998010409 @default.
• W4296902001 cites W3003428515 @default.
• W4296902001 cites W3004690717 @default.
• W4296902001 cites W3009456793 @default.
• W4296902001 cites W3013952048 @default.
• W4296902001 cites W3025111165 @default.
• W4296902001 cites W3034726763 @default.
• W4296902001 cites W3034904792 @default.
• W4296902001 cites W3084430883 @default.
• W4296902001 cites W3086834600 @default.
• W4296902001 cites W3087417110 @default.
• W4296902001 cites W3101667008 @default.
• W4296902001 cites W3105625590 @default.
• W4296902001 cites W3106274667 @default.
• W4296902001 cites W3176254532 @default.
• W4296902001 cites W3188872815 @default.
• W4296902001 cites W3198848843 @default.
• W4296902001 cites W3201229310 @default.
• W4296902001 cites W3202364339 @default.
• W4296902001 cites W4200110030 @default.
• W4296902001 cites W4213324236 @default.
• W4296902001 cites W4220707558 @default.
• W4296902001 cites W4304092624 @default.
• W4296902001 doi "https://doi.org/10.1007/s10032-022-00415-6" @default.
• W4296902001 hasPublicationYear "2022" @default.
• W4296902001 type Work @default.
• W4296902001 citedByCount "4" @default.

• next