Papers › NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition

NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition

16 Jul 2024arXiv:2407.11380archive 2025-07-28

Chenyu Liu, Jia Pan, Jinshui Hu, BaoCai Yin, Bing Yin, Mingjun Chen, Cong Liu, Jun Du, Qingfeng Liu

Recently, Handwritten Mathematical Expression Recognition (HMER) has gained considerable attention in pattern recognition for its diverse applications in document understanding. Current methods typically approach HMER as an image-to-sequence generation task within an autoregressive (AR) encoder-decoder framework. However, these approaches suffer from several drawbacks: 1) a lack of overall language context, limiting information utilization beyond the current decoding step; 2) error accumulation during AR decoding; and 3) slow decoding speed. To tackle these problems, this paper makes the first attempt to build a novel bottom-up Non-AutoRegressive Modeling approach for HMER, called NAMER. NAMER comprises a Visual Aware Tokenizer (VAT) and a Parallel Graph Decoder (PGD). Initially, the VAT tokenizes visible symbols and local relations at a coarse level. Subsequently, the PGD refines all tokens and establishes connectivities in parallel, leveraging comprehensive visual and linguistic contexts. Experiments on CROHME 2014/2016/2019 and HME100K datasets demonstrate that NAMER not only outperforms the current state-of-the-art (SOTA) methods on ExpRate by 1.93%/2.35%/1.49%/0.62%, but also achieves significant speedups of 13.7x and 6.7x faster in decoding time and overall FPS, proving the effectiveness and efficiency of NAMER.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderHandwritten Mathmatical Expression Recognitiondocument understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Mathmatical Expression Recognition CROHME 2014 NAMER ExpRate 60.51 #5 of 17 Archive leaderboard report
Handwritten Mathmatical Expression Recognition CROHME 2016 NAMER ExpRate 60.24 #4 of 16 Archive leaderboard report
Handwritten Mathmatical Expression Recognition CROHME 2019 NAMER ExpRate 61.72 #4 of 14 Archive leaderboard report
Handwritten Mathmatical Expression Recognition HME100K NAMER ExpRate 68.52 #4 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AWAREAttentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections