Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention

• URL: http://arxiv.org/abs/2607.00057v1
• Date: Tue, 30 Jun 2026 07:48:05 GMT
• Title: Enhancing Oracle Bone Inscription Recognition via Multi-Scale Layer Attention
• Abstract summary: Oracle Bone Inscriptions (OBIs) recognition plays a crucial role in understanding ancient Chinese culture.<n>Traditional methods rely on expert knowledge and manual analysis, which are time-consuming and error-prone.<n>We propose Multi-Scale Layer Attention (MSLA), a novel paradigm that explicitly models both multi-scale and cross-layer feature interactions.
• Score: 15.00246240540568
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Oracle Bone Inscriptions (OBIs) recognition plays a crucial role in understanding ancient Chinese culture. However, accurately recognizing OBIs remains highly challenging due to their complex, irregular, and often degraded shapes. Traditional methods rely on expert knowledge and manual analysis, which are time-consuming and error-prone. Although deep learning has greatly advanced general image recognition, existing methods struggle to capture the fine-grained details and subtle variations inherent in OBIs, resulting in limited performance. Even most recent and effective layer attention techniques are designed to capture fine-grained dependencies through enhanced inter-layer interactions, yet they still exhibit only marginal improvements in OBIs recognition. To address these limitations, we propose Multi-Scale Layer Attention (MSLA), a novel paradigm that explicitly models both multi-scale and cross-layer feature interactions. By enriching the representation with fine-grained details across multiple spatial scales, MSLA enables more accurate and robust OBIs recognition. Extensive experiments on large-scale OBIs datasets demonstrate that MSLA consistently outperforms existing attention mechanisms while maintaining computational efficiency.

Related papers

• Beyond Single Character: Evaluating MLLMs for Sentence-Level Oracle Bone Inscription Understanding [52.79561716745463]
  We introduce S-OBI, a novel benchmark for evaluating MLLMs in Sentence-level OBI understanding.<n>S-OBI synthesizes clear and standardized sentence-level OBI instances through glyph substitution and composition.<n>Experiments reveal the inferiority of contemporary MLLMs on sentence-level OBI understanding.
  arXiv  Detail & Related papers  (2026-06-30T05:59:44Z)
• A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts [80.98474052840929]
  Gated attention has been empirically demonstrated to increase the expressiveness of low-rank mapping in standard attention.<n>We show that each entry in a gated attention matrix or a multi-head self-attention matrix can be written as a hierarchical mixture of experts.
  arXiv  Detail & Related papers  (2026-02-01T22:22:13Z)
• Granular-ball Guided Masking: Structure-aware Data Augmentation [97.18560547134587]
  Granular-ball Guided Masking (GBGM) is a structure-aware augmentation strategy guided by Granular-ball Computing (GBC)<n>GBGM adaptively preserves semantically rich, structurally important regions while suppressing redundant areas through a coarse-to-fine hierarchical masking process.<n>Experiments on multiple benchmarks demonstrate consistent improvements in classification accuracy and masked image reconstruction.
  arXiv  Detail & Related papers  (2025-12-24T07:15:33Z)
• LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection [7.094483187879095]
  LEAF is a novel and robust expert-based framework for Continual Event Detection.<n>It incorporates a specialized mixture of experts architecture into the base model, where each expert is parameterized with low-rank adaptation (LoRA) matrices.<n>A semantic-aware expert selection mechanism dynamically routes instances to the most relevant experts, enabling expert specialization and reducing knowledge interference.
  arXiv  Detail & Related papers  (2025-09-29T10:00:25Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark [36.21507457913964]
  oracle bone inscription (OBI) recognition plays a significant role in understanding the history and culture of ancient China.<n>The existing OBI datasets suffer from a long-tail distribution problem, leading to biased performance of OBI recognition models across majority and minority classes.<n>We present the Oracle-P15K, a structure-aligned OBI dataset for OBI generation and denoising, consisting of 14,542 images infused with domain knowledge from OBI experts.
  arXiv  Detail & Related papers  (2025-04-13T13:03:25Z)
• Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character Recognition [59.05212866862219]
  The study of oracle characters plays an important role in Chinese archaeology and philology. The difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition. We develop a novel unsupervised domain adaptation (UDA) method to transfer recognition knowledge from labeled handprinted oracle characters to unlabeled scanned data.
  arXiv  Detail & Related papers  (2024-09-24T09:07:05Z)
• Bengali Sign Language Recognition through Hand Pose Estimation using Multi-Branch Spatial-Temporal Attention Model [0.5825410941577593]
  We propose a spatial-temporal attention-based BSL recognition model considering hand joint skeletons extracted from the sequence of images. Our model captures discriminative structural displacements and short-range dependency based on unified joint features projected onto high-dimensional feature space.
  arXiv  Detail & Related papers  (2024-08-26T08:55:16Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• Axial-LOB: High-Frequency Trading with Axial Attention [0.0]
  Axial-LOB is a novel fully-attentional deep learning architecture for predicting price movements of stocks from limit order book (LOB) data. Our architecture is able to construct feature maps that incorporate global interactions, while significantly reducing the size of the parameter space. The effectiveness of Axial-LOB is demonstrated on a large benchmark dataset, containing time series representations of millions of high-frequency trading events.
  arXiv  Detail & Related papers  (2022-12-04T12:11:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.