用单一序列生成表格结构、内容和位置，无需复杂后处理。
TableSeq: Unified Generation of Structure, Content, and Layout
- 将表格识别统一为序列生成任务，输出HTML标签、文本和坐标令牌
- 在PubTabNet上达95.23 TEDS，FinTabNet上98.69 S-TEDS，表现领先
- 支持无任务头的索引查询，适合需要灵活交互的应用
我们提出TableSeq，一种仅以图像为输入的端到端框架，联合完成表格结构识别、内容识别与单元格定位。该模型将这些任务统一为单序列生成问题：一个解码器输出交错的HTML标签、单元格文本和离散坐标标记，从而在统一的自回归序列中对齐逻辑结构、文本内容与几何位置。该设计避免了外部OCR、辅助解码器和复杂多阶段后处理。TableSeq结合轻量级高分辨率FCN-H16编码器、最小结构先验头和单层Transformer编码器，形成紧凑架构，在复杂布局上仍保持高效。在标准基准上，TableSeq达到竞争性或顶尖性能：在PubTabNet上取得95.23 TEDS / 96.83 S-TEDS，FinTabNet上97.45 TEDS / 98.69 S-TEDS，SciTSR上在CAR协议下实现99.79 / 99.54 / 99.66的精确率/召回率/F1，同时在PubTables-1M上保持竞争力。此外，相同序列接口可泛化至基于索引的表格查询，无需特定任务头，取得最佳IRDR分数及有竞争力的ICDR/ICR表现。我们还研究多标记预测以加速块级解码，证明其可在精度损失有限下降低推理延迟。总体而言，TableSeq提供了一个实用且可复现的统一表格识别单流基线，源码将公开于https://github.com/hamdilaziz/TableSeq。
原文摘要 · Abstract (English)
We present TableSeq, an image-only, end-to-end framework for joint table structure recognition, content recognition, and cell localization. The model formulates these tasks as a single sequence-generation problem: one decoder produces an interleaved stream of \texttt{HTML} tags, cell text, and discretized coordinate tokens, thereby aligning logical structure, textual content, and cell geometry within a unified autoregressive sequence. This design avoids external OCR, auxiliary decoders, and complex multi-stage post-processing. TableSeq combines a lightweight high-resolution FCN-H16 encoder with a minimal structure-prior head and a single-layer transformer encoder, yielding a compact architecture that remains effective on challenging layouts. Across standard benchmarks, TableSeq achieves competitive or state-of-the-art results while preserving architectural simplicity. It reaches 95.23 TEDS / 96.83 S-TEDS on PubTabNet, 97.45 TEDS / 98.69 S-TEDS on FinTabNet, and 99.79 / 99.54 / 99.66 precision / recall / F1 on SciTSR under the CAR protocol, while remaining competitive on PubTables-1M under GriTS. Beyond TSR/TCR, the same sequence interface generalizes to index-based table querying without task-specific heads, achieving the best IRDR score and competitive ICDR/ICR performance. We also study multi-token prediction for faster blockwise decoding and show that it reduces inference latency with only limited accuracy degradation. Overall, TableSeq provides a practical and reproducible single-stream baseline for unified table recognition, and the source code will be made publicly available at https://github.com/hamdilaziz/TableSeq.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。