Papers › VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations

VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations

13 May 2021arXiv:2105.06220archive 2025-07-28

Peng Zhang, Can Li, Liang Qiao, Zhanzhan Cheng, ShiLiang Pu, Yi Niu, Fei Wu

Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to the understanding process. Though many works have been proposed to exploit the above information, they show unsatisfactory results. NLP-based methods model layout analysis as a sequence labeling task and show insufficient capabilities in layout modeling. CV-based methods model layout analysis as a detection or segmentation task, but bear limitations of inefficient modality fusion and lack of relation modeling between layout components. To address the above limitations, we propose a unified framework VSR for document layout analysis, combining vision, semantics and relations. VSR supports both NLP-based and CV-based methods. Specifically, we first introduce vision through document image and semantics through text embedding maps. Then, modality-specific visual and semantic features are extracted using a two-stream network, which are adaptively fused to make full use of complementary information. Finally, given component candidates, a relation module based on graph neural network is incorported to model relations between components and output final results. On three popular benchmarks, VSR outperforms previous models by large margins. Code will be released soon.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

hikopensource/davar-lab-ocr officialpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to You Only Recognize Once: Towards Fast Video Text Spotting (arXiv:1903.03299; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Document Layout AnalysisGraph Neural Network

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Layout Analysis PubLayNet val VSR Figure 0.964 #3 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val VSR List 0.947 #3 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val VSR Overall 0.957 #3 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val VSR Table 0.974 #3 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val VSR Text 0.967 #3 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val VSR Title 0.931 #3 of 15 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

Graph Neural Network

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