Papers › A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer

A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer

9 Dec 2021arXiv:2112.04888archive 2025-07-28

Weijia Wu, Yuanqiang Cai, Debing Zhang, Sibo Wang, Zhuang Li, Jiahong Li, Yejun Tang, Hong Zhou

Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVText. Firstly, we provide 2,000+ videos with more than 1,750,000+ frames, 25 times larger than the existing largest dataset with incidental text in videos. Secondly, our dataset covers 30+ open categories with a wide selection of various scenarios, e.g., Life Vlog, Driving, Movie, etc. Thirdly, abundant text types annotation (i.e., title, caption or scene text) are provided for the different representational meanings in video. Fourthly, the BOVText provides bilingual text annotation to promote multiple cultures live and communication. Besides, we propose an end-to-end video text spotting framework with Transformer, termed TransVTSpotter, which solves the multi-orient text spotting in video with a simple, but efficient attention-based query-key mechanism. It applies object features from the previous frame as a tracking query for the current frame and introduces a rotation angle prediction to fit the multiorient text instance. On ICDAR2015(video), TransVTSpotter achieves the state-of-the-art performance with 44.1% MOTA, 9 fps. The dataset and code of TransVTSpotter can be found at github:com=weijiawu=BOVText and github:com=weijiawu=TransVTSpotter, respectively.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2112.04888")

Code

Syntology Ran 16 of 19 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 14 ran with no contract checked.

By repository: official repository: 19 samples from 2 repositories, 16 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

weijiawu/BOVText-Benchmark officialmentioned in papermentioned on GitHub report
weijiawu/transvtspotter officialmentioned in papermentioned on GitHubpytorch report
weijiawu/MMVText-Benchmark mentioned on GitHubCC-BY-4.0 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.

Code Syntology ran Syntology

19 samples harvested; 16 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
14ran
3unverified

Licence: 19 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

add_expensive_edges weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/lap.py official repository ran fingerprinted CC-BY-4.0 · pointer only · 75c50b21f10622fe · report
dice_loss weijiawu/transvtspotter/models/segmentation.py official repository ran · violated contract fingerprinted no licence file found · pointer only · ac8fe530cdad4d8c · report
get_rotate_mat weijiawu/transvtspotter/models/save_track.py official repository ran fingerprinted no licence file found · pointer only · 934f6f437dd35300 · report
load_motchallenge weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/io.py official repository ran CC-BY-4.0 · pointer only · df7c890d21316ed3 · report
lsa_solve_scipy weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/lap.py official repository ran fingerprinted CC-BY-4.0 · pointer only · 73aafda163f7eb35 · report
norm2squared_matrix weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/distances.py official repository ran fingerprinted CC-BY-4.0 · pointer only · 8aac7a69af7327b2 · report
num_frames weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/metrics.py official repository ran CC-BY-4.0 · pointer only · c226fad167ab7651 · report
obj_frequencies weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/metrics.py official repository ran CC-BY-4.0 · pointer only · fd57be74b7693046 · report
pred_frequencies weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/metrics.py official repository ran CC-BY-4.0 · pointer only · b443457d657ce785 · report
quiet_divide weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/math_util.py official repository ran fingerprinted CC-BY-4.0 · pointer only · 8c8460f479f8b77e · report
read_mot_results weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/tracking_utils/io.py official repository ran CC-BY-4.0 · pointer only · 9a73f2c41ea25d0b · report
read_results weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/tracking_utils/io.py official repository ran CC-BY-4.0 · pointer only · 3b4276dfe539afa3 · report
read_text_results weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/tracking_utils/io.py official repository ran CC-BY-4.0 · pointer only · 65529c5a828c8fac · report
rect_min_max weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/distances.py official repository ran fingerprinted CC-BY-4.0 · pointer only · d8bed56ba7a09f52 · report
sigmoid_focal_loss weijiawu/transvtspotter/models/segmentation.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 5c0711aada67957e · report
sort_key weijiawu/transvtspotter/models/save_track.py official repository ran no licence file found · pointer only · eedc05e12aec5bd3 · report
linear_sum_assignment weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/lap.py official repository unverified CC-BY-4.0 · pointer only · afa1b0e940655c4c · report
load_detrac_mat weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/io.py official repository unverified CC-BY-4.0 · pointer only · 5bd3eff2e6eab7ba · report
load_vatictxt weijiawu/BOVText-Benchmark/Evaluation_Protocol/Task1_VideoTextTracking/motmetrics/io.py official repository unverified CC-BY-4.0 · pointer only · 56d557c272771a4b · report

Tasks

Text Spottingtext annotation

Datasets

Introduced by this paper, per the archive.

BOVText

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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