Papers › A Fast and Accurate One-Stage Approach to Visual Grounding

A Fast and Accurate One-Stage Approach to Visual Grounding

18 Aug 2019ICCV 2019 10arXiv:1908.06354archive 2025-07-28

Zhengyuan Yang, Boqing Gong, Li-Wei Wang, Wenbing Huang, Dong Yu, Jiebo Luo

We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight. The performances of existing propose-and-rank two-stage methods are capped by the quality of the region candidates they propose in the first stage --- if none of the candidates could cover the ground truth region, there is no hope in the second stage to rank the right region to the top. To avoid this caveat, we propose a one-stage model that enables end-to-end joint optimization. The main idea is as straightforward as fusing a text query's embedding into the YOLOv3 object detector, augmented by spatial features so as to account for spatial mentions in the query. Despite being simple, this one-stage approach shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension, according to our experiments. Given these results along with careful investigations into some popular region proposals, we advocate for visual grounding a paradigm shift from the conventional two-stage methods to the one-stage framework.

PaperPDFConference PDFCodeCode 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="1908.06354")

Code

Syntology Ran 1 of 19 code samples harvested from 1 repository linked to this paper; 18 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 19 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zyang-ur/onestage_grounding officialmentioned on GitHubpytorchMIT report
zyang-ur/ReSC mentioned on GitHubpytorchMIT 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; 1 ran; 1 honoured the contract we drafted; 18 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 · honoured contract
18unverified

Licence: 0 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 zyang-ur/onestage_grounding. “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.

lr_poly zyang-ur/onestage_grounding/train_yolo.py official repository ran · honoured contract fingerprinted MIT (permissive) · b3b7c1c716f4ca66 · report
bbox_iou_numpy zyang-ur/onestage_grounding/utils/utils.py official repository unverified MIT (permissive) · ec48fe4bebce9e11 · report
bbox_randscale zyang-ur/onestage_grounding/dataset/referit_loader.py official repository unverified MIT (permissive) · 9811fc4335a757ba · report
body_region_confusion_matrix zyang-ur/onestage_grounding/utils/parsing_metrics.py official repository unverified MIT (permissive) · 419a432ce9a6b3ad · report
build_object_targets zyang-ur/onestage_grounding/model/darknet.py official repository unverified MIT (permissive) · 94ef5f8ebf328450 · report
build_target zyang-ur/onestage_grounding/train_yolo.py official repository unverified MIT (permissive) · df36ec87b420dbdf · report
convert_examples_to_features zyang-ur/onestage_grounding/dataset/referit_loader.py official repository unverified MIT (permissive) · 694e413f977737ba · report
create_modules zyang-ur/onestage_grounding/model/darknet.py official repository unverified MIT (permissive) · a57e101603c7a691 · report
generate_coord zyang-ur/onestage_grounding/model/grounding_model.py official repository unverified MIT (permissive) · 0336cb59d505cda3 · report
label_accuracy_score zyang-ur/onestage_grounding/utils/parsing_metrics.py official repository unverified MIT (permissive) · 47314d0f58b9e44b · report
label_confusion_matrix zyang-ur/onestage_grounding/utils/parsing_metrics.py official repository unverified MIT (permissive) · c7ccdc37dfee61f7 · report
letterbox zyang-ur/onestage_grounding/utils/transforms.py official repository unverified MIT (permissive) · 7d95e42ef6cbd96a · report
parse_model_config zyang-ur/onestage_grounding/model/darknet.py official repository unverified MIT (permissive) · 7541c25367bf48c2 · report
random_affine zyang-ur/onestage_grounding/utils/transforms.py official repository unverified MIT (permissive) · 408bfee1417b817e · report
read_examples zyang-ur/onestage_grounding/dataset/referit_loader.py official repository unverified MIT (permissive) · e4f50d4eeb6144e9 · report
wrap_points zyang-ur/onestage_grounding/utils/transforms.py official repository unverified MIT (permissive) · cb5d2317201b6913 · report
xywh2xyxy zyang-ur/onestage_grounding/utils/utils.py official repository unverified MIT (permissive) · 39509f649c31ad13 · report
xyxy2xywh zyang-ur/onestage_grounding/utils/utils.py official repository unverified MIT (permissive) · a43bd5ac31eb7191 · report
yolo_loss zyang-ur/onestage_grounding/train_yolo.py official repository unverified MIT (permissive) · 13969771dccff2bc · report

Tasks

Referring ExpressionReferring Expression ComprehensionVisual Grounding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionGlobal Average PoolingLogistic RegressionResidual ConnectionSPEEDSoftmaxYOLOv3k-Means Clustering

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