Papers › Zero-Shot Grounding of Objects from Natural Language Queries

Zero-Shot Grounding of Objects from Natural Language Queries

20 Aug 2019ICCV 2019 10arXiv:1908.07129archive 2025-07-28

Arka Sadhu, Kan Chen, Ram Nevatia

A phrase grounding system localizes a particular object in an image referred to by a natural language query. In previous work, the phrases were restricted to have nouns that were encountered in training, we extend the task to Zero-Shot Grounding(ZSG) which can include novel, "unseen" nouns. Current phrase grounding systems use an explicit object detection network in a 2-stage framework where one stage generates sparse proposals and the other stage evaluates them. In the ZSG setting, generating appropriate proposals itself becomes an obstacle as the proposal generator is trained on the entities common in the detection and grounding datasets. We propose a new single-stage model called ZSGNet which combines the detector network and the grounding system and predicts classification scores and regression parameters. Evaluation of ZSG system brings additional subtleties due to the influence of the relationship between the query and learned categories; we define four distinct conditions that incorporate different levels of difficulty. We also introduce new datasets, sub-sampled from Flickr30k Entities and Visual Genome, that enable evaluations for the four conditions. Our experiments show that ZSGNet achieves state-of-the-art performance on Flickr30k and ReferIt under the usual "seen" settings and performs significantly better than baseline in the zero-shot setting.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 16 ran (12 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 16 samples that ran has no recorded date.

TheShadow29/zsgnet-pytorch officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 16 ran (4 instrument-failed) · 2 unverified 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

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
1ran; the contract check could not run
12ran
2unverified

Licence: 1 of the 18 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from TheShadow29/zsgnet-pytorch. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

TheShadow29/zsgnet-pytorch official repository 18 samples, 16 ran (4 instrument-failed) · 2 unverified
add_extras in 12 papers code/ssd_vgg.py ran · our draft was wrong MIT (permissive) · 2a8545e480332b47 · report fixture: signature cfg:list/1/int, i:int/0/int, batch_norm:bool/0/bool · returned list · level recorded 2026-09-22
conv2d in 119 papers code/mdl.py ran MIT (permissive) · 4b907a406f06ace0 · report fixture: signature ni:int/0/int, nf:int/0/int, ks:int/0/int, stride:int/0/int, padding:NoneType/0/?, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-25
conv2d_relu code/mdl.py ran MIT (permissive) · 7af4e486b4c60709 · report fixture: signature ni:int/0/int, nf:int/0/int, ks:int/0/int, stride:int/0/int, padding:NoneType/0/?, bn:bool/0/bool, bias:bool/0/bool · returned Sequential · level recorded 2026-09-25
conv3x3 in 1,376 papers code/fpn_resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
cthw2tlbr code/anchors.py ran fingerprinted MIT (permissive) · a7dcff4207ca66bf · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-25
exec_func_if_main_proc code/utils.py ran MIT (permissive) · 609205821f10988e · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-25
make_data_sampler in 11 papers code/dat_loader.py ran MIT (permissive) · daf082e9921b6a03 · report fixture: signature dataset:TensorDataset/0/?, shuffle:bool/0/bool, distributed:bool/0/bool · returned RandomSampler · level recorded 2026-09-25
multibox in 12 papers code/ssd_vgg.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · b490ac8699f5a7ad · report fixture: signature vgg:list/1/callable, extra_layers:list/1/callable, cfg:list/1/int, num_classes:int/0/int · returned tuple · level recorded 2026-09-22
pad_out code/fpn_resnet.py ran fingerprinted MIT (permissive) · ad11ef6d39eb2ff3 · report fixture: signature k:int/0/int · returned int · level recorded 2026-09-25
pil2tensor in 5 papers code/dat_loader.py ran MIT (permissive) · dfeaf11b09c7a0bc · report fixture: returned Tensor · level recorded 2026-09-25
reduce_dict in 73 papers code/utils.py ran MIT (permissive) · b7654b7006fe061d · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-25
reduce_dict_corr code/utils.py ran MIT (permissive) · 75e6e3f3c795ee43 · report fixture: signature input_dict:dict/0/?, nums:Tensor/0/int · returned dict · level recorded 2026-09-25
reshape in 14 papers code/evaluator.py ran MIT (permissive) · fdb481756a08ea1e · report fixture: signature box:Tensor/2/float, new_size:Tensor/2/float · returned Tensor · level recorded 2026-09-25
tlbr2cthw code/anchors.py ran fingerprinted MIT (permissive) · 345cb82041ecd304 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-25
tlbr2tlhw code/anchors.py ran fingerprinted MIT (permissive) · 6206186edff240f5 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-25
vgg in 16 papers code/ssd_vgg.py ran · our draft was wrong MIT (permissive) · 6921f7ed00595a4f · report fixture: signature cfg:list/1/int, i:int/0/int, batch_norm:bool/0/bool · returned list · level recorded 2026-09-22
collater code/dat_loader.py unverified MIT (permissive) · 13ae5809344e4f05 · report
resnet50 in 121 papers code/fpn_resnet.py unverified MIT (permissive) · fe0212a6c494a57f · report

Tasks

Natural Language QueriesObject DetectionPhrase Groundingobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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