Papers › Zero-shot Referring Expression Comprehension via Structural Similarity Between Images...

Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions

28 Nov 2023CVPR 2024 1arXiv:2311.17048archive 2025-07-28

Zeyu Han, Fangrui Zhu, Qianru Lao, Huaizu Jiang

Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a capacity to understand relationships among disentangled entities. Unfortunately, existing large vision-language alignment (VLA) models, e.g., CLIP, struggle with both aspects so cannot be directly used for this task. To mitigate this gap, we leverage large foundation models to disentangle both images and texts into triplets in the format of (subject, predicate, object). After that, grounding is accomplished by calculating the structural similarity matrix between visual and textual triplets with a VLA model, and subsequently propagate it to an instance-level similarity matrix. Furthermore, to equip VLA models with the ability of relationship understanding, we design a triplet-matching objective to fine-tune the VLA models on a collection of curated dataset containing abundant entity relationships. Experiments demonstrate that our visual grounding performance increase of up to 19.5% over the SOTA zero-shot model on RefCOCO/+/g. On the more challenging Who's Waldo dataset, our zero-shot approach achieves comparable accuracy to the fully supervised model. Code is available at https://github.com/Show-han/Zeroshot_REC.

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 20 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 3 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 14 ran (9 with no instrument failure; 5 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

show-han/zeroshot_rec officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 20 samples, 14 ran (5 instrument-failed) · 6 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

20 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 3 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · violated contract
5ran · our draft was wrong
6ran
6unverified

Licence: 10 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 of them, 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 show-han/zeroshot_rec. “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”. “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.

show-han/zeroshot_rec official repository 20 samples, 14 ran (5 instrument-failed) · 6 unverified
basic_clean in 217 papers VLA_finetune/open_clip/tokenizer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
freeze_batch_norm_2d in 15 papers VLA_finetune/open_clip/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 9b5765523c6d17fd · report fixture: signature module:callable/0/?, module_match:dict/0/?, name:str/0/str · returned SimpleModel · level recorded 2026-09-26
get_pairs in 260 papers VLA_finetune/open_clip/tokenizer.py ran · our draft was wrong Apache-2.0 (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
image_transform in 11 papers VLA_finetune/open_clip/transform.py ran Apache-2.0 (permissive) · 181856ae1295b257 · report fixture: signature image_size:int/0/int, is_train:bool/0/bool, mean:tuple/1/float, std:tuple/1/float, resize_longest_max:bool/0/bool, fill_color:int/0/int · returned Compose · level recorded 2026-09-24
is_bbox_invalid VLA_finetune/training/data.py ran fingerprinted Apache-2.0 (permissive) · b3288ad88c4922cc · report fixture: signature bbox:list/1/int · returned bool · level recorded 2026-09-24
is_global_master in 11 papers VLA_finetune/training/distributed.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · 7c29b374198bddcd · report fixture: signature args:Args/0/? · returned bool · level recorded 2026-09-22
is_local_master in 9 papers VLA_finetune/training/distributed.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · 0377e309e95cfc3e · report fixture: signature args:Args/0/? · returned bool · level recorded 2026-09-22
is_master in 43 papers VLA_finetune/training/distributed.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · b092791002b40e8a · report fixture: signature args:Args/0/? · returned bool · level recorded 2026-09-22
list_pretrained_tag_models VLA_finetune/open_clip/pretrained.py ran Apache-2.0 (permissive) · 8b49391377816761 · report fixture: signature tag:str/0/str · returned list · level recorded 2026-09-24
load_checkpoint in 277 papers VLA_finetune/open_clip/factory.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · ad4accadc0057d93 · report fixture: returned _IncompatibleKeys · level recorded 2026-09-24
load_state_dict in 114 papers VLA_finetune/open_clip/factory.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 4b3a4d17e1df3140 · report fixture: signature checkpoint_path:str/0/str, map_location:str/0/str · returned dict · level recorded 2026-09-24
trace_model in 12 papers VLA_finetune/open_clip/model.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 8e95157106d1df8c · report fixture: signature model:callable/0/?, batch_size:int/0/int, device:device/0/? · returned TopLevelTracedModule · level recorded 2026-09-22
union_bbox VLA_finetune/training/data.py ran fingerprinted Apache-2.0 (permissive) · 149543b13e8a1623 · report fixture: signature bbox1:list/1/int, bbox2:list/1/int · returned list · level recorded 2026-09-24
whitespace_clean in 230 papers VLA_finetune/open_clip/tokenizer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
build_model_from_openai_state_dict in 42 papers VLA_finetune/open_clip/model.py unverified Apache-2.0 (permissive) · e209d001d7c966cf · report
create_model in 163 papers VLA_finetune/open_clip/factory.py unverified Apache-2.0 (permissive) · 23d02ffb86d06cff · report
gather_features in 78 papers VLA_finetune/open_clip/loss.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · ddcbd45e940484ee · report
list_pretrained in 7 papers VLA_finetune/open_clip/pretrained.py unverified Apache-2.0 (permissive) · 2d83d0f60f01d050 · report
list_pretrained_model_tags VLA_finetune/open_clip/pretrained.py unverified Apache-2.0 (permissive) · 8ce0ee4c850e934d · report
load_openai_model in 16 papers VLA_finetune/open_clip/openai.py unverified Apache-2.0 (permissive) · f22c4b3b6fb51672 · report

Tasks

DisentanglementReferring ExpressionReferring Expression ComprehensionVisual Grounding

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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