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 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="2311.17048")

Code

Syntology Ran 13 of 20 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · violated contract; 4 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 20 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

show-han/zeroshot_rec officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

20 samples harvested; 13 ran; 0 honoured the contract we drafted; 7 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.

3ran · violated contract
4ran · our draft was wrong
6ran
7unverified

Licence: 0 of the 20 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 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. “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.

basic_clean show-han/zeroshot_rec/VLA_finetune/open_clip/tokenizer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 98f385d847636a3e · report
get_pairs show-han/zeroshot_rec/VLA_finetune/open_clip/tokenizer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d919ae32e5e4e616 · report
image_transform show-han/zeroshot_rec/VLA_finetune/open_clip/transform.py official repository ran Apache-2.0 (permissive) · 181856ae1295b257 · report
is_bbox_invalid show-han/zeroshot_rec/VLA_finetune/training/data.py official repository ran fingerprinted Apache-2.0 (permissive) · b3288ad88c4922cc · report
is_global_master show-han/zeroshot_rec/VLA_finetune/training/distributed.py official repository ran · violated contract Apache-2.0 (permissive) · 7c29b374198bddcd · report
is_local_master show-han/zeroshot_rec/VLA_finetune/training/distributed.py official repository ran · violated contract Apache-2.0 (permissive) · 0377e309e95cfc3e · report
is_master show-han/zeroshot_rec/VLA_finetune/training/distributed.py official repository ran · violated contract Apache-2.0 (permissive) · b092791002b40e8a · report
list_pretrained_tag_models show-han/zeroshot_rec/VLA_finetune/open_clip/pretrained.py official repository ran Apache-2.0 (permissive) · 8b49391377816761 · report
load_checkpoint show-han/zeroshot_rec/VLA_finetune/open_clip/factory.py official repository ran Apache-2.0 (permissive) · ad4accadc0057d93 · report
load_state_dict show-han/zeroshot_rec/VLA_finetune/open_clip/factory.py official repository ran Apache-2.0 (permissive) · 4b3a4d17e1df3140 · report
trace_model show-han/zeroshot_rec/VLA_finetune/open_clip/model.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 8e95157106d1df8c · report
union_bbox show-han/zeroshot_rec/VLA_finetune/training/data.py official repository ran fingerprinted Apache-2.0 (permissive) · 149543b13e8a1623 · report
whitespace_clean show-han/zeroshot_rec/VLA_finetune/open_clip/tokenizer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 9542161e9640b858 · report
build_model_from_openai_state_dict show-han/zeroshot_rec/VLA_finetune/open_clip/model.py official repository unverified Apache-2.0 (permissive) · e209d001d7c966cf · report
create_model show-han/zeroshot_rec/VLA_finetune/open_clip/factory.py official repository unverified Apache-2.0 (permissive) · 23d02ffb86d06cff · report
freeze_batch_norm_2d show-han/zeroshot_rec/VLA_finetune/open_clip/utils.py official repository unverified Apache-2.0 (permissive) · 9b5765523c6d17fd · report
gather_features show-han/zeroshot_rec/VLA_finetune/open_clip/loss.py official repository unverified Apache-2.0 (permissive) · ddcbd45e940484ee · report
list_pretrained show-han/zeroshot_rec/VLA_finetune/open_clip/pretrained.py official repository unverified Apache-2.0 (permissive) · 2d83d0f60f01d050 · report
list_pretrained_model_tags show-han/zeroshot_rec/VLA_finetune/open_clip/pretrained.py official repository unverified Apache-2.0 (permissive) · 8ce0ee4c850e934d · report
load_openai_model show-han/zeroshot_rec/VLA_finetune/open_clip/openai.py official repository 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