Papers › 3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting

3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting

26 Apr 2024arXiv:2404.17273archive 2025-07-28

Xuri Ge, Songpei Xu, Fuhai Chen, Jie Wang, Guoxin Wang, Shan An, Joemon M. Jose

In this paper, we propose a novel visual Semantic-Spatial Self-Highlighting Network (termed 3SHNet) for high-precision, high-efficiency and high-generalization image-sentence retrieval. 3SHNet highlights the salient identification of prominent objects and their spatial locations within the visual modality, thus allowing the integration of visual semantics-spatial interactions and maintaining independence between two modalities. This integration effectively combines object regions with the corresponding semantic and position layouts derived from segmentation to enhance the visual representation. And the modality-independence guarantees efficiency and generalization. Additionally, 3SHNet utilizes the structured contextual visual scene information from segmentation to conduct the local (region-based) or global (grid-based) guidance and achieve accurate hybrid-level retrieval. Extensive experiments conducted on MS-COCO and Flickr30K benchmarks substantiate the superior performances, inference efficiency and generalization of the proposed 3SHNet when juxtaposed with contemporary state-of-the-art methodologies. Specifically, on the larger MS-COCO 5K test set, we achieve 16.3%, 24.8%, and 18.3% improvements in terms of rSum score, respectively, compared with the state-of-the-art methods using different image representations, while maintaining optimal retrieval efficiency. Moreover, our performance on cross-dataset generalization improves by 18.6%. Data and code are available at https://github.com/XuriGe1995/3SHNet.

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="2404.17273")

Code

Syntology Ran 10 of 10 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xurige1995/3shnet officialmentioned in paperpytorchApache-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

10 samples harvested; 10 ran; 0 honoured the contract we drafted; 0 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.

2ran · our draft was wrong
8ran

Licence: 0 of the 10 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 xurige1995/3shnet. “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.

compute_sim xurige1995/3shnet/lib/evaluation_rgn_seg_sp_se.py official repository ran fingerprinted Apache-2.0 (permissive) · 92939f518491d46a · report
default_collate_override xurige1995/3shnet/eval_rgn_seg_sp_se.py official repository ran fingerprinted Apache-2.0 (permissive) · 61e35a6b0af63e50 · report
encode_data xurige1995/3shnet/lib/evaluation_rgn_seg_sp_se.py official repository ran Apache-2.0 (permissive) · 56b228e2d72c6b46 · report
encode_data xurige1995/3shnet/lib/evaluation_rgn_seg_sp_se_cross.py official repository ran Apache-2.0 (permissive) · a624aee24b1da924 · report
func_attention xurige1995/3shnet/lib/Crossmodal_Fusion4_sm.py official repository ran Apache-2.0 (permissive) · dd78f2924d527191 · report
func_attention xurige1995/3shnet/lib/Crossmodal_Fusion4_sp.py official repository ran Apache-2.0 (permissive) · 9e0a6b0cf8aa2ef0 · report
i2t xurige1995/3shnet/lib/evaluation_rgn_seg_sp_se.py official repository ran Apache-2.0 (permissive) · 64aed5eaff276e96 · report
l1norm xurige1995/3shnet/lib/Crossmodal_Fusion4_sm.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 9bf455ab09372ab4 · report
l2norm xurige1995/3shnet/lib/Crossmodal_Fusion4_sm.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · be7c4a676b9f1e19 · report
maxk_pool1d_var xurige1995/3shnet/lib/encoders_rgn_seg_sp_se.py official repository ran Apache-2.0 (permissive) · 84519de0fc36134e · report

Tasks

Cross-Modal RetrievalRetrievalSentenceSentence Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval COCO 2014 3SHNet Image-to-text R@1 67.9 #23 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 3SHNet Image-to-text R@10 95.4 #23 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 3SHNet Image-to-text R@5 90.5 #23 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 3SHNet Text-to-image R@1 50.3 #23 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 3SHNet Text-to-image R@10 87.7 #23 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 3SHNet Text-to-image R@5 79.3 #23 of 36 Archive leaderboard report
Cross-Modal Retrieval Flickr30k 3SHNet Image-to-text R@1 87.1 #12 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k 3SHNet Image-to-text R@10 99.2 #12 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k 3SHNet Image-to-text R@5 98.2 #12 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k 3SHNet Text-to-image R@1 69.5 #12 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k 3SHNet Text-to-image R@10 94.7 #12 of 27 Archive leaderboard report
Cross-Modal Retrieval Flickr30k 3SHNet Text-to-image R@5 91.0 #12 of 27 Archive leaderboard report
Cross-Modal Retrieval MSCOCO 3SHNet Image-to-text R@1 85.8 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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