Papers › Position-guided Text Prompt for Vision-Language Pre-training

Position-guided Text Prompt for Vision-Language Pre-training

19 Dec 2022CVPR 2023 1arXiv:2212.09737archive 2025-07-28

Alex Jinpeng Wang, Pan Zhou, Mike Zheng Shou, Shuicheng Yan

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N×N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling `P" or ``O" in aPTP ``The block P has a O". This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT \cite{vilt} baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP \cite{blip} baseline. Moreover, PTP achieves comparable results with object-detector based methods, and much faster inference speed since PTP discards its object detector for inference while the later cannot. Our code and pre-trained weight will be released at \url{https://github.com/sail-sg/ptp}.

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="2212.09737")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 5 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sail-sg/ptp 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

5 samples harvested; 3 ran; 0 honoured the contract we drafted; 2 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 · our draft was wrong
2ran · fixture could not drive it
2unverified

Licence: 0 of the 5 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 sail-sg/ptp. “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_acc sail-sg/ptp/src/blip_src/utils.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · aa81d03f07735ab8 · report
compute_n_params sail-sg/ptp/src/blip_src/utils.py official repository ran · our draft was wrong Apache-2.0 (permissive) · ad12a494674d23fb · report
itm_eval sail-sg/ptp/src/blip_src/train_retrieval.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · c7f85279d772ea19 · report
generate_object_bbox sail-sg/ptp/src/data_preprocess/generate_sample_with_bbox_and_classes.py official repository unverified Apache-2.0 (permissive) · d0feb6a1aa7fd1e1 · report
init_distributed_ddpjob sail-sg/ptp/src/blip_src/utils.py official repository unverified Apache-2.0 (permissive) · 600f616bde761407 · report

Tasks

Cross-Modal RetrievalImage CaptioningObjectRetrievalVisual GroundingVisual ReasoningZero-Shot Cross-Modal Retrieval

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval COCO 2014 PTP-BLIP (14M) Image-to-text R@1 81.5 #6 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 PTP-BLIP (14M) Image-to-text R@10 97.9 #6 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 PTP-BLIP (14M) Image-to-text R@5 95.9 #6 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 PTP-BLIP (14M) Text-to-image R@1 64.9 #6 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 PTP-BLIP (14M) Text-to-image R@10 92.2 #6 of 36 Archive leaderboard report
Cross-Modal Retrieval COCO 2014 PTP-BLIP (14M) Text-to-image R@5 87.4 #6 of 36 Archive leaderboard report
Image Captioning COCO Captions PTP-BLIP (14M) BLEU-4 40.1 #19 of 41 Archive leaderboard report
Image Captioning COCO Captions PTP-BLIP (14M) CIDER 135.0 #19 of 41 Archive leaderboard report
Image Captioning COCO Captions PTP-BLIP (14M) METEOR 30.4 #19 of 41 Archive leaderboard report
Image Captioning COCO Captions PTP-BLIP (14M) SPICE 23.7 #19 of 41 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 PTP-BLIP Image-to-text R@1 69.7 #5 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 PTP-BLIP Image-to-text R@10 94.7 #5 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 PTP-BLIP Image-to-text R@5 90.0 #5 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 PTP-BLIP Text-to-image R@1 49.5 #5 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 PTP-BLIP Text-to-image R@10 84.2 #5 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval COCO 2014 PTP-BLIP Text-to-image R@5 75.9 #5 of 18 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k PTP-BLIP (14M) Image-to-text R@1 87.1 #16 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k PTP-BLIP (14M) Image-to-text R@10 99.3 #16 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k PTP-BLIP (14M) Image-to-text R@5 98.4 #16 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k PTP-BLIP (14M) Text-to-image R@1 73.1 #16 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k PTP-BLIP (14M) Text-to-image R@10 94.8 #16 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k PTP-BLIP (14M) Text-to-image R@5 91.0 #16 of 22 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.

Methods

ALIGNBLIPSPEED

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