Papers › Align and Prompt: Video-and-Language Pre-training with Entity Prompts

Align and Prompt: Video-and-Language Pre-training with Entity Prompts

17 Dec 2021CVPR 2022 1arXiv:2112.09583archive 2025-07-28

Dongxu Li, Junnan Li, Hongdong Li, Juan Carlos Niebles, Steven C. H. Hoi

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between unimodal video and text features. Besides, learning fine-grained visual-language alignment usually requires off-the-shelf object detectors to provide object information, which is bottlenecked by the detector's limited vocabulary and expensive computation cost. We propose Align and Prompt: an efficient and effective video-and-language pre-training framework with better cross-modal alignment. First, we introduce a video-text contrastive (VTC) loss to align unimodal video-text features at the instance level, which eases the modeling of cross-modal interactions. Then, we propose a new visually-grounded pre-training task, prompting entity modeling (PEM), which aims to learn fine-grained region-entity alignment. To achieve this, we first introduce an entity prompter module, which is trained with VTC to produce the similarity between a video crop and text prompts instantiated with entity names. The PEM task then asks the model to predict the entity pseudo-labels (i.e normalized similarity scores) for randomly-selected video crops. The resulting pre-trained model achieves state-of-the-art performance on both text-video retrieval and videoQA, outperforming prior work by a substantial margin. Our code and pre-trained models are available at https://github.com/salesforce/ALPRO.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

salesforce/alpro officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CVF open access id Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper (that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity AlignmentRetrievalVideo RetrievalVisual Question Answering (VQA)Zero-Shot Video Retrievalcross-modal alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval DiDeMo ALPRO text-to-video Median Rank 3 #35 of 40 Archive leaderboard report
Video Retrieval DiDeMo ALPRO text-to-video R@1 35.9 #35 of 40 Archive leaderboard report
Video Retrieval DiDeMo ALPRO text-to-video R@10 78.8 #35 of 40 Archive leaderboard report
Video Retrieval DiDeMo ALPRO text-to-video R@5 67.5 #35 of 40 Archive leaderboard report
Visual Question Answering (VQA) MSRVTT-QA ALPRO Accuracy 0.421 #23 of 34 Archive leaderboard report
Visual Question Answering (VQA) MSVD-QA ALPRO Accuracy 0.459 #29 of 36 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo ALPRO text-to-video Median Rank 6 #20 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo ALPRO text-to-video R@1 23.8 #20 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo ALPRO text-to-video R@10 57.9 #20 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo ALPRO text-to-video R@5 47.3 #20 of 26 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ALPRO text-to-video Median Rank 8 #30 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ALPRO text-to-video R@1 24.1 #30 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ALPRO text-to-video R@10 55.4 #30 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT ALPRO text-to-video R@5 44.7 #30 of 41 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