Papers › Unified Coarse-to-Fine Alignment for Video-Text Retrieval

Unified Coarse-to-Fine Alignment for Video-Text Retrieval

18 Sep 2023ICCV 2023 1arXiv:2309.10091archive 2025-07-28

Ziyang Wang, Yi-Lin Sung, Feng Cheng, Gedas Bertasius, Mohit Bansal

The canonical approach to video-text retrieval leverages a coarse-grained or fine-grained alignment between visual and textual information. However, retrieving the correct video according to the text query is often challenging as it requires the ability to reason about both high-level (scene) and low-level (object) visual clues and how they relate to the text query. To this end, we propose a Unified Coarse-to-fine Alignment model, dubbed UCoFiA. Specifically, our model captures the cross-modal similarity information at different granularity levels. To alleviate the effect of irrelevant visual clues, we also apply an Interactive Similarity Aggregation module (ISA) to consider the importance of different visual features while aggregating the cross-modal similarity to obtain a similarity score for each granularity. Finally, we apply the Sinkhorn-Knopp algorithm to normalize the similarities of each level before summing them, alleviating over- and under-representation issues at different levels. By jointly considering the crossmodal similarity of different granularity, UCoFiA allows the effective unification of multi-grained alignments. Empirically, UCoFiA outperforms previous state-of-the-art CLIP-based methods on multiple video-text retrieval benchmarks, achieving 2.4%, 1.4% and 1.3% improvements in text-to-video retrieval R@1 on MSR-VTT, Activity-Net, and DiDeMo, respectively. Our code is publicly available at https://github.com/Ziyang412/UCoFiA.

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="2309.10091")

Code

Syntology Ran 8 of 14 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ziyang412/ucofia officialmentioned in papermentioned on GitHubpytorchMIT 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

14 samples harvested; 8 ran; 0 honoured the contract we drafted; 6 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 · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
4ran
6unverified

Licence: 0 of the 14 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 Ziyang412/UCoFiA. “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.

check_attr Ziyang412/UCoFiA/eval_t2v/modules/modeling.py official repository ran · violated contract MIT (permissive) · 47c2715feba5fd6b · report
compute_metrics Ziyang412/UCoFiA/eval_t2v/metrics.py official repository ran fingerprinted MIT (permissive) · f45b80d057798fed · report
init_device Ziyang412/UCoFiA/eval_t2v/main_ucofia.py official repository ran · fixture could not drive it MIT (permissive) · a0c23f10479a984e · report
sinkhorn_knopp Ziyang412/UCoFiA/eval_t2v/modules/modeling_ucofia.py official repository ran MIT (permissive) · 59bb972d444a2a94 · report
sinkhorn_knopp_video Ziyang412/UCoFiA/eval_t2v/modules/modeling_ucofia.py official repository ran MIT (permissive) · e043fd83bad9c5f0 · report
tensor_text_to_video_metrics Ziyang412/UCoFiA/eval_t2v/metrics.py official repository ran MIT (permissive) · 66bf2e9b33bd27dd · report
update_attr Ziyang412/UCoFiA/eval_t2v/modules/modeling.py official repository ran · our draft was wrong MIT (permissive) · d34a2226d2cf142e · report
url_to_filename Ziyang412/UCoFiA/eval_t2v/modules/file_utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · af64ec220e8bcdbc · report
cached_path Ziyang412/UCoFiA/eval_t2v/modules/file_utils.py official repository unverified MIT (permissive) · 349d780dd4a89a37 · report
filename_to_url Ziyang412/UCoFiA/eval_t2v/modules/file_utils.py official repository unverified MIT (permissive) · db0ac56aaf6e35e6 · report
get_args Ziyang412/UCoFiA/eval_t2v/main_clip4clip.py official repository unverified MIT (permissive) · 5dad69c6b079e518 · report
get_args Ziyang412/UCoFiA/eval_t2v/main_ucofia.py official repository unverified MIT (permissive) · 318dd90e2fb0bff7 · report
tensor_video_to_text_sim Ziyang412/UCoFiA/eval_t2v/metrics.py official repository unverified MIT (permissive) · b6f9f3930836fe3f · report
video_bias_func Ziyang412/UCoFiA/eval_t2v/modules/modeling_ucofia.py official repository unverified MIT (permissive) · 6315d7e89c70a061 · report

Tasks

RetrievalText RetrievalText to Video RetrievalVideo RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval MSR-VTT UCoFiA text-to-video R@1 49.4 #12 of 40 Archive leaderboard report
Video Retrieval MSR-VTT UCoFiA text-to-video R@10 83.5 #12 of 40 Archive leaderboard report
Video Retrieval MSR-VTT UCoFiA text-to-video R@5 72.1 #12 of 40 Archive leaderboard report
Video Retrieval MSR-VTT-1kA UCoFiA text-to-video R@1 49.4 #19 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA UCoFiA text-to-video R@10 83.5 #19 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA UCoFiA text-to-video R@5 72.1 #19 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA UCoFiA video-to-text R@1 47.1 #19 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA UCoFiA video-to-text R@10 83.0 #19 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA UCoFiA video-to-text R@5 74.3 #19 of 63 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