Papers › Multi-event Video-Text Retrieval

Multi-event Video-Text Retrieval

22 Aug 2023ICCV 2023 1arXiv:2308.11551archive 2025-07-28

Gengyuan Zhang, Jisen Ren, Jindong Gu, Volker Tresp

Video-Text Retrieval (VTR) is a crucial multi-modal task in an era of massive video-text data on the Internet. A plethora of work characterized by using a two-stream Vision-Language model architecture that learns a joint representation of video-text pairs has become a prominent approach for the VTR task. However, these models operate under the assumption of bijective video-text correspondences and neglect a more practical scenario where video content usually encompasses multiple events, while texts like user queries or webpage metadata tend to be specific and correspond to single events. This establishes a gap between the previous training objective and real-world applications, leading to the potential performance degradation of earlier models during inference. In this study, we introduce the Multi-event Video-Text Retrieval (MeVTR) task, addressing scenarios in which each video contains multiple different events, as a niche scenario of the conventional Video-Text Retrieval Task. We present a simple model, Me-Retriever, which incorporates key event video representation and a new MeVTR loss for the MeVTR task. Comprehensive experiments show that this straightforward framework outperforms other models in the Video-to-Text and Text-to-Video tasks, effectively establishing a robust baseline for the MeVTR task. We believe this work serves as a strong foundation for future studies. Code is available at https://github.com/gengyuanmax/MeVTR.

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="2308.11551")

Code

Syntology Ran 10 of 18 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 18 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.

gengyuanmax/mevtr officialmentioned in papermentioned on GitHubpytorch 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

18 samples harvested; 10 ran; 1 honoured the contract we drafted; 8 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 · honoured contract
1ran · violated contract
5ran · our draft was wrong
1ran · fixture could not drive it
2ran
8unverified

Licence: 18 of the 18 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 gengyuanmax/MeVTR. “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 gengyuanmax/MeVTR/modules/tokenization_clip.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 98f385d847636a3e · report
check_attr gengyuanmax/MeVTR/modules/modeling.py official repository ran · violated contract no licence file found · pointer only · 47c2715feba5fd6b · report
compute_metrics_together gengyuanmax/MeVTR/metrics.py official repository ran no licence file found · pointer only · d872576fb8dc10f9 · report
get_pairs gengyuanmax/MeVTR/modules/tokenization_clip.py official repository ran · our draft was wrong no licence file found · pointer only · d919ae32e5e4e616 · report
init_device gengyuanmax/MeVTR/main_task_retrieval_multi.py official repository ran · fixture could not drive it no licence file found · pointer only · a0c23f10479a984e · report
tensor_text_to_video_metrics gengyuanmax/MeVTR/metrics.py official repository ran no licence file found · pointer only · 66bf2e9b33bd27dd · report
update_attr gengyuanmax/MeVTR/modules/modeling.py official repository ran · our draft was wrong no licence file found · pointer only · d34a2226d2cf142e · report
url_to_filename gengyuanmax/MeVTR/modules/file_utils.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · af64ec220e8bcdbc · report
warmup_linear gengyuanmax/MeVTR/modules/optimization.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · e0960afdb0d64aa7 · report
whitespace_clean gengyuanmax/MeVTR/modules/tokenization_clip.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 9542161e9640b858 · report
build_model gengyuanmax/MeVTR/modules/module_clip.py official repository unverified no licence file found · pointer only · f5470c7056a406fe · report
build_model gengyuanmax/MeVTR/modules/module_clip_cluster.py official repository unverified no licence file found · pointer only · 4079eacfa57a27a4 · report
cached_path gengyuanmax/MeVTR/modules/file_utils.py official repository unverified no licence file found · pointer only · 349d780dd4a89a37 · report
filename_to_url gengyuanmax/MeVTR/modules/file_utils.py official repository unverified no licence file found · pointer only · db0ac56aaf6e35e6 · report
get_args gengyuanmax/MeVTR/main_task_retrieval_multi.py official repository unverified no licence file found · pointer only · bda05e1a2c123953 · report
tensor_video_to_text_sim gengyuanmax/MeVTR/metrics.py official repository unverified no licence file found · pointer only · b6f9f3930836fe3f · report
warmup_constant gengyuanmax/MeVTR/modules/optimization.py official repository unverified no licence file found · pointer only · 59e4e730a9dc5dc6 · report
warmup_cosine gengyuanmax/MeVTR/modules/optimization.py official repository unverified no licence file found · pointer only · 20b3d25ba1b796e5 · report

Tasks

Language ModellingRetrievalText RetrievalVideo-Text Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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