Papers › TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

24 Jan 2020ECCV 2020 8arXiv:2001.09099archive 2025-07-28

Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal

We introduce TV show Retrieval (TVR), a new multimodal retrieval dataset. TVR requires systems to understand both videos and their associated subtitle (dialogue) texts, making it more realistic. The dataset contains 109K queries collected on 21.8K videos from 6 TV shows of diverse genres, where each query is associated with a tight temporal window. The queries are also labeled with query types that indicate whether each of them is more related to video or subtitle or both, allowing for in-depth analysis of the dataset and the methods that built on top of it. Strict qualification and post-annotation verification tests are applied to ensure the quality of the collected data. Further, we present several baselines and a novel Cross-modal Moment Localization (XML ) network for multimodal moment retrieval tasks. The proposed XML model uses a late fusion design with a novel Convolutional Start-End detector (ConvSE), surpassing baselines by a large margin and with better efficiency, providing a strong starting point for future work. We have also collected additional descriptions for each annotated moment in TVR to form a new multimodal captioning dataset with 262K captions, named TV show Caption (TVC). Both datasets are publicly available. TVR: https://tvr.cs.unc.edu, TVC: https://tvr.cs.unc.edu/tvc.html.

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="2001.09099")

Code

Syntology Ran 8 of 19 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 19 samples from 2 repositories, 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.

jayleicn/TVCaption officialmentioned in papermentioned on GitHubpytorchMIT report
jayleicn/TVRetrieval 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

19 samples harvested; 8 ran; 2 honoured the contract we drafted; 11 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 · honoured contract
3ran · our draft was wrong
3ran
11unverified

Licence: 0 of the 19 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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_temporal_iou jayleicn/TVRetrieval/utils/temporal_nms.py official repository ran fingerprinted MIT (permissive) · ea2ba2c075c6b18b · report
flat_list_of_lists jayleicn/TVCaption/baselines/multimodal_transformer/local_utils.py official repository ran MIT (permissive) · cef10190a6f8f7e9 · report
gelu jayleicn/TVCaption/baselines/multimodal_transformer/transformer/model.py official repository ran · honoured contract fingerprinted MIT (permissive) · 69e3a274f98c15af · report
load_json jayleicn/TVCaption/utils/basic_utils.py official repository ran · our draft was wrong MIT (permissive) · 2d946250dd2f5a4f · report
load_json jayleicn/TVCaption/baselines/multimodal_transformer/local_utils.py official repository ran · our draft was wrong MIT (permissive) · 53d425eb1278ddda · report
load_jsonl jayleicn/TVCaption/standalone_eval/evaluate.py official repository ran MIT (permissive) · f1d1cccccf038785 · report
load_pickle jayleicn/TVCaption/utils/basic_utils.py official repository ran · our draft was wrong MIT (permissive) · 570ad34bd1af44a8 · report
mask_logits jayleicn/TVRetrieval/baselines/crossmodal_moment_localization/model_xml.py official repository ran · honoured contract fingerprinted MIT (permissive) · 1c17153fb5488283 · report
caption_collate jayleicn/TVCaption/baselines/multimodal_transformer/transformer/tvc_dataset.py official repository unverified MIT (permissive) · ff6297422c0e1b92 · report
count_parameters jayleicn/TVCaption/baselines/multimodal_transformer/local_utils.py official repository unverified MIT (permissive) · edb929dece68582e · report
length_penalty_builder jayleicn/TVCaption/baselines/multimodal_transformer/transformer/decode_strategy.py official repository unverified MIT (permissive) · 07940cb25a48bfc4 · report
load_glove jayleicn/TVCaption/baselines/multimodal_transformer/build_vocab.py official repository unverified MIT (permissive) · a81aaf990607f138 · report
pool_across_time jayleicn/TVRetrieval/utils/model_utils.py official repository unverified MIT (permissive) · 286f821a3988fcbe · report
prepare_batch_inputs jayleicn/TVCaption/baselines/multimodal_transformer/transformer/tvc_dataset.py official repository unverified MIT (permissive) · bff9917618d44658 · report
remove_nonascii jayleicn/TVCaption/standalone_eval/evaluate.py official repository unverified MIT (permissive) · a45f62024eb3d2c5 · report
sort_res jayleicn/TVCaption/baselines/multimodal_transformer/translate.py official repository unverified MIT (permissive) · 712ae5d2ea349b4d · report
step_collate jayleicn/TVCaption/baselines/multimodal_transformer/transformer/tvc_dataset.py official repository unverified MIT (permissive) · c1ba877d826f25af · report
temporal_non_maximum_suppression jayleicn/TVRetrieval/utils/temporal_nms.py official repository unverified MIT (permissive) · d235ed6d33e43a98 · report
tile jayleicn/TVCaption/baselines/multimodal_transformer/translator.py official repository unverified MIT (permissive) · 69b8b31e44791260 · report

Tasks

Moment RetrievalRetrievalVideo Corpus Moment RetrievalVideo Retrieval

Datasets

Introduced by this paper, per the archive.

TVCTVR

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Retrieval TVR XML (Lei et al., 2020) R@10 8.93 #2 of 2 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