Papers › TVQA: Localized, Compositional Video Question Answering

TVQA: Localized, Compositional Video Question Answering

5 Sep 2018EMNLP 2018 10arXiv:1809.01696archive 2025-07-28

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

Recent years have witnessed an increasing interest in image-based question-answering (QA) tasks. However, due to data limitations, there has been much less work on video-based QA. In this paper, we present TVQA, a large-scale video QA dataset based on 6 popular TV shows. TVQA consists of 152,545 QA pairs from 21,793 clips, spanning over 460 hours of video. Questions are designed to be compositional in nature, requiring systems to jointly localize relevant moments within a clip, comprehend subtitle-based dialogue, and recognize relevant visual concepts. We provide analyses of this new dataset as well as several baselines and a multi-stream end-to-end trainable neural network framework for the TVQA task. The dataset is publicly available at http://tvqa.cs.unc.edu.

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="1809.01696")

Code

Syntology Ran 3 of 8 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 8 samples from 2 repositories, 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.

BM-K/Question-Difficulty-Estimation mentioned on GitHubpytorch report
h19920918/quiz_for_day06 mentioned on GitHub report
jayleicn/TVQA mentioned on GitHubpytorchMIT report
mansigoel/TVQA mentioned 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

8 samples harvested; 3 ran; 0 honoured the contract we drafted; 5 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.

3ran · our draft was wrong
5unverified

Licence: 0 of the 8 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.

get_vidname2cnt_per_show mansigoel/TVQA/preprocessing.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 1b30465bb758c4b8 · report
load_json jayleicn/TVQA/utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 53d425eb1278ddda · report
merge_list_dicts mansigoel/TVQA/preprocessing.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 13141c69e7fed551 · report
max_along_time jayleicn/TVQA/model/rnn.py community (archive-listed) unverified MIT (permissive) · 4e8b207ee04445f8 · report
mean_along_time jayleicn/TVQA/model/rnn.py community (archive-listed) unverified MIT (permissive) · 8ec050fe9cabe7f9 · report
pad_collate jayleicn/TVQA/tvqa_dataset.py community (archive-listed) unverified MIT (permissive) · d10981a16ea4b3bc · report
preprocess_inputs jayleicn/TVQA/tvqa_dataset.py community (archive-listed) unverified MIT (permissive) · 1dc3bf82cc77e497 · report
read_json_lines jayleicn/TVQA/utils.py community (archive-listed) unverified MIT (permissive) · 62891394278900f5 · report

Tasks

Video Question Answering

Datasets

Introduced by this paper, per the archive.

TVQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering SUTD-TrafficQA TVQA 1/2 63.15 #5 of 6 Archive leaderboard report
Video Question Answering SUTD-TrafficQA TVQA 1/4 35.16 #5 of 6 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