Papers › TVQA+: Spatio-Temporal Grounding for Video Question Answering

TVQA+: Spatio-Temporal Grounding for Video Question Answering

25 Apr 2019ACL 2020 6arXiv:1904.11574archive 2025-07-28

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

We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural language questions about videos. We first augment the TVQA dataset with 310.8K bounding boxes, linking depicted objects to visual concepts in questions and answers. We name this augmented version as TVQA+. We then propose Spatio-Temporal Answerer with Grounded Evidence (STAGE), a unified framework that grounds evidence in both spatial and temporal domains to answer questions about videos. Comprehensive experiments and analyses demonstrate the effectiveness of our framework and how the rich annotations in our TVQA+ dataset can contribute to the question answering task. Moreover, by performing this joint task, our model is able to produce insightful and interpretable spatio-temporal attention visualizations. Dataset and code are publicly available at: http: //tvqa.cs.unc.edu, https://github.com/jayleicn/TVQAplus

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="1904.11574")

Code

Syntology Ran 6 of 13 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 13 samples from 2 repositories, 6 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/TVQA-PLUS officialmentioned in papermentioned on GitHubpytorchMIT report
jayleicn/TVQAplus officialmentioned in papermentioned on GitHubpytorch report
h19920918/quiz_for_day06 mentioned on GitHub 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

13 samples harvested; 6 ran; 1 honoured the contract we drafted; 7 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
2ran · our draft was wrong
2ran · fixture could not drive it
1ran
7unverified

Licence: 0 of the 13 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.

clean_label jayleicn/TVQAplus/eval/eval_tvqa_plus.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 15a10d81f1798c24 · report
compute_temporal_iou jayleicn/TVQAplus/eval/eval_tvqa_plus.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · e6748ac2de40b82f · report
find_max_pair jayleicn/TVQAplus/inference.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · ac298b19120de9b3 · report
flat_list_of_lists jayleicn/TVQA-PLUS/model/model_utils.py official repository ran MIT (permissive) · cef10190a6f8f7e9 · report
load_json jayleicn/TVQA-PLUS/utils.py official repository ran · our draft was wrong MIT (permissive) · 53d425eb1278ddda · report
mask_logits jayleicn/TVQA-PLUS/model/model_utils.py official repository ran · honoured contract fingerprinted MIT (permissive) · 1c17153fb5488283 · report
clones jayleicn/TVQA-PLUS/model/self_attention.py official repository unverified MIT (permissive) · 3b1c10bbead1587d · report
compute_temporal_metrics jayleicn/TVQAplus/eval/eval_tvqa_plus.py official repository unverified MIT (permissive) · c5706ab8b1fb0d80 · report
filter_list_dicts jayleicn/TVQA-PLUS/tvqa_dataset.py official repository unverified MIT (permissive) · 371c15cd94273e6d · report
load_jsonl_as_dict jayleicn/TVQA-PLUS/utils.py official repository unverified MIT (permissive) · 5c8b4d65ef6e0701 · report
pad_sequence_3d_label jayleicn/TVQA-PLUS/tvqa_dataset.py official repository unverified MIT (permissive) · c9c5db64f027a226 · report
read_json_lines jayleicn/TVQA-PLUS/utils.py official repository unverified MIT (permissive) · 4c3a3572441640fa · report
rm_empty_by_copy jayleicn/TVQA-PLUS/tvqa_dataset.py official repository unverified MIT (permissive) · 350e1afa784151b9 · report

Tasks

Question AnsweringVideo 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 TVQA STAGE (Lei et al., 2019) Accuracy 70.50 #6 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