Papers › Learning Situation Hyper-Graphs for Video Question Answering

Learning Situation Hyper-Graphs for Video Question Answering

18 Apr 2023CVPR 2023 1arXiv:2304.08682archive 2025-07-28

Aisha Urooj Khan, Hilde Kuehne, Bo Wu, Kim Chheu, Walid Bousselham, Chuang Gan, Niels Lobo, Mubarak Shah

Answering questions about complex situations in videos requires not only capturing the presence of actors, objects, and their relations but also the evolution of these relationships over time. A situation hyper-graph is a representation that describes situations as scene sub-graphs for video frames and hyper-edges for connected sub-graphs and has been proposed to capture all such information in a compact structured form. In this work, we propose an architecture for Video Question Answering (VQA) that enables answering questions related to video content by predicting situation hyper-graphs, coined Situation Hyper-Graph based Video Question Answering (SHG-VQA). To this end, we train a situation hyper-graph decoder to implicitly identify graph representations with actions and object/human-object relationships from the input video clip. and to use cross-attention between the predicted situation hyper-graphs and the question embedding to predict the correct answer. The proposed method is trained in an end-to-end manner and optimized by a VQA loss with the cross-entropy function and a Hungarian matching loss for the situation graph prediction. The effectiveness of the proposed architecture is extensively evaluated on two challenging benchmarks: AGQA and STAR. Our results show that learning the underlying situation hyper-graphs helps the system to significantly improve its performance for novel challenges of video question-answering tasks.

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="2304.08682")

Code

Syntology Ran 8 of 15 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 15 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.

aurooj/shg-vqa 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

15 samples harvested; 8 ran; 0 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.

8ran
7unverified

Licence: 15 of the 15 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 aurooj/SHG-VQA. “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.

BertAttention aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran fingerprinted no licence file found · pointer only · 5294ad4cfb6fd592 · report
BertCrossattLayer aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 602576fb49da0fad · report
BertIntermediate aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 07fe34e1f674c0cc · report
BertSelfattLayer aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran fingerprinted no licence file found · pointer only · 454867610f1f0d75 · report
FixedPositionalEncoding aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 55bcd1b73de582b9 · report
LearnedPositionalEncoding aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran no licence file found · pointer only · bb8b49b7ee5ab76f · report
PrimaryCaps aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 6948edf5bd10ffdd · report
VisualConfig aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository ran no licence file found · pointer only · 51ace9dd870b213e · report
BertLayer aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · 35c89d3fc6a77009 · report
ConvCaps aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · c492a4693f826a30 · report
CrossAndSelfLayer aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · 304514e4ec620c8e · report
CrossLayer aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · 2e5ef0dbcca6c565 · report
LXRTCapsulesEncoder aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · a68f475e70b1e9e5 · report
SelfCrossLayer aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · 5c2a6eaf5ca58e25 · report
VisualFeatEncoder aurooj/SHG-VQA/AGQA/src/lxrt/modeling_capsbert.py official repository unverified no licence file found · pointer only · e7159315c7bda9ac · report

Tasks

DecoderQuestion AnsweringVideo Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering AGQA 2.0 balanced SHG-VQA (trained from scratch) Average Accuracy 49.2 #6 of 8 Archive leaderboard report
Video Question Answering STAR Benchmark SHG-VQA (trained from scratch) Average Accuracy 39.47 #17 of 17 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