Papers › Learning Trimodal Relation for AVQA with Missing Modality

Learning Trimodal Relation for AVQA with Missing Modality

23 Jul 2024arXiv:2407.16171archive 2025-07-28

Kyu Ri Park, Hong Joo Lee, Jung Uk Kim

Recent Audio-Visual Question Answering (AVQA) methods rely on complete visual and audio input to answer questions accurately. However, in real-world scenarios, issues such as device malfunctions and data transmission errors frequently result in missing audio or visual modality. In such cases, existing AVQA methods suffer significant performance degradation. In this paper, we propose a framework that ensures robust AVQA performance even when a modality is missing. First, we propose a Relation-aware Missing Modal (RMM) generator with Relation-aware Missing Modal Recalling (RMMR) loss to enhance the ability of the generator to recall missing modal information by understanding the relationships and context among the available modalities. Second, we design an Audio-Visual Relation-aware (AVR) diffusion model with Audio-Visual Enhancing (AVE) loss to further enhance audio-visual features by leveraging the relationships and shared cues between the audio-visual modalities. As a result, our method can provide accurate answers by effectively utilizing available information even when input modalities are missing. We believe our method holds potential applications not only in AVQA research but also in various multi-modal scenarios.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 24 code samples: 21 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 24: 20 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 17 ran (15 with no instrument failure; 2 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

visualaikhu/missing-avqa officialmentioned in papermentioned on GitHubpytorchSyntology: 21 samples, 17 ran (2 instrument-failed) · 4 unverified 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

24 samples harvested: 20 ran (of which 14 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · our draft was wrong
14ran
4unverified

Licence: 3 of the 24 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 visualaikhu/missing-avqa. 3 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 7 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

visualaikhu/missing-avqa official repository 21 samples, 17 ran (2 instrument-failed) · 4 unverified
AVQA_Memory net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · b19aa687804ddbdd · report fixture: returned AVQA_Memory · level recorded 2026-09-22
Attend in 6 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · a461fe5c0890e880 · report fixture: returned Attend · level recorded 2026-09-22
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · 100973e0dc95d746 · report fixture: returned Attention · level recorded 2026-09-22
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · f3b98aa33cb4d3fc · report fixture: returned BasicBlock · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · 1b1fcc6ab25fa4ef · report fixture: returned Block · level recorded 2026-09-22
Bottleneck in 98 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · 0df99f2ca89a9f10 · report fixture: returned Bottleneck · level recorded 2026-09-22
Downsample in 58 papers net_grd_avst/net_avst.py ran · our draft was wrong MIT (permissive) · b5bf8353f4199efb · report fixture: signature dim:int/0/int, dim_out:int/0/int · returned Sequential · level recorded 2026-09-22
GaussianDiffusion in 61 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · 1cbe92e0187480a4 · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
LinearAttention in 20 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · 49dea4e895a85ad5 · report fixture: returned LinearAttention · level recorded 2026-09-22
QstEncoder net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · bb260ea644c95e3a · report fixture: returned QstEncoder · level recorded 2026-09-22
RMSNorm in 61 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 30e7fae83920ab01 · report fixture: returned RMSNorm · level recorded 2026-09-22
RandomOrLearnedSinusoidalPosEmb net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · b100b6c72c401001 · report fixture: returned RandomOrLearnedSinusoidalPosEmb · level recorded 2026-09-22
ResNet in 139 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 6f0b7d14d56b9a7b · report fixture: returned ResNet · level recorded 2026-09-22
ResnetBlock in 49 papers net_grd_avst/net_avst.py ran · metamorphic tier: deterministic MIT (permissive) · b18e27ad640dde3d · report fixture: returned ResnetBlock · level recorded 2026-09-22
SinusoidalPosEmb in 18 papers
census: 6 implementations from 6 papers, 3 distinct outputs on one shared input
net_grd_avst/net_avst.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2b8015ff3c87273a · report fixture: returned SinusoidalPosEmb · level recorded 2026-09-22
Upsample in 77 papers net_grd_avst/net_avst.py ran · our draft was wrong MIT (permissive) · 410a7d2e8c88e682 · report fixture: signature dim:int/0/int, dim_out:NoneType/0/? · returned Sequential · level recorded 2026-09-22
cosine_beta_schedule in 76 papers net_grd_avst/net_avst.py ran · honoured contract fingerprinted MIT (permissive) · 079814bd981435a5 · report fixture: signature timesteps:int/0/int, s:float/0/float · returned Tensor · level recorded 2026-09-22
AVQA_Fusion_Net net_grd_avst/net_avst.py unverified MIT (permissive) · a787fa87e1afe3f0 · report
Unet in 14 papers net_grd_avst/net_avst.py unverified MIT (permissive) · 44756209b5482bd6 · report
_resnet in 27 papers net_grd_avst/net_avst.py unverified MIT (permissive) · 023ac56ffd33d3bc · report
resnet18 in 432 papers net_grd_avst/net_avst.py unverified MIT (permissive) · b03e2f9d7a1ce561 · report
Repository not located 3 samples, 3 ran (0 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
cast_tuple in 58 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · d229662b12e581b6 · report fixture: signature t:Tensor/2/float, length:int/0/int · returned tuple · level recorded 2026-09-22
normalize_to_neg_one_to_one in 13 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · a1229a9f4df127e2 · report fixture: signature img:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unnormalize_to_zero_to_one in 14 papers
census: 4 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 97e1bbd232dfe092 · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22

Tasks

Audio-Visual Question Answering (AVQA)Audio-visual Question AnsweringQuestion AnsweringVisual Question Answering

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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