Papers › Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

19 Jun 2021ACL 2021 5arXiv:2106.10446archive 2025-07-28

Ahjeong Seo, Gi-Cheon Kang, Joonhan Park, Byoung-Tak Zhang

Video Question Answering is a task which requires an AI agent to answer questions grounded in video. This task entails three key challenges: (1) understand the intention of various questions, (2) capturing various elements of the input video (e.g., object, action, causality), and (3) cross-modal grounding between language and vision information. We propose Motion-Appearance Synergistic Networks (MASN), which embed two cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question's intentions. MASN consists of a motion module, an appearance module, and a motion-appearance fusion module. The motion module computes the action-oriented cross-modal joint representations, while the appearance module focuses on the appearance aspect of the input video. Finally, the motion-appearance fusion module takes each output of the motion module and the appearance module as input, and performs question-guided fusion. As a result, MASN achieves new state-of-the-art performance on the TGIF-QA and MSVD-QA datasets. We also conduct qualitative analysis by visualizing the inference results of MASN. The code is available at https://github.com/ahjeongseo/MASN-pytorch.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 20 code samples harvested from 1 repository linked to this paper: 15 ran (of which 14 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 20 samples from 1 repository, 15 ran (15 with no instrument failure; 0 where Syntology's instrument failed). 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ahjeongseo/MASN-pytorch officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 15 ran (0 instrument-failed) · 5 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

20 samples harvested: 15 ran (of which 14 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

15ran
5unverified

Licence: 0 of the 20 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 ahjeongseo/MASN-pytorch. “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 6 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.

ahjeongseo/MASN-pytorch official repository 20 samples, 15 ran (0 instrument-failed) · 5 unverified
AttAdj model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · bd681740f90f16fd · report fixture: returned AttAdj · level recorded 2026-09-22
AttFlat model/masn.py ran MIT (permissive) · 759b0914ac77b28a · report fixture: returned AttFlat · level recorded 2026-09-22
BCNet model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · e259237fcad3dc88 · report fixture: returned BCNet · level recorded 2026-09-22
BaseRNN model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · dc8f9d8e6494711c · report fixture: returned BaseRNN · level recorded 2026-09-22
FC in 11 papers model/masn.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 05b99b050c8b7491 · report fixture: returned FC · level recorded 2026-09-22
FCNet in 6 papers model/masn.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 63433a241385e836 · report fixture: returned FCNet · level recorded 2026-09-22
FFN in 37 papers model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · ccbe74241dafb0f7 · report fixture: returned FFN · level recorded 2026-09-22
GCN in 41 papers model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · b86d984ed27f78a4 · report fixture: returned GCN · level recorded 2026-09-22
GraphConvolution in 36 papers model/masn.py ran MIT (permissive) · 388325a7a33168a2 · report fixture: signature input:Tensor/3/float, adj:Tensor/3/float · returned Tensor · level recorded 2026-09-24
MLP in 375 papers model/masn.py ran fingerprinted MIT (permissive) · 14b57ad597a09b12 · report fixture: returned MLP · level recorded 2026-09-22
PositionEncoding in 9 papers model/masn.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 8df81fac54e85c99 · report fixture: returned PositionEncoding · level recorded 2026-09-22
SentenceEncoderRNN model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · ef071499ee045c12 · report fixture: returned SentenceEncoderRNN · level recorded 2026-09-22
VideoAdjLearner model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · b54092a60a1899c5 · report fixture: returned VideoAdjLearner · level recorded 2026-09-22
WeightDropLinear model/masn.py ran · metamorphic tier: deterministic MIT (permissive) · 7c200f265dc848c2 · report fixture: returned WeightDropLinear · level recorded 2026-09-22
weight_drop model/masn.py ran MIT (permissive) · 3d02a8046580e19b · report fixture: returned weight_drop · level recorded 2026-09-22
BAN model/masn.py unverified MIT (permissive) · 1e41b6c5ad0bb279 · report
BiAttention model/masn.py unverified MIT (permissive) · 84b7ec1fe8c2e0b6 · report
MASN model/masn.py unverified MIT (permissive) · 119ae32ced71cbed · report
MotionApprFusion model/masn.py unverified MIT (permissive) · f38305bce2e96714 · report
_weight_drop model/masn.py unverified MIT (permissive) · 73eb643334aa5e32 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Motion-Appearance Synergistic Networks (MASN) (graph method: Motion-Appearance Synergistic Networks (MASN)). 21 bricks; individually on a fixture: 16 ran (of which 15 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. MASN entry · level 0 · unverified · 119ae32ced71cbed
  2. AttFlat helper · level 1 · ran · 759b0914ac77b28a
  3. BAN model · level 0 · unverified · 1e41b6c5ad0bb279
  4. GCN model · level 1 · ran · b86d984ed27f78a4
  5. MotionApprFusion model · level 0 · unverified · f38305bce2e96714
  6. PositionEncoding helper · level 1 · ran · 8df81fac54e85c99
  7. SentenceEncoderRNN helper · level 1 · ran · ef071499ee045c12
  8. VideoAdjLearner model · level 1 · ran · b54092a60a1899c5
  9. WeightDropLinear helper · level 1 · ran · 7c200f265dc848c2
  10. MLP helper · level 1 · ran · 14b57ad597a09b12
  11. BCNet helper · level 1 · ran · e259237fcad3dc88
  12. BiAttention helper · level 0 · unverified · 84b7ec1fe8c2e0b6
  13. FCNet helper · level 1 · ran · 63433a241385e836
  14. GraphConvolution helper · level 1 · ran · 388325a7a33168a2
  15. AttAdj helper · level 1 · ran · bd681740f90f16fd
  16. FFN helper · level 1 · ran · ccbe74241dafb0f7
  17. LayerNorm helper · level 1 · ran · 82506e21f7dfa931
  18. BaseRNN helper · level 1 · ran · dc8f9d8e6494711c
  19. _weight_drop helper · level 0 · unverified · 73eb643334aa5e32
  20. FC helper · level 1 · ran · 05b99b050c8b7491
  21. weight_drop helper · level 1 · ran · 3d02a8046580e19b

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2106.10446") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AI AgentQuestion AnsweringVideo Question Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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