Papers › Multimodal Transformer for Unaligned Multimodal Language Sequences

Multimodal Transformer for Unaligned Multimodal Language Sequences

1 Jun 2019ACL 2019 7arXiv:1906.00295archive 2025-07-28

Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov

Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data non-alignment due to variable sampling rates for the sequences from each modality; and 2) long-range dependencies between elements across modalities. In this paper, we introduce the Multimodal Transformer (MulT) to generically address the above issues in an end-to-end manner without explicitly aligning the data. At the heart of our model is the directional pairwise crossmodal attention, which attends to interactions between multimodal sequences across distinct time steps and latently adapt streams from one modality to another. Comprehensive experiments on both aligned and non-aligned multimodal time-series show that our model outperforms state-of-the-art methods by a large margin. In addition, empirical analysis suggests that correlated crossmodal signals are able to be captured by the proposed crossmodal attention mechanism in MulT.

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="1906.00295")

Code

Syntology Ran 8 of 17 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 2 ran; community (archive-listed): 8 samples from 1 repository, 4 ran; 2 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.

yaohungt/Multimodal-Transformer officialmentioned in papermentioned on GitHubpytorch report
JhnLee/multimodal-transformer mentioned on GitHubpytorch report
kenford953/graphcage mentioned on GitHubpytorch report
pliang279/MFN mentioned on GitHubpytorchMIT 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

17 samples harvested; 8 ran; 3 honoured the contract we drafted; 9 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 · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
1ran
9unverified

Licence: 10 of the 17 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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

multiclass_acc yaohungt/Multimodal-Transformer/src/eval_metrics.py official repository ran · honoured contract fingerprinted MIT (permissive) · 9487efb0962df60b · report
weighted_accuracy yaohungt/Multimodal-Transformer/src/eval_metrics.py official repository ran · honoured contract fingerprinted MIT (permissive) · 6d4da8365bb0f5d1 · report
MULTModel yaohungt/Multimodal-Transformer/src/models.py official repository unverified MIT (permissive) · 81f5a0e8677cf0a6 · report
MultiheadAttention yaohungt/Multimodal-Transformer/src/models.py official repository unverified MIT (permissive) · a1bae24ff466241b · report
TransformerEncoder yaohungt/Multimodal-Transformer/src/models.py official repository unverified MIT (permissive) · 8a709f2a4a8e7ede · report
TransformerEncoderLayer yaohungt/Multimodal-Transformer/src/models.py official repository unverified MIT (permissive) · 9518e860e7fd09b2 · report
eval_mosi yaohungt/Multimodal-Transformer/src/eval_metrics.py official repository unverified MIT (permissive) · 52ec3727261ea9b7 · report
SinusoidalPositionalEmbedding kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 0056ce87dc2bc16f · report
buffered_future_mask kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) ran · violated contract fingerprinted no licence file found · pointer only · 184a5eddedaf6a42 · report
fill_with_neg_inf kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 8f266b9d616de9b9 · report
make_positions kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 21958d540bd87a8c · report
MULTModel kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) unverified no licence file found · pointer only · 4e132df3b6dfa3c6 · report
MultiheadAttention kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) unverified no licence file found · pointer only · 34e57a8ff4c50a35 · report
TransformerEncoder kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) unverified no licence file found · pointer only · da29e003f8b8fe95 · report
TransformerEncoderLayer kenford953/graphcage/src/CrossmodalTransformer.py community (archive-listed) unverified no licence file found · pointer only · b04b6b2fd212ab1a · report
LayerNorm identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 02408cb7d7b045d1 · report
Linear identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 10865bbb99140edd · report

Tasks

Multimodal Sentiment AnalysisTime SeriesTime Series Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multimodal Sentiment Analysis MOSI MulT Accuracy 83 #6 of 11 Archive leaderboard report
Multimodal Sentiment Analysis MOSI MulT F1 score 82.8 #6 of 11 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

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