SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13802 · CVPR · 2023

Decoupled Multimodal Distilling for Emotion Recognition

Yong Li, Yuanzhi Wang, Zhen Cui

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2303.13802.json · badge: /api/ran/2303.13802.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mdswyz/DMD community
Papers with Code archive
2 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
LayerNorm Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
this paper's copy was not recorded; identical code first harvested from wangqiangneu/dlcl
pointer only; the stored copy get_code serves, from wangqiangneu/dlcl, is pointer only (licence: NOASSERTION) · get_code("2f3bc129645ecd7a")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SinusoidalPositionalEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
mdswyz/DMD/trains/singleTask/model/dmd.py
code served (permissive licence) · get_code("6cde542a176e7ff1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, SinusoidalPositionalEmbedding: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'embedding_dim': 8,
    'padding_idx': 0,
    'left_pad': False,
    'init_size': 128,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SinusoidalPositionalEmbedding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SinusoidalPositionalEmbedding output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
buffered_future_mask Ran
ran; our contract draft was wrong, not the code
mdswyz/DMD/trains/singleTask/model/dmd.py
code served (permissive licence) · get_code("d13fbe5e7e90947f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function uses:
# - tensor.size(0) to get first dimension
# - tensor.is_cuda to check device
# - tensor.device to get device
# - tensor2.size(0) if tensor2 is not None
# So we need torch tensors

tensor = torch.ones(4, 3)
tensor2 = torch.ones(5, 3)

ARGS = {
    'tensor': tensor,
    'tensor2': tensor2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 5) — shape (4, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
DMD Not yet run
unverified (harvested, no recorded run)
mdswyz/DMD/trains/singleTask/model/dmd.py
code served (permissive licence) · get_code("c4736460ceb9ee69")
How it ran

no invocation recorded.

MultiheadAttention Not yet run
unverified (harvested, no recorded run)
mdswyz/DMD/trains/singleTask/model/dmd.py
code served (permissive licence) · get_code("89990d89c23c5bfa")
How it ran

no invocation recorded.

TransformerEncoder Not yet run
unverified (harvested, no recorded run)
mdswyz/DMD/trains/singleTask/model/dmd.py
code served (permissive licence) · get_code("8236465be0bb8229")
How it ran

no invocation recorded.

TransformerEncoderLayer Not yet run
unverified (harvested, no recorded run)
mdswyz/DMD/trains/singleTask/model/dmd.py
code served (permissive licence) · get_code("7b9d2681c13f15dc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 5 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
LayerNorm
brick of this paper's assembly: helper
8 other papers
4 dated earlier, 4 later · 3 only as an assembly brick
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1906.00295 (2019-06)
Multimodal Transformer for Unaligned Multimodal Language Sequences
1906.01787 (2019-06)
Learning Deep Transformer Models for Machine Translation
and 5 more not named here
MultiheadAttention
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 1 only as an assembly brick
1906.00295 (2019-06)
Multimodal Transformer for Unaligned Multimodal Language Sequences
2407.05374 (2024-07)
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
2411.01409 (2024-11)
Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
TransformerEncoder
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
1906.00295 (2019-06)
Multimodal Transformer for Unaligned Multimodal Language Sequences
2111.08456 (2021-11)
Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions
2407.05374 (2024-07)
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
TransformerEncoderLayer
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
1906.00295 (2019-06)
Multimodal Transformer for Unaligned Multimodal Language Sequences
2111.08456 (2021-11)
Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions
2407.05374 (2024-07)
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
buffered_future_mask
brick of this paper's assembly: helper
1 other paper
1 later
2312.14667 (2023-12)
Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Human multimodal emotion recognition (MER) aims to perceive human emotions via language, visual and acoustic modalities. Despite the impressive performance of previous MER approaches, the inherent multimodal heterogeneities still haunt and the contribution of different modalities varies significantly. In this work, we mitigate this issue by proposing a decoupled multimodal distillation (DMD) approach that facilitates flexible and adaptive crossmodal knowledge distillation, aiming to enhance the discriminative features of each modality. Specially, the representation of each modality is decoupled into two parts, i.e., modalityirrelevant/-exclusive spaces, in a self-regression manner. DMD utilizes a graph distillation unit (GD-Unit) for each decoupled part so that each GD can be performed in a more specialized and effective manner. A GD-Unit consists of a dynamic graph where each vertice represents a modality and each edge indicates a dynamic knowledge distillation. Such GD paradigm provides a flexible knowledge transfer manner where the distillation weights can be automatically learned, thus enabling diverse crossmodal knowledge transfer patterns. Experimental results show DMD consistently obtains superior performance than state-of-the-art MER methods. Visualization results show the graph edges in DMD exhibit meaningful distributional patterns w.r.t. the modality-irrelevant/-exclusive feature spaces. Codes are released at https://github.com/mdswyz/DMD.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.13802")
get_code_for_paper("2303.13802")
have("2303.13802")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.13802.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.13802.svg)](https://syntology.ai/paper/2303.13802)

Connect an agent — have() is free.