SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.09502 · ICML · 2024

EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning

Joon Chung, Jongsuk Kim, Junmo Kim, Hyeongkeun Lee, Kyeongha Rho

arXiv · PDF · Open in the Atlas

Code that ran

6 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure of our instrument; 7 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/2403.09502.json · badge: /api/ran/2403.09502.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
JongSuk1/EquiAV canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
jongsuk1/equiav community
Papers with Code archive
4 ran · 3 no recorded run
FunctionStatusWhere it lives
CrossAttention Ran
ran on a synthesized input · constructed an object; no result was computed
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("d4d9aba462915ffd")
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, CrossAttention: 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)

# Define ARGS dict with all parameters for CrossAttention.__init__
ARGS = {
    'q_dim': 4,
    'kv_dim': 5,
    'dim_head': 8,
    'num_heads': 2,
    'qkv_bias': False,
    'qk_norm': False,
    'attn_drop': 0.1,
    'norm_layer': nn.LayerNorm
}
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 CrossAttention — 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 CrossAttention 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
CrossAttentionBlock Ran
ran on a synthesized input · constructed an object; no result was computed
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("894dad2556348ddd")
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, CrossAttentionBlock: 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
from timm.models.layers import DropPath
from timm.models.vision_transformer import Mlp

torch.manual_seed(0)

# Build the ARGS dictionary with all parameters for CrossAttentionBlock
ARGS = {
    'emb_dim': 64,
    'aug_emb_dim': 48,
    'num_heads': 8,
    'mlp_ratio': 4.0,
    'qkv_bias': False,
    'drop': 0.0,
    'attn_drop': 0.0,
    'drop_path': 0.0,
    'act_layer': nn.GELU,
    'norm_layer': nn.LayerNorm,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CrossAttentionBlock — 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 CrossAttentionBlock 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
MLPProjectionHead Ran
ran on a synthesized input · constructed an object; no result was computed
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("f5a101a28eb19371")
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, MLPProjectionHead: 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 = {
    "in_dim": 4,
    "hidden_dim": 8,
    "out_dim": 3,
    "norm_layer": nn.LayerNorm,
    "act_layer": nn.ReLU,
    "drop": 0.1,
}
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 MLPProjectionHead — 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 MLPProjectionHead 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
PatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("fe14abb5583a3609")
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, PatchEmbed: 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
from timm.models.layers import to_2tuple, trunc_normal_, DropPath

torch.manual_seed(0)

ARGS = {
    "img_size": 224,
    "patch_size": 16,
    "in_chans": 3,
    "embed_dim": 768,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PatchEmbed — 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 PatchEmbed 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
compute_metrics Ran
ran; our contract draft was wrong, not the code
JongSuk1/EquiAV/retrieval.py
code served (permissive licence) · get_code("d59b4b3c004c31ff")
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 dict. 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 numpy as np

# The function compute_metrics expects x to be a 2D numpy array
# It sorts negated values, extracts diagonals, and computes ranking metrics
# The array should have shape (n, n) where n is the number of samples

np.random.seed(0)

# Create a small square matrix for testing
# Shape: (4, 4) - small enough for testing
x = np.random.randn(4, 4).astype(np.float32)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_sim_mat Ran
ran, honoured the contract we drafted
JongSuk1/EquiAV/retrieval.py
code served (permissive licence) · get_code("a1ababfdce80565d")
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 ndarray, ndim 2, dtype family float, shape (2, 2) 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 numpy as np
import torch

np.random.seed(0)
torch.manual_seed(0)

# The function expects:
# a: numpy array of shape [B, D] where B is batch size and D is dimension
# b: numpy array of shape [B, D] with same batch size B and dimension D
# It computes cosine similarity between all pairs of vectors

B = 2  # batch size
D = 4  # dimension

a = np.random.randn(B, D).astype(np.float32)
b = np.random.randn(B, D).astype(np.float32)

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) 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
Block Not yet run
unverified (harvested, no recorded run)
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("76fafb76150402b2")
How it ran

no invocation recorded.

MainModel Not yet run
unverified (harvested, no recorded run)
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("291f78cc0fbb175c")
How it ran

no invocation recorded.

get_1d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
JongSuk1/EquiAV/models/pos_embed.py
pointer only (licence: MIT); the stored copy get_code serves, from zhangyifei01/LMIM, is pointer only (licence: NONE) · get_code("12035a2f77d8016c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhangyifei01/LMIM, and GitHub detected no licence in that repository when it was checked. 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. No invocation recorded.

get_2d_sincos_pos_embed Not yet run
unverified (harvested, no recorded run)
jongsuk1/equiav/models/pt_EquiAV.py
code served (permissive licence) · get_code("660403f722993455")
How it ran

no invocation recorded.

get_2d_sincos_pos_embed Not yet run
unverified (harvested, no recorded run)
JongSuk1/EquiAV/models/pos_embed.py
code served (permissive licence) · get_code("57abad7bed6d36ff")
How it ran

no invocation recorded.

get_2d_sincos_pos_embed_from_grid Not yet run
unverified (harvested, no recorded run)
JongSuk1/EquiAV/models/pos_embed.py
pointer only (licence: MIT); the stored copy get_code serves, from zhangyifei01/LMIM, is pointer only (licence: NONE) · get_code("f10004e059714d42")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhangyifei01/LMIM, and GitHub detected no licence in that repository when it was checked. 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. No invocation recorded.

get_retrieval_result Not yet run
unverified (harvested, no recorded run)
JongSuk1/EquiAV/retrieval.py
code served (permissive licence) · get_code("cf8971124ae68c20")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 2 the same month, 5 later) and 6 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
get_2d_sincos_pos_embed_from_grid
brick of this paper's assembly: helper
190 other papers
74 dated earlier, 6 the same month, 109 later, 1 same year, order not determinable · 65 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
and 187 more not named here
get_1d_sincos_pos_embed_from_grid
brick of this paper's assembly: helper
39 other papers
32 dated earlier, 7 later · 25 only as an assembly brick
2105.12723 (2021-05)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2204.09435 (2022-04)
Hephaestus: A large scale multitask dataset towards InSAR understanding
and 36 more not named here
PatchEmbed
brick of this paper's assembly: model
4 other papers
1 dated earlier, 1 the same month, 2 later · 3 only as an assembly brick
2210.07839 (2022-10)
Contrastive Audio-Visual Masked Autoencoder
2403.19638 (2024-03)
Siamese Vision Transformers are Scalable Audio-visual Learners
2501.02030 (2025-01)
Detecting Music Performance Errors with Transformers
and 1 more not named here
get_2d_sincos_pos_embed
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 1 only as an assembly brick
2210.07839 (2022-10)
Contrastive Audio-Visual Masked Autoencoder
2501.02030 (2025-01)
Detecting Music Performance Errors with Transformers
2505.01237 (2025-05)
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
Block
brick of this paper's assembly: model
2 other papers
1 dated earlier, 1 later · 2 only as an assembly brick
2210.07839 (2022-10)
Contrastive Audio-Visual Masked Autoencoder
2505.01237 (2025-05)
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment
compute_metrics 2 other papers
2 dated earlier
1808.02559 (2018-08)
A Joint Sequence Fusion Model for Video Question Answering and Retrieval
1912.06430 (2019-12)
End-to-End Learning of Visual Representations from Uncurated Instructional Videos

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

Recent advancements in self-supervised audiovisual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning methods, audio-visual learning has struggled to fully harness these benefits, as augmentations can easily disrupt the correspondence between input pairs. To address this limitation, we introduce EquiAV, a novel framework that leverages equivariance for audio-visual contrastive learning. Our approach begins with extending equivariance to audio-visual learning, facilitated by a shared attention-based transformation predictor. It enables the aggregation of features from diverse augmentations into a representative embedding, providing robust supervision. Notably, this is achieved with minimal computational overhead. Extensive ablation studies and qualitative results verify the effectiveness of our method. EquiAV outperforms previous works across various audiovisual benchmarks. The code is available on https://github.com/JongSuk1/EquiAV

For agents

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

get_harvested_code_for_paper("2403.09502")
get_code_for_paper("2403.09502")
have("2403.09502")

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

curl https://syntology.ai/api/ran/2403.09502.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.09502.svg)](https://syntology.ai/paper/2403.09502)

Connect an agent — have() is free.