SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.19638 · ECCV · 2024

Siamese Vision Transformers are Scalable Audio-visual Learners

Gedas Bertasius, Yan-Bo Lin

arXiv · PDF · Open in the Atlas

Code that ran

15 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 1 violated it and 3 have no contract verdict; 8 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/2403.19638.json · badge: /api/ran/2403.19638.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
genjib/avsiam canonical (classifier label)
classifier basis: census
12 ran · 3 no recorded run
GenjiB/AVSiam community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input · constructed an object; no result was computed
GenjiB/AVSiam/src/models/cav_mae_base.py
pointer only (licence: NONE) · get_code("7ade838e8920e111")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GenjiB/AVSiam 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. A run is recorded.

Block Ran
ran on a synthesized input · constructed an object; no result was computed
GenjiB/AVSiam/src/models/cav_mae_base.py
pointer only (licence: NONE) · get_code("534488ebed89ff98")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GenjiB/AVSiam 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. A run is recorded.

GatherLayer Ran
ran on a synthesized input · constructed an object; no result was computed
GenjiB/AVSiam/src/models/cav_mae_base.py
pointer only (licence: NONE) · get_code("06f4ef2afc928c74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GenjiB/AVSiam 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. A run is recorded.

cosine_scheduler Ran
ran, honoured the contract we drafted
genjib/avsiam/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from boyazeng/understand_bias, is pointer only (licence: NONE) · get_code("b700fb0a3496b255")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

distributed_concat Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
genjib/avsiam/src/traintest_cavmae_base.py
pointer only (licence: NONE) · get_code("fc419f8d3ed996b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

get_grad_norm_ Ran
ran, honoured the contract we drafted
genjib/avsiam/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from sekeunkim/echofm, is pointer only (licence: NONE) · get_code("ba1356e8ceb654d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

get_immediate_subdirectories Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/retrieval.py
pointer only (licence: NONE) · get_code("e217fb47bef3abe4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

get_sim_mat Ran
ran, honoured the contract we drafted
genjib/avsiam/src/retrieval.py
pointer only (licence: NONE) · get_code("72584682b61aedb0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

get_similarity Ran
ran, violated the contract we drafted
genjib/avsiam/src/retrieval.py
pointer only (licence: NONE) · get_code("04fa3bcbfec2c0c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

lookup_list Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/dataloader.py
pointer only (licence: NONE) · get_code("c15efdd12442aeb4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

make_index_dict Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/dataloader.py
pointer only (licence: NONE) · get_code("a8fb3f62e2a901d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

make_name_dict Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/dataloader.py
pointer only (licence: NONE) · get_code("cbf115a314bcd23e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

multiple_samples_collate Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from Alvin-Zeng/temporal-robustness-benchmark, is pointer only (licence: NONE) · get_code("024894a396cde124")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

remove_data_parallel Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/run_cavmae_ft_base.py
pointer only (licence: NONE) · get_code("d75abe35d8363cd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

wa_model Ran
ran; our contract draft was wrong, not the code
genjib/avsiam/src/run_cavmae_ft_base.py
pointer only (licence: NONE) · get_code("b862a6e8aa9d205a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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. A run is recorded.

CAVMAE_BASE Not yet run
unverified (harvested, no recorded run)
GenjiB/AVSiam/src/models/cav_mae_base.py
pointer only (licence: NONE) · get_code("d123c3dc102fe116")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GenjiB/AVSiam 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.

validate Not yet run
unverified (harvested, no recorded run)
genjib/avsiam/src/traintest_cavmae_base.py
pointer only (licence: NONE) · get_code("1edf032c61297c85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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.

validate Not yet run
unverified (harvested, no recorded run)
genjib/avsiam/src/traintest_ft_base.py
pointer only (licence: NONE) · get_code("64f4a07393bf408b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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.

validate_mlp Not yet run
unverified (harvested, no recorded run)
genjib/avsiam/src/traintest_cavmae_base.py
pointer only (licence: NONE) · get_code("2c0dfd9400b965e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, genjib/avsiam 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.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 3 the same month, 5 later) and 9 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
cosine_scheduler 26 other papers
18 dated earlier, 1 the same month, 6 later, 1 same year, order not determinable
1905.02244 (2019-05)
Searching for MobileNetV3
136810051 (2022 (year only))
AMixer: Adaptive Weight Mixing for Self-Attention Free Vision Transformers
136860514 (2022 (year only))
SLIP: Self-supervision meets Language-Image Pre-training
and 23 more not named here
get_grad_norm_ 21 other papers
5 dated earlier, 1 the same month, 15 later
2308.00566 (2023-08)
Stochastic positional embeddings improve masked image modeling
2310.12979 (2023-10)
Predicting a Protein's Stability under a Million Mutations
2311.13627 (2023-11)
Vamos: Versatile Action Models for Video Understanding
and 18 more not named here
lookup_list 7 other papers
4 dated earlier, 3 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2307.03183 (2023-07)
Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
and 4 more not named here
make_index_dict 7 other papers
4 dated earlier, 3 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2307.03183 (2023-07)
Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
and 4 more not named here
make_name_dict 7 other papers
4 dated earlier, 3 later
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2307.03183 (2023-07)
Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers
and 4 more not named here
get_immediate_subdirectories 3 other papers
3 dated earlier
2110.09784 (2021-10)
SSAST: Self-Supervised Audio Spectrogram Transformer
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
2311.11177 (2023-11)
Assessing the Security of GitHub Copilot Generated Code -- A Targeted Replication Study
multiple_samples_collate 2 other papers
1 dated earlier, 1 the same month
2308.04549 (2023-08)
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
2403.20254 (2024-03)
Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
distributed_concat 1 other paper
1 dated earlier
2308.01686 (2023-08)
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
get_sim_mat 1 other paper
1 dated earlier
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models
get_similarity 1 other paper
1 dated earlier
2208.00061 (2022-08)
UAVM: Towards Unifying Audio and Visual Models

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

Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual pretraining. Our framework uses a single shared vision transformer backbone to process audio and visual inputs, improving its parameter efficiency, reducing the GPU memory footprint, and allowing us to scale our method to larger datasets and model sizes. We pretrain our model using a contrastive audio-visual matching objective with a multi-ratio random masking scheme, which enables our model to process larger audio-visual instance batches, helpful for contrastive learning. Unlike prior audio-visual methods, our method can robustly handle audio, visual, and audio-visual inputs with a single shared ViT backbone. Furthermore, despite using the shared backbone for both modalities, AVSiam achieves competitive or even better results than prior methods on AudioSet and VGGSound for audio-visual classification and retrieval. Our code is available at https://github.com/GenjiB/AVSiam

For agents

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

get_harvested_code_for_paper("2403.19638")
get_code_for_paper("2403.19638")
have("2403.19638")

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

curl https://syntology.ai/api/ran/2403.19638.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.19638.svg)](https://syntology.ai/paper/2403.19638)

Connect an agent — have() is free.