SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.05068 · CVPR · 2021

Probabilistic Embeddings for Cross-Modal Retrieval

Seong Oh, Sanghyuk Chun, Yannis Kalantidis, Diane Larlus, Rafael Sampaio De Rezende

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 2 have no contract verdict; 1 failure of our instrument; 1 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/2101.05068.json · badge: /api/ran/2101.05068.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
VL-Group/2022-NeurIPS-DAA community
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
EncoderText Ran
ran on a synthesized input · constructed an object; no result was computed
VL-Group/2022-NeurIPS-DAA/model.py
code served (permissive licence) · get_code("038f061481e4d6d7")
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, EncoderText: 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 = {
    "vocab_size": 100,
    "word_dim": 4,
    "embed_size": 8,
    "num_layers": 1,
    "use_bi_gru": False,
    "no_txtnorm": False,
}
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 EncoderText — 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 EncoderText 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
Loss Ran
ran on a synthesized input · constructed an object; no result was computed
VL-Group/2022-NeurIPS-DAA/model.py
code served (permissive licence) · get_code("bc0cd89064229f55")
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, Loss: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Create valid arguments for the Loss class
loss_module = nn.Module()

# Construct the ARGS dictionary with all parameters for Loss.__init__
ARGS = {
    'margin': 0.5,
    'max_violation': False,
    'daa_weight': 25
}
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 Loss — 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 Loss 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
cider_compute Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VL-Group/2022-NeurIPS-DAA/model.py
code served (permissive licence) · get_code("dba1d4acee89488d")
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; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim 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)

# According to the function signature and docstring:
# tfidf is a tuple of (tfidf_GT, tfidf_single)
# tfidf_GT shape: (N, K, D) where N=batch_size, K=num_captions, D=vocab_length
# tfidf_single shape: (N, D)
# The function reshapes tfidf_GT to (-1, D) and computes mm with tfidf_single.t()
# Then reshapes back to (N, 5, -1), so K must be 5

N = 2  # batch size
K = 5  # number of ground-truth captions
D = 4  # vocabulary dimension

# Create tfidf_GT with shape (N, K, D) = (2, 5, 4)
tfidf_GT = torch.randn(N, K, D)

# Create tfidf_single with shape (N, D) = (2, 4)
tfidf_single = torch.randn(N, D)

# tfidf parameter is a tuple of these two tensors
tfidf = (tfidf_GT, tfidf_single)

ARGS = {
    "tfidf": tfidf,
    "eps": 1e-06
}
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 — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
SGRAF Not yet run
unverified (harvested, no recorded run)
VL-Group/2022-NeurIPS-DAA/model.py
code served (permissive licence) · get_code("e1a889cdcf785bd1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the task particularly challenging. Given an image (respectively a caption), there are multiple captions (respectively images) that equally make sense. In this paper, we argue that deterministic functions are not sufficiently powerful to capture such one-to-many correspondences. Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples from the different modalities are represented as probabilistic distributions in the common embedding space. Since common benchmarks such as COCO suffer from non-exhaustive annotations for crossmodal matches, we propose to additionally evaluate retrieval on the CUB dataset, a smaller yet clean database where all possible image-caption pairs are annotated. We extensively ablate PCME and demonstrate that it not only improves the retrieval performance over its deterministic counterpart but also provides uncertainty estimates that render the embeddings more interpretable. Code is available at https://github.com/naver-ai/pcme.

For agents

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

get_harvested_code_for_paper("2101.05068")
get_code_for_paper("2101.05068")
have("2101.05068")

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

curl https://syntology.ai/api/ran/2101.05068.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.05068.svg)](https://syntology.ai/paper/2101.05068)

Connect an agent — have() is free.