SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.06181 · 2018

Dual Encoding for Zero-Example Video Retrieval

arXiv · PDF · Open in the Atlas

Code that ran

14 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 3 failures of our instrument; 0 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/1809.06181.json · badge: /api/ran/1809.06181.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
danieljf24/dual_encoding canonical (classifier label)
classifier basis: census
14 ran · 0 no recorded run
FunctionStatusWhere it lives
cal_error Ran
ran on a synthesized input
danieljf24/dual_encoding/evaluation.py
code served (permissive licence) · get_code("f0d62466a8eb8596")
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 (3, 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

# Create small sample data for videos and captions
# videos: shape (2, 4) - 2 samples, 4-dimensional embeddings
videos = np.random.randn(2, 4).astype(np.float32)

# captions: shape (3, 4) - 3 samples, 4-dimensional embeddings
captions = np.random.randn(3, 4).astype(np.float32)

# measure: distance metric to use
measure = 'cosine'

ARGS = {
    'videos': videos,
    'captions': captions,
    'measure': measure
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (3, 2) — shape (3, 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
checkToSkip Ran
ran on a synthesized input
danieljf24/dual_encoding/basic/common.py
code served (permissive licence) · get_code("7ca6f198648a8c2f")
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 int, ndim 0, dtype family int, shape () 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 os
import tempfile

# Create a temporary file path that exists
temp_dir = tempfile.gettempdir()
existing_file = os.path.join(temp_dir, "test_existing_file.txt")
with open(existing_file, 'w') as f:
    f.write("test")

ARGS = {
    "filename": existing_file,
    "overwrite": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () 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
cosine_sim Ran
ran; our contract draft was wrong, not the code
danieljf24/dual_encoding/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kadarakos/mulisera, is pointer only (licence: NONE) · get_code("9b0a787b92a87023")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kadarakos/mulisera, 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. A run is recorded.

deserialize_keras_object Ran
ran on a synthesized input
danieljf24/dual_encoding/basic/generic_utils.py
code served (permissive licence) · get_code("4c86980038a0bfa1")
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 CustomLayer. 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 sys
import six
import inspect

# Define a minimal class with from_config method
class CustomLayer:
    def __init__(self, units=10, activation='relu'):
        self.units = units
        self.activation = activation
    
    @classmethod
    def from_config(cls, config, custom_objects=None):
        return cls(**config)

# Define a class without from_config
class SimpleClass:
    def __init__(self, param1='value1', param2='value2'):
        self.param1 = param1
        self.param2 = param2

# Test case 1: Dict-based identifier with class_name
identifier_dict = {
    'class_name': 'CustomLayer',
    'config': {
        'units': 20,
        'activation': 'sigmoid'
    }
}

# Test case 2: String-based identifier
identifier_string = 'my_function'

# Define a simple function for testing
def my_function(x):
    return x * 2

# Module objects dict containing available classes and functions
module_objects = {
    'CustomLayer': CustomLayer,
    'SimpleClass': SimpleClass,
    'my_function': my_function
}

# Custom objects dict
custom_objects = {
    'CustomClass': SimpleClass
}

# Prepare arguments for different test scenarios
ARGS = {
    'identifier': identifier_dict,
    'module_objects': module_objects,
    'custom_objects': custom_objects,
    'printable_module_name': 'object'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CustomLayer — a CustomLayer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CustomLayer 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
euclidean_sim Ran
ran; our contract draft was wrong, not the code
danieljf24/dual_encoding/loss.py
code served (permissive licence) · get_code("efbc5b769d3027ca")
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 (3, 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 torch
import numpy as np

torch.manual_seed(0)

# The function takes two tensors: im and s
# From the body:
# - s.unsqueeze(1).expand(s.size(0), im.size(0), s.size(1))
# - im.unsqueeze(0).expand(s.size(0), im.size(0), s.size(1))
# - YmX.pow(2).sum(2).t()
# 
# This suggests:
# - s has shape (batch_s, embedding_dim)
# - im has shape (batch_im, embedding_dim)
# The operation creates (batch_s, batch_im, embedding_dim) tensors
# and computes euclidean distance

batch_s = 2
batch_im = 3
embedding_dim = 4

# Create im: image embeddings with shape (batch_im, embedding_dim)
im = torch.randn(batch_im, embedding_dim)

# Create s: sentence embeddings with shape (batch_s, embedding_dim)
s = torch.randn(batch_s, embedding_dim)

ARGS = {
    "im": im,
    "s": s,
}
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 Tensor, ndim 2, dtype family float, shape (3, 2) — shape (3, 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
func_dump Ran
ran on a synthesized input
danieljf24/dual_encoding/basic/generic_utils.py
code served (permissive licence) · get_code("2a22cf19f80d1a68")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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 marshal
import codecs

def sample_function(x, y):
    """A simple user-defined function with closure variables."""
    z = x + y
    return z * 2

ARGS = {
    "func": sample_function
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
getVideoId Ran
ran on a synthesized input
danieljf24/dual_encoding/basic/util.py
code served (permissive licence) · get_code("1d761438a684a77f")
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 str. 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.

ARGS = {
    'cap_id': 'video123#caption_text'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_learning_rate Ran
ran on a synthesized input
danieljf24/dual_encoding/trainer.py
code served (permissive licence) · get_code("39751868d8fb921d")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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
import torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

# Create an optimizer with param_groups that have 'lr' keys
optimizer = optim.SGD(model.parameters(), lr=0.001)

ARGS = {
    'optimizer': optimizer
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
l2norm Ran
ran; our contract draft was wrong, not the code
danieljf24/dual_encoding/model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kadarakos/mulisera, is pointer only (licence: NONE) · get_code("741174c85c8d06ad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kadarakos/mulisera, 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. A run is recorded.

l2norm Ran
ran on a synthesized input
danieljf24/dual_encoding/evaluation.py
code served (permissive licence) · get_code("397dccf0a72eb52c")
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, 4) 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

# Create a small test matrix with shape (2, 4)
# This will be L2-normalized along axis=1 (across columns for each row)
X = np.array([
    [3.0, 4.0, 0.0, 0.0],
    [1.0, 1.0, 1.0, 1.0]
], dtype=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 ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
load_config Ran
ran on a synthesized input
danieljf24/dual_encoding/tester.py
code served (permissive licence) · get_code("8a7f4b647afc154c")
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 tempfile
import os

# Create a temporary config file
temp_dir = tempfile.mkdtemp()
config_file = os.path.join(temp_dir, "config.py")

# Write a minimal valid config
config_content = """
config = {
    'model_name': 'test_model',
    'batch_size': 32,
    'learning_rate': 0.001,
    'num_epochs': 10
}
"""

with open(config_file, 'w') as f:
    f.write(config_content)

ARGS = {
    'config_path': config_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
order_sim Ran
ran on a synthesized input
danieljf24/dual_encoding/loss.py
code served (permissive licence) · get_code("da16023b8239c604")
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 (2, 3) 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)

# Based on the function body, it expects:
# - im: a tensor that will be unsqueezed at dimension 0, so needs shape (num_images, embedding_dim)
# - s: a tensor that will be unsqueezed at dimension 1, so needs shape (num_sentences, embedding_dim)
# Both tensors are used in broadcasting and arithmetic operations

# Create small tensors with distinct dimensions
# im: (2, 4) - 2 images, 4-dim embeddings
# s: (3, 4) - 3 sentences, 4-dim embeddings
im = torch.randn(2, 4)
s = torch.randn(3, 4)

ARGS = {
    "im": im,
    "s": s,
}
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 (2, 3) — shape (2, 3) 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
read_dict Ran
ran on a synthesized input
danieljf24/dual_encoding/basic/util.py
code served (permissive licence) · get_code("cf46aeba3c8af36f")
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 tempfile
import os

# Create a temporary file with dict content
temp_dir = tempfile.mkdtemp()
filepath = os.path.join(temp_dir, "test_dict.txt")

# Write a valid Python dict representation to the file
test_dict = {"key1": "value1", "key2": 42, "key3": [1, 2, 3]}
with open(filepath, 'w') as f:
    f.write(str(test_dict))

ARGS = {
    "filepath": filepath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
serialize_keras_object Ran
ran on a synthesized input
danieljf24/dual_encoding/basic/generic_utils.py
code served (permissive licence) · get_code("2523689649dade4a")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a mock Keras-like object with get_config method
class MockKerasLayer(nn.Module):
    def __init__(self):
        super().__init__()
        self.units = 64
        self.activation = 'relu'
    
    def get_config(self):
        return {
            'units': self.units,
            'activation': self.activation
        }
    
    def forward(self, x):
        return x

# Test case 1: Object with get_config method
keras_object = MockKerasLayer()

# Test case 2: Function object (has __name__)
def dummy_function():
    pass

# Test case 3: None value
none_value = None

# Create a list to test multiple cases
test_instances = [keras_object, dummy_function, none_value]

# ARGS will test the first instance (with get_config)
ARGS = {
    'instance': keras_object
}
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 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

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 12 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 12 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
cosine_sim 12 other papers
2 dated earlier, 10 later
1707.05612 (2017-07)
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
1806.10348 (2018-06)
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples
1909.05506 (2019-09)
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
and 9 more not named here
order_sim 7 other papers
7 later
2004.09144 (2020-04)
Transformer Reasoning Network for Image-Text Matching and Retrieval
2008.05231 (2020-08)
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
2104.00650 (2021-04)
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
and 4 more not named here
l2norm 6 other papers
1 dated earlier, 5 later
1707.05612 (2017-07)
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
2002.02814 (2020-02)
Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network
2004.09144 (2020-04)
Transformer Reasoning Network for Image-Text Matching and Retrieval
and 3 more not named here
checkToSkip 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
deserialize_keras_object 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
euclidean_sim 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
func_dump 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
getVideoId 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
get_learning_rate 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
l2norm 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
read_dict 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval
serialize_keras_object 1 other paper
1 later
136960251 (2022 (year only))
Learning Linguistic Association Towards Efficient Text-Video Retrieval

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

This paper attacks the challenging problem of zero-example video retrieval. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described in natural language text with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is required. The majority of existing methods are concept based, extracting relevant concepts from queries and videos and accordingly establishing associations between the two modalities. In contrast, this paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Dual encoding is conceptually simple, practically effective and end-to-end. As experiments on three benchmarks, i.e. MSR-VTT, TRECVID 2016 and 2017 Ad-hoc Video Search show, the proposed solution establishes a new state-of-the-art for zero-example video retrieval.

For agents

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

get_harvested_code_for_paper("1809.06181")
get_code_for_paper("1809.06181")
have("1809.06181")

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

curl https://syntology.ai/api/ran/1809.06181.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.06181.svg)](https://syntology.ai/paper/1809.06181)

Connect an agent — have() is free.