SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.07410 · 2019

ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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 2 have no contract verdict; 0 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/1908.07410.json · badge: /api/ran/1908.07410.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
MKLab-ITI/visil canonical (classifier label)
classifier basis: census
2 ran · 4 no recorded run
FunctionStatusWhere it lives
chamfer_similarity Ran
ran on a synthesized input
MKLab-ITI/visil/model/similarity.py
code served (permissive licence) · get_code("1495cfaac81f2e80")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

# Create a small similarity matrix for testing
# Shape: (batch_size=2, num_features_a=4, num_features_b=3)
sim_data = np.random.randn(2, 4, 3).astype(np.float32)
sim = tf.constant(sim_data)

ARGS = {
    "sim": sim,
    "max_axis": 1,
    "mean_axis": 0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor output has no array shape of its own; none is 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
symmetric_chamfer_similarity Ran
ran on a synthesized input
MKLab-ITI/visil/model/similarity.py
code served (permissive licence) · get_code("60fc9288d2497144")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

# Create a small similarity matrix (2x3x4 shape for distinct dimensions)
# This represents similarity scores between two sets of points
sim = tf.constant(np.random.randn(2, 3, 4), dtype=tf.float32)

ARGS = {
    "sim": sim,
    "axes": [0, 1]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor output has no array shape of its own; none is 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
preprocess_for_eval Not yet run
unverified (harvested, no recorded run)
MKLab-ITI/visil/model/nets/vgg_preprocessing.py
code served (permissive licence) · get_code("b35644780c2d36b7")
How it ran

no invocation recorded.

preprocess_for_train Not yet run
unverified (harvested, no recorded run)
MKLab-ITI/visil/model/nets/vgg_preprocessing.py
code served (permissive licence) · get_code("5348d906683c3ddb")
How it ran

no invocation recorded.

preprocess_image Not yet run
unverified (harvested, no recorded run)
MKLab-ITI/visil/model/nets/vgg_preprocessing.py
code served (permissive licence) · get_code("f9400a8b074c96ca")
How it ran

no invocation recorded.

triplet_loss Not yet run
unverified (harvested, no recorded run)
MKLab-ITI/visil/model/similarity.py
code served (permissive licence) · get_code("cb3be0da48af7c2b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
preprocess_image 2 other papers
2 dated earlier
1608.06993 (2016-08)
Densely Connected Convolutional Networks
1905.02231 (2019-05)
A Geometric Approach to Obtain a Bird's Eye View from an Image
preprocess_for_eval 1 other paper
1 dated earlier
1905.02231 (2019-05)
A Geometric Approach to Obtain a Bird's Eye View from an Image
preprocess_for_train 1 other paper
1 dated earlier
1905.02231 (2019-05)
A Geometric Approach to Obtain a Bird's Eye View from an Image

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

In this paper we introduce ViSiL, a Video Similarity Learning architecture that considers fine-grained Spatio-Temporal relations between pairs of videos -- such relations are typically lost in previous video retrieval approaches that embed the whole frame or even the whole video into a vector descriptor before the similarity estimation. By contrast, our Convolutional Neural Network (CNN)-based approach is trained to calculate video-to-video similarity from refined frame-to-frame similarity matrices, so as to consider both intra- and inter-frame relations. In the proposed method, pairwise frame similarity is estimated by applying Tensor Dot (TD) followed by Chamfer Similarity (CS) on regional CNN frame features - this avoids feature aggregation before the similarity calculation between frames. Subsequently, the similarity matrix between all video frames is fed to a four-layer CNN, and then summarized using Chamfer Similarity (CS) into a video-to-video similarity score -- this avoids feature aggregation before the similarity calculation between videos and captures the temporal similarity patterns between matching frame sequences. We train the proposed network using a triplet loss scheme and evaluate it on five public benchmark datasets on four different video retrieval problems where we demonstrate large improvements in comparison to the state of the art. The implementation of ViSiL is publicly available.

For agents

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

get_harvested_code_for_paper("1908.07410")
get_code_for_paper("1908.07410")
have("1908.07410")

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

curl https://syntology.ai/api/ran/1908.07410.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.07410.svg)](https://syntology.ai/paper/1908.07410)

Connect an agent — have() is free.