SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.02568 · 2020

Multimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability

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 (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures 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/2009.02568.json · badge: /api/ran/2009.02568.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
cfosco/memento_keras community (classifier label)
classifier basis not recorded on the link
6 ran · 7 no recorded run
FunctionStatusWhere it lives
conv3d_bn Ran
ran on a synthesized input
cfosco/memento_keras/src/i3d_inception.py
code served (permissive licence) · get_code("bf1dc83f1366e68c")
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 KerasTensor. 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
from tensorflow import keras
from tensorflow.keras import backend as K

# Set image data format to channels_last (default)
K.set_image_data_format('channels_last')

# Create a small input tensor
# Shape: (batch_size, depth, height, width, channels)
input_tensor = keras.Input(shape=(4, 3, 5, 2))

ARGS = {
    'x': input_tensor,
    'filters': 8,
    'num_frames': 3,
    'num_row': 2,
    'num_col': 2,
    'padding': 'same',
    'strides': (1, 1, 1),
    'use_bias': False,
    'use_activation_fn': True,
    'use_bn': True,
    'name': 'test_conv3d_bn'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor 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
create_command Ran
ran on a synthesized input
cfosco/memento_keras/src/job_utils.py
code served (permissive licence) · get_code("4d4eaadab842c496")
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.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'ckpt': '/path/to/checkpoint.pth',
    'dataset': 'HMDB51',
    'model_type': 'i3d',
    'num_classes': 51,
    'split': 1,
    'verbose': 1,
    'batch_size': 5,
    'gpus': 4,
    'workers': 10,
    'use_mp': 0,
    'type': 'rgb',
    'do_per_class': 0,
    'extra_cmd': ''
}
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 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
load_2_frames Ran
ran on a synthesized input
cfosco/memento_keras/src/memento_utils.py
code served (permissive licence) · get_code("8aaf079b0fa220fe")
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 4, 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 numpy as np
import os
import tempfile
import cv2
from cv2 import imread, resize

# Create a temporary directory with dummy frame images
temp_dir = tempfile.mkdtemp()

# Create 20 dummy frames (224x224 RGB images)
for i in range(20):
    # Create a simple numpy array and save as image
    frame = np.random.randint(0, 256, (224, 224, 3), dtype=np.uint8)
    frame_path = os.path.join(temp_dir, f"frame_{i:03d}.png")
    cv2.imwrite(frame_path, frame)

ARGS = {
    "frames_folder": temp_dir,
    "space_between_frames": 5,
    "verbose": True,
    "is_train": False,
    "img_size": (224, 224)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, 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
load_videomem_captions Ran
ran on a synthesized input
cfosco/memento_keras/src/captioning_utils.py
code served (permissive licence) · get_code("fb2e11f0f805a4a5")
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 caption data in the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_filepath = temp_file.name

# Write sample data in the format the function expects
# Format: "name caption-with-hyphens"
sample_data = """video1 this-is-a-caption
video2 another-sample-caption
video3 one-more-test
"""

temp_file.write(sample_data)
temp_file.close()

ARGS = {
    'filepath': temp_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
step_decay Ran
ran on a synthesized input
cfosco/memento_keras/src/memento_utils.py
code served (permissive licence) · get_code("52cf5153e77f0902")
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 function. 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 math

# Analyze the function: step_decay takes init_lr, drop, epochs_drop, and min_lr
# It returns an inner function that takes epoch and computes a learning rate
# All parameters are numeric (float/int), no complex objects needed

ARGS = {
    "init_lr": 0.0001,
    "drop": 0.1,
    "epochs_drop": 3.0,
    "min_lr": 1e-07
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
top_3_accuracy Ran
ran on a synthesized input
cfosco/memento_keras/src/keras_training.py
code served (permissive licence) · get_code("73819bbd2f8a1f69")
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 EagerTensor, ndim 1, dtype family float, shape (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
from keras.metrics import top_k_categorical_accuracy

# Set seed for reproducibility
torch.manual_seed(0)

# Create small dummy data for the function
# y_true: one-hot encoded or class indices (batch_size=2)
# y_pred: predictions/logits (batch_size=2, num_classes=4)

batch_size = 2
num_classes = 4

# y_true: one-hot encoded format (2, 4)
y_true = np.array([
    [1, 0, 0, 0],
    [0, 1, 0, 0]
], dtype=np.float32)

# y_pred: predicted probabilities or logits (2, 4)
# Make predictions where top-3 includes the true class
y_pred = np.array([
    [0.7, 0.2, 0.05, 0.05],
    [0.1, 0.6, 0.2, 0.1]
], dtype=np.float32)

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float, shape (2,) — shape (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
build_label2str Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/generator.py
code served (permissive licence) · get_code("1dc96782f73721cb")
How it ran

no invocation recorded.

build_str2label Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/generator.py
code served (permissive licence) · get_code("abffecf7b9824bba")
How it ran

no invocation recorded.

compute_optical_flow Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/i3d_preprocessing.py
code served (permissive licence) · get_code("357040be5805184b")
How it ran

no invocation recorded.

eval_i3d_over_splits Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/keras_eval.py
code served (permissive licence) · get_code("930ba3d9064ddc67")
How it ran

no invocation recorded.

load_2_frames_opencv Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/memento_utils.py
code served (permissive licence) · get_code("424c36ffa78628ed")
How it ran

no invocation recorded.

save_json Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/job_utils.py
code served (permissive licence) · get_code("a8efb7d59e3015ff")
How it ran

no invocation recorded.

top_5_accuracy Not yet run
unverified (harvested, no recorded run)
cfosco/memento_keras/src/keras_training.py
code served (permissive licence) · get_code("2d7160925cdf2fef")
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 13 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 13 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

A key capability of an intelligent system is deciding when events from past experience must be remembered and when they can be forgotten. Towards this goal, we develop a predictive model of human visual event memory and how those memories decay over time. We introduce Memento10k, a new, dynamic video memorability dataset containing human annotations at different viewing delays. Based on our findings we propose a new mathematical formulation of memorability decay, resulting in a model that is able to produce the first quantitative estimation of how a video decays in memory over time. In contrast with previous work, our model can predict the probability that a video will be remembered at an arbitrary delay. Importantly, our approach combines visual and semantic information (in the form of textual captions) to fully represent the meaning of events. Our experiments on two video memorability benchmarks, including Memento10k, show that our model significantly improves upon the best prior approach (by 12% on average).

For agents

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

get_harvested_code_for_paper("2009.02568")
get_code_for_paper("2009.02568")
have("2009.02568")

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

curl https://syntology.ai/api/ran/2009.02568.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.02568.svg)](https://syntology.ai/paper/2009.02568)

Connect an agent — have() is free.