SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.05546 · ECCV · 2024

AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling

Misha Sra, Sherry Chen, Yaron Vaxman, Elad Baruch, David Asulin, Aviad Moreshet, Pradeep Sen

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures 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/2407.05546.json · badge: /api/ran/2407.05546.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
SherryXTChen/AID-Appeal canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get_augmentation Ran
ran; our contract draft was wrong, not the code
SherryXTChen/AID-Appeal/datasets.py
code served (permissive licence) · get_code("1b97ef2d481d518f")
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 Compose. 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 torchvision.transforms as transforms

class OptConfig:
    def __init__(self):
        self.image_size = 224

opt = OptConfig()

ARGS = {
    'opt': opt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
preprocess_image Ran
ran, honoured the contract we drafted
SherryXTChen/AID-Appeal/datasets.py
code served (permissive licence) · get_code("eb96a9c3af9b85c8")
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 3, dtype family float, shape (3, 80, 80) 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 torchvision.transforms as transforms
from PIL import Image
import io

torch.manual_seed(0)

# Create a minimal valid image file in memory
def create_test_image():
    img = Image.new('RGB', (100, 80), color='red')
    img_bytes = io.BytesIO()
    img.save(img_bytes, format='PNG')
    img_bytes.seek(0)
    return img_bytes

# We need to write to a temporary file since Image.open expects a path
import tempfile
import os

temp_dir = tempfile.mkdtemp()
test_image_path = os.path.join(temp_dir, 'test.png')
test_img = Image.new('RGB', (100, 80), color='red')
test_img.save(test_image_path)

# Define augmentation as identity (does nothing)
class IdentityAugmentation:
    def __call__(self, image):
        return image

# Define transform to convert PIL image to tensor
transform = transforms.Compose([
    transforms.ToTensor(),
])

augmentation = IdentityAugmentation()

ARGS = {
    'image_path': test_image_path,
    'augmentation': augmentation,
    'transform': transform,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 80, 80) — shape (3, 80, 80) 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
setup_processing Ran
ran; our contract draft was wrong, not the code
SherryXTChen/AID-Appeal/dataset_creation/synthetic_appeal_dataset_creation.py
code served (permissive licence) · get_code("15d6cfb9ca16ff03")
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 MockP. 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 copy
from PIL import Image
import torch
import numpy as np

class MockP:
    """Stand-in object for the 'p' parameter that has attributes to be copied and modified."""
    def __init__(self):
        self.seed = 0
        self.prompt = ""
        self.negative_prompt = ""
        self.init_images = []
        self.image_mask = None
        self.inpainting_fill = 0
        self.denoising_strength = 1.0

p = MockP()

prompt = "a dog wearing sunglasses"
negative_prompt = "blurry, low quality"
init_images = [Image.new('RGB', (64, 48), color='red'), Image.new('RGB', (64, 48), color='blue')]
image_mask = Image.new('L', (64, 48), color=128)
inpainting_fill = 1
denoising_strength = 0.75
seed = 42

ARGS = {
    "p": p,
    "prompt": prompt,
    "negative_prompt": negative_prompt,
    "init_images": init_images,
    "image_mask": image_mask,
    "inpainting_fill": inpainting_fill,
    "denoising_strength": denoising_strength,
    "seed": seed,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockP — a MockP output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockP 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
sharpen_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SherryXTChen/AID-Appeal/dataset_creation/image_filtering.py
code served (permissive licence) · get_code("79493f3a4c7755ee")
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 3, dtype family int, shape (4, 3, 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 numpy as np
import cv2

# Create a small test image
# Using uint8 (typical for images) with shape (height, width, channels)
image = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

ARGS = {
    "image": image
}
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 ndarray, ndim 3, dtype family int, shape (4, 3, 3) — shape (4, 3, 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
split_data Ran
ran; our contract draft was wrong, not the code
SherryXTChen/AID-Appeal/datasets.py
code served (permissive licence) · get_code("d43aee5d3b5057f8")
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 os
from collections import defaultdict

# Construct valid arguments for split_data function

# Create a list of data paths that includes both directory paths (ending with /)
# and file paths (ending with .jpg). The function extracts the first 2 underscore-
# separated parts of the basename as data_type.

data_path_list = [
    'dataset_type1_part1/',
    'dataset_type1_part2.jpg',
    'dataset_type1_part3/',
    'dataset_type2_part1.jpg',
    'dataset_type2_part2/',
    'dataset_type2_part3.jpg',
    'dataset_type1_part4.jpg',
    'dataset_type2_part4/',
]

# split_start and split_end define the fraction of data to use
# Must satisfy: 0 <= split_start < split_end <= 1
split_start = 0.2
split_end = 0.8

ARGS = {
    'data_path_list': data_path_list,
    'split_start': split_start,
    'split_end': split_end,
}
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 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
if_food Not yet run
unverified (harvested, no recorded run)
SherryXTChen/AID-Appeal/dataset_creation/image_filtering.py
code served (permissive licence) · get_code("40107467e6a6c9c1")
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, 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 6 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

We propose Image Content Appeal Assessment (ICAA), a novel metric that quantifies the level of positive interest an image's content generates for viewers, such as the appeal of food in a photograph. This is fundamentally different from traditional Image-Aesthetics Assessment (IAA), which judges an image's artistic quality. While previous studies often confuse the concepts of "aesthetics" and "appeal," our work addresses this by being the first to study ICAA explicitly. To do this, we propose a novel system that automates dataset creation and implements algorithms to estimate and boost content appeal. We use our pipeline to generate two large-scale datasets (70K+ images each) in diverse domains (food and room interior design) to train our models, which revealed little correlation between content appeal and aesthetics. Our user study, with more than 76% of participants preferring the appeal-enhanced images, confirms that our appeal ratings accurately reflect user preferences, establishing ICAA as a unique evaluative criterion. Our code and datasets are available at https://github.com/SherryXTChen/AID-Appeal.

For agents

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

get_harvested_code_for_paper("2407.05546")
get_code_for_paper("2407.05546")
have("2407.05546")

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

curl https://syntology.ai/api/ran/2407.05546.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.05546.svg)](https://syntology.ai/paper/2407.05546)

Connect an agent — have() is free.