SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.11065 · 2022

MovieCLIP: Visual Scene Recognition in Movies

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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 6 have no contract verdict; 1 failure of our instrument; 3 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/2210.11065.json · badge: /api/ran/2210.11065.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
usc-sail/mica-MovieCLIP canonical (classifier label)
classifier basis not recorded on the link
8 ran · 3 no recorded run
FunctionStatusWhere it lives
generate_cmd_clip_list Ran
ran on a synthesized input
usc-sail/mica-MovieCLIP/preprocess_scripts/check_shot_segment_files_overlap.py
code served (permissive licence) · get_code("b20728fa672ca30b")
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
import tempfile
import shutil
from pathlib import Path

# Create temporary directory structure for testing
temp_base = tempfile.mkdtemp()

# Create sample folders with files
folder_names = ['folder1', 'folder2', 'folder3']
for folder_name in folder_names:
    folder_path = os.path.join(temp_base, folder_name)
    os.makedirs(folder_path, exist_ok=True)
    # Create some dummy files in each folder
    for i in range(3):
        file_path = os.path.join(folder_path, f'file_{i}.txt')
        with open(file_path, 'w') as f:
            f.write(f'dummy content {i}')

ARGS = {
    'folder_list': folder_names,
    'base_folder': temp_base
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tqdm — 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
generate_file_name Ran
ran on a synthesized input
usc-sail/mica-MovieCLIP/preprocess_scripts/check_shot_segment_files_overlap.py
code served (permissive licence) · get_code("7c0d71ba04363654")
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 os

def generate_file_name(file_path):
    scenes_index = file_path.index('Scenes')
    file_name = file_path[0:scenes_index - 1]
    return file_name

# The function expects a file_path string that contains 'Scenes' in it
# It finds the index of 'Scenes', then returns everything before it (minus 1 character)
file_path = "/home/user/data/Scenes/scene_001/frame_000.jpg"

ARGS = {
    "file_path": file_path
}
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
generate_video_key_wise_dictionary Ran
ran on a synthesized input
usc-sail/mica-MovieCLIP/preprocess_scripts/preprocess_movieCLIP_json_format.py
code served (permissive licence) · get_code("1c1579560a594d32")
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. 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 pandas as pd

# Create small CSV data with required columns
csv_data = pd.DataFrame({
    'Scene Number': [1, 2, 3],
    'Start Time (seconds)': [0.0, 10.5, 20.0],
    'End Time (seconds)': [5.0, 15.5, 25.0],
    'Start Frame': [0, 315, 600],
    'End Frame': [150, 465, 750]
})

# Create tag data dictionary matching expected structure
tag_data = {
    'video-Scene-001.mp4': {
        'Labels': ['action', 'drama'],
        'Values': [0.85, 0.65]
    },
    'video-Scene-002.mp4': {
        'Labels': ['comedy'],
        'Values': [0.45]
    },
    'video-Scene-003.mp4': {
        'Labels': ['thriller', 'suspense', 'drama'],
        'Values': [0.92, 0.78, 0.55]
    }
}

# File key used to construct scene names
file_key = 'video'

ARGS = {
    'file_key': file_key,
    'csv_data': csv_data,
    'tag_data': tag_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
getActivation Ran
ran on a synthesized input
usc-sail/mica-MovieCLIP/feature_extraction/extract_places365_features.py
code served (permissive licence) · get_code("f2cba7d64b723bb9")
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 torch
import torch.nn as nn

torch.manual_seed(0)

activation = {}

def getActivation(name):
    def hook(model, input, output):
        activation[name] = output.detach()
    return hook

# Build a simple model to test the hook
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()
name = "layer_output"

ARGS = {
    "name": name
}
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 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
linear_combination Ran
ran, honoured the contract we drafted
usc-sail/mica-MovieCLIP/losses/loss_functions.py
pointer only (licence: MIT); the stored copy get_code serves, from tmlr-group/atol, is pointer only (licence: NONE) · get_code("ee5e85cfd16bc5dc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tmlr-group/atol, 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.

optimizer_adam Ran
ran on a synthesized input
usc-sail/mica-MovieCLIP/optimizers/optimizer.py
code served (permissive licence) · get_code("fd9228d157bd9d54")
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 Adam. 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 minimal model with parameters
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()
lr = 0.001
weight_decay = 0.0001

ARGS = {
    "model": model,
    "lr": lr,
    "weight_decay": weight_decay
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
read_txt_file Ran
ran on a synthesized input
usc-sail/mica-MovieCLIP/preprocess_scripts/compute_distribution_visual_scene_labels.py
code served (permissive licence) · get_code("7596f0e252f8018d")
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 int; 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 tempfile
import os

# Create a temporary text file with the expected format
# Format: first element is ignored, rest are space-separated integers
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("image1 1 0 1 0\n")
temp_file.write("image2 1 1 0 1\n")
temp_file.write("image3 0 1 1 0\n")
temp_file.close()

ARGS = {
    'txt_file_path': temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tqdm — 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 int — 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
reduce_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
usc-sail/mica-MovieCLIP/losses/loss_functions.py
pointer only (licence: MIT); the stored copy get_code serves, from tmlr-group/atol, is pointer only (licence: NONE) · get_code("9f7b947fbfdaa657")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tmlr-group/atol, 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.

focal_loss Not yet run
unverified (harvested, no recorded run)
usc-sail/mica-MovieCLIP/losses/loss_functions.py
code served (permissive licence) · get_code("4bebda9ddfdffe0a")
How it ran

no invocation recorded.

generate_video_tensor_cv2 Not yet run
unverified (harvested, no recorded run)
usc-sail/mica-MovieCLIP/feature_extraction/extract_places365_features.py
code served (permissive licence) · get_code("c551073449e12e26")
How it ran

no invocation recorded.

read_shot_segment_csv_file Not yet run
unverified (harvested, no recorded run)
usc-sail/mica-MovieCLIP/preprocess_scripts/preprocess_movieCLIP_json_format.py
code served (permissive licence) · get_code("c824a0c1aaa7431f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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, 3 later) and 8 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
focal_loss 3 other papers
1 dated earlier, 2 later
1901.05555 (2019-01)
Class-Balanced Loss Based on Effective Number of Samples
2302.08872 (2023-02)
Revisiting adversarial training for the worst-performing class
2310.02861 (2023-10)
Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection
linear_combination 3 other papers
2 dated earlier, 1 later
2103.15808 (2021-03)
CvT: Introducing Convolutions to Vision Transformers
2208.13196 (2022-08)
Grounded Affordance from Exocentric View
2311.03236 (2023-11)
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
reduce_loss 3 other papers
2 dated earlier, 1 later
2103.15808 (2021-03)
CvT: Introducing Convolutions to Vision Transformers
2208.13196 (2022-08)
Grounded Affordance from Exocentric View
2311.03236 (2023-11)
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources

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

Longform media such as movies have complex narrative structures, with events spanning a rich variety of ambient visual scenes. Domain specific challenges associated with visual scenes in movies include transitions, person coverage, and a wide array of real-life and fictional scenarios. Existing visual scene datasets in movies have limited taxonomies and don't consider the visual scene transition within movie clips. In this work, we address the problem of visual scene recognition in movies by first automatically curating a new and extensive movie-centric taxonomy of 179 scene labels derived from movie scripts and auxiliary web-based video datasets. Instead of manual annotations which can be expensive, we use CLIP to weakly label 1.12 million shots from 32K movie clips based on our proposed taxonomy. We provide baseline visual models trained on the weakly labeled dataset called MovieCLIP and evaluate them on an independent dataset verified by human raters. We show that leveraging features from models pretrained on MovieCLIP benefits downstream tasks such as multi-label scene and genre classification of web videos and movie trailers.

For agents

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

get_harvested_code_for_paper("2210.11065")
get_code_for_paper("2210.11065")
have("2210.11065")

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

curl https://syntology.ai/api/ran/2210.11065.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.11065.svg)](https://syntology.ai/paper/2210.11065)

Connect an agent — have() is free.