SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.10247 · 2020

Learning Joint Spatial-Temporal Transformations for Video Inpainting

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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 1 has no contract verdict; 2 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/2007.10247.json · badge: /api/ran/2007.10247.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
researchmm/STTN canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
get_ref_index Ran
ran on a synthesized input
researchmm/STTN/core/dataset.py
code served (permissive licence) · get_code("460140ea6a070542")
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 random

random.seed(0)

ARGS = {
    "length": 10,
    "sample_length": 3
}
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 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
random_accelerate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
researchmm/STTN/core/utils.py
code served (permissive licence) · get_code("d98f6e80e969ffbd")
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 numpy as np
import torch

np.random.seed(0)

# Analyzing the function:
# - velocity: tuple of (speed, angle) - used as "speed, angle = velocity"
# - maxAcceleration: tuple of (d_speed, d_angle) - used as "d_speed, d_angle = maxAcceleration"
# - dist: string parameter with default 'uniform', can be 'uniform', 'guassian', or other

velocity = (5.0, 0.785)  # (speed in m/s, angle in radians)
maxAcceleration = (2.0, 0.1)  # (max speed change, max angle change)
dist_type = 'uniform'

ARGS = {
    'velocity': velocity,
    'maxAcceleration': maxAcceleration,
    'dist': dist_type
}
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 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
spectral_norm Ran
ran; our contract draft was wrong, not the code
researchmm/STTN/core/spectral_norm.py
code served (permissive licence) · get_code("2fbfa7555a2ca4af")
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 SimpleModule. 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
from torch.nn.functional import normalize

torch.manual_seed(0)

# Create a simple linear module to apply spectral norm to
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        # Create a weight parameter with distinct dimensions (4x3)
        self.weight = nn.Parameter(torch.randn(4, 3))
    
    def forward(self, x):
        return torch.matmul(x, self.weight.t())

module = SimpleModule()

ARGS = {
    'module': module,
    'name': 'weight',
    'n_power_iterations': 1,
    'eps': 1e-12,
    'dim': None
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
create_random_shape_with_random_motion Not yet run
unverified (harvested, no recorded run)
researchmm/STTN/core/utils.py
code served (permissive licence) · get_code("30f35d199c193fbe")
How it ran

no invocation recorded.

get_random_shape Not yet run
unverified (harvested, no recorded run)
researchmm/STTN/core/utils.py
code served (permissive licence) · get_code("6377912546960040")
How it ran

no invocation recorded.

remove_spectral_norm Not yet run
unverified (harvested, no recorded run)
researchmm/STTN/core/spectral_norm.py
code served (permissive licence) · get_code("5db67c73b56c8cd0")
How it ran

no invocation recorded.

use_spectral_norm Not yet run
unverified (harvested, no recorded run)
researchmm/STTN/core/spectral_norm.py
code served (permissive licence) · get_code("b674053606e02d7e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 5 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
remove_spectral_norm 6 other papers
2 dated earlier, 4 later
1911.07532 (2019-11)
Graph Neural Ordinary Differential Equations
2003.00378 (2020-03)
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
2106.08748 (2021-06)
Input Invex Neural Network
and 3 more not named here
spectral_norm 6 other papers
3 dated earlier, 3 later
1911.13239 (2019-11)
DoveNet: Deep Image Harmonization via Domain Verification
2001.02332 (2020-01)
Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
2003.00378 (2020-03)
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
and 3 more not named here
random_accelerate 2 other papers
2 later
2402.17726 (2024-02)
VRP-SAM: SAM with Visual Reference Prompt
2404.05580 (2024-04)
Responsible Visual Editing
create_random_shape_with_random_motion 1 other paper
1 later
2309.13890 (2023-09)
Bitstream-corrupted Video Recovery: A Novel Benchmark Dataset and Method
get_random_shape 1 other paper
1 later
2309.13890 (2023-09)
Bitstream-corrupted Video Recovery: A Novel Benchmark Dataset and Method

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

High-quality video inpainting that completes missing regions in video frames is a promising yet challenging task. State-of-the-art approaches adopt attention models to complete a frame by searching missing contents from reference frames, and further complete whole videos frame by frame. However, these approaches can suffer from inconsistent attention results along spatial and temporal dimensions, which often leads to blurriness and temporal artifacts in videos. In this paper, we propose to learn a joint Spatial-Temporal Transformer Network (STTN) for video inpainting. Specifically, we simultaneously fill missing regions in all input frames by self-attention, and propose to optimize STTN by a spatial-temporal adversarial loss. To show the superiority of the proposed model, we conduct both quantitative and qualitative evaluations by using standard stationary masks and more realistic moving object masks. Demo videos are available at https://github.com/researchmm/STTN.

For agents

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

get_harvested_code_for_paper("2007.10247")
get_code_for_paper("2007.10247")
have("2007.10247")

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

curl https://syntology.ai/api/ran/2007.10247.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.10247.svg)](https://syntology.ai/paper/2007.10247)

Connect an agent — have() is free.