SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.11110 · ICLR · 2024

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

Haonan Yu, Wei Xu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2401.11110.json · badge: /api/ran/2401.11110.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
hnyu/vonet canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_ari Ran
ran; our contract draft was wrong, not the code
hnyu/vonet/vonet/vonet_agent.py
code served (permissive licence) · get_code("f5910e56e5b7adb3")
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) and returned Tensor, 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

torch.manual_seed(0)

# Create small tensors for the function
batch_size = 2
time_steps = 3
height = 4
width = 5
num_groups = 6

# seg: segmentation predictions, shape [B, T, H, W] with values in range [0, num_groups)
seg = torch.randint(0, num_groups, (batch_size, time_steps, height, width))

# gt_seg: ground truth segmentation, shape [B, T, H, W] with values that may exceed num_groups
gt_seg = torch.randint(0, num_groups + 2, (batch_size, time_steps, height, width))

# temporal_padding: mask of shape [B, T] indicating valid timesteps (1 = valid, 0 = padding)
temporal_padding = torch.ones((batch_size, time_steps), dtype=torch.float32)
# Mark some timesteps as padding
temporal_padding[0, 2] = 0
temporal_padding[1, 1] = 0

ARGS = {
    "seg": seg,
    "gt_seg": gt_seg,
    "num_groups": num_groups,
    "temporal_padding": temporal_padding,
    "ignore_background": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
compute_mIoU Ran
ran; our contract draft was wrong, not the code
hnyu/vonet/vonet/vonet_agent.py
code served (permissive licence) · get_code("dc4fb5a2910278ef")
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) and returned Tensor, 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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# seg: predicted segmentation (B, T, H, W)
# gt_seg: ground truth segmentation (B, T, H, W)
# temporal_padding: (B, T) mask indicating valid timesteps

B = 2  # batch size
T = 3  # temporal dimension
H = 4  # height
W = 5  # width

# Create ground truth segmentation with small integer IDs
gt_seg = torch.randint(0, 3, (B, T, H, W), dtype=torch.int64)

# Create predicted segmentation with small integer IDs
seg = torch.randint(0, 4, (B, T, H, W), dtype=torch.int64)

# Create temporal padding mask (B, T) - all ones means all timesteps are valid
temporal_padding = torch.ones((B, T), dtype=torch.float32)

ARGS = {
    "seg": seg,
    "gt_seg": gt_seg,
    "temporal_padding": temporal_padding,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
get_segmentation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hnyu/vonet/vonet/vonet_agent.py
code served (permissive licence) · get_code("65ad0ce069276942")
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) and returned Tensor, ndim 1, dtype family int, 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

torch.manual_seed(0)

# Create a mask tensor with shape (batch_size, num_classes, 1)
# The function expects:
# - squeeze(2) to remove the last dimension
# - argmax along dim=1 (class dimension)
# - gather along dim=1
# So we need shape (batch=2, num_classes=4, 1)
mask = torch.randn(2, 4, 1)

# Threshold for probability filtering
threshold = 0.5

ARGS = {
    "mask": mask,
    "threshold": threshold,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

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

Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation. We present VONet, an innovative approach that is inspired by MONet. While utilizing a U-Net architecture, VONet employs an efficient and effective parallel attention inference process, generating attention masks for all slots simultaneously. Additionally, to enhance the temporal consistency of each mask across consecutive video frames, VONet develops an object-wise sequential VAE framework. The integration of these innovative encoder-side techniques, in conjunction with an expressive transformer-based decoder, establishes VONet as the leading unsupervised method for object learning across five MOVI datasets, encompassing videos of diverse complexities. Code is available at https://github.com/hnyu/vonet.

For agents

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

get_harvested_code_for_paper("2401.11110")
get_code_for_paper("2401.11110")
have("2401.11110")

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

curl https://syntology.ai/api/ran/2401.11110.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.11110.svg)](https://syntology.ai/paper/2401.11110)

Connect an agent — have() is free.