SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.05425 · 2020

UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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 5 have no contract verdict; 0 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/2001.05425.json · badge: /api/ran/2001.05425.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
idilesenzulfikar/UNOVOST community (classifier label)
classifier basis not recorded on the link
5 ran · 4 no recorded run
FunctionStatusWhere it lives
calculate_merge_score Ran
ran on a synthesized input
idilesenzulfikar/UNOVOST/tracker/merge_tracklets.py
code served (permissive licence) · get_code("a085d818ca7c1b3a")
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 numpy as np
from numpy import array as arr

# Create tracklet with avg_reid_score and start time
tracklet = {
    'avg_reid_score': arr([0.1, 0.2, 0.3, 0.4]),
    'start': 5
}

# Create merge_props list with multiple proposals
merge_props = [
    {
        'avg_reid_score': arr([0.15, 0.25, 0.35, 0.45]),
        'end': 4
    },
    {
        'avg_reid_score': arr([0.05, 0.15, 0.25, 0.35]),
        'end': 3
    },
    {
        'avg_reid_score': arr([0.12, 0.22, 0.32, 0.42]),
        'end': 6
    }
]

# Calculate norm_distance as a reference distance metric
norm_distance = 0.5

# Set time_weighting flag
time_weighting = False

# Set alpha parameter for time-weighted scoring
alpha = 0.6

ARGS = {
    'tracklet': tracklet,
    'merge_props': merge_props,
    'norm_distance': norm_distance,
    'time_weighting': time_weighting,
    'alpha': alpha
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
match_hungarian Ran
ran on a synthesized input
idilesenzulfikar/UNOVOST/tracker/generate_tracklets.py
code served (permissive licence) · get_code("8ae81d74fadcf1e4")
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 2, 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 numpy as np
from scipy.optimize import linear_sum_assignment

# Create a small distance matrix for the hungarian algorithm
# Using a 4x3 matrix to have distinct dimensions
dist_matrix = np.array([
    [0.1, 0.5, 0.9],
    [0.2, 0.3, 0.7],
    [0.8, 0.1, 0.4],
    [0.6, 0.2, 0.5]
], dtype=np.float32)

# Set threshold to filter matches
thresh = 0.5

ARGS = {
    "dist_matrix": dist_matrix,
    "thresh": thresh
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — 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
max_ind_threshold Ran
ran on a synthesized input
idilesenzulfikar/UNOVOST/tracker/generate_tracklets.py
code served (permissive licence) · get_code("b69cc9f81bfafb2a")
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 2, 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 numpy as np

# Create a small matrix with some values
# The function will find max values and set rows/cols to -1
mat = np.array([
    [0.9, 0.5, 0.3, 0.2],
    [0.4, 0.8, 0.6, 0.1],
    [0.7, 0.2, 0.9, 0.4]
], dtype=np.float32)

num_track = 2
threshold = 0.5

ARGS = {
    "mat": mat,
    "num_track": num_track,
    "threshold": threshold
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — 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
normalization_distance Ran
ran on a synthesized input
idilesenzulfikar/UNOVOST/tracker/merge_tracklets.py
code served (permissive licence) · get_code("9e989e00c2494f1a")
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 float64, ndim 0, 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

torch_manual_seed = 0

tracklets_info = [
    {
        'avg_reid_score': np.array([0.1, 0.2, 0.3, 0.4])
    },
    {
        'avg_reid_score': np.array([0.5, 0.6, 0.7, 0.8])
    },
    {
        'avg_reid_score': np.array([0.9, 1.0, 1.1, 1.2])
    }
]

ARGS = {
    'tracklets_info': tracklets_info
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
refine_cluster Ran
ran on a synthesized input
idilesenzulfikar/UNOVOST/tracker/merge_tracklets.py
code served (permissive licence) · get_code("b0d98c6932105c96")
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. 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 numpy as np

torch.manual_seed(0)

# Build arguments for refine_cluster(clustered_seqs, sequence)
# 
# The function iterates through clustered_seqs (list of lists)
# and for each c_seq, iterates through sequence (list of token IDs)
# checking membership and removing elements.

# clustered_seqs: list of lists, where each inner list contains token IDs
clustered_seqs = [
    [1, 2, 3, 4],
    [5, 6, 7],
    [8, 9, 10, 11]
]

# sequence: list of token IDs to check and remove from each cluster
sequence = [1, 2, 5]

ARGS = {
    "clustered_seqs": clustered_seqs,
    "sequence": sequence
}
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 list — a list 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
draw_mask Not yet run
unverified (harvested, no recorded run)
idilesenzulfikar/UNOVOST/visualize.py
code served (permissive licence) · get_code("bf4aa6c559a825c2")
How it ran

no invocation recorded.

extract_features Not yet run
unverified (harvested, no recorded run)
idilesenzulfikar/UNOVOST/tracker/alternative_ReID.py
code served (permissive licence) · get_code("8d09082fc09dda26")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
idilesenzulfikar/UNOVOST/tracker/alternative_ReID.py
code served (permissive licence) · get_code("d47d076b8637e969")
How it ran

no invocation recorded.

resolve_tracklet_props Not yet run
unverified (harvested, no recorded run)
idilesenzulfikar/UNOVOST/tracker/generate_tracklets.py
code served (permissive licence) · get_code("a0f60e614c942408")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 address Unsupervised Video Object Segmentation (UVOS), the task of automatically generating accurate pixel masks for salient objects in a video sequence and of tracking these objects consistently through time, without any input about which objects should be tracked. Towards solving this task, we present UnOVOST (Unsupervised Offline Video Object Segmentation and Tracking) as a simple and generic algorithm which is able to track and segment a large variety of objects. This algorithm builds up tracks in a number stages, first grouping segments into short tracklets that are spatio-temporally consistent, before merging these tracklets into long-term consistent object tracks based on their visual similarity. In order to achieve this we introduce a novel tracklet-based Forest Path Cutting data association algorithm which builds up a decision forest of track hypotheses before cutting this forest into paths that form long-term consistent object tracks. When evaluating our approach on the DAVIS 2017 Unsupervised dataset we obtain state-of-the-art performance with a mean J &F score of 67.9% on the val, 58% on the test-dev and 56.4% on the test-challenge benchmarks, obtaining first place in the DAVIS 2019 Unsupervised Video Object Segmentation Challenge. UnOVOST even performs competitively with many semi-supervised video object segmentation algorithms even though it is not given any input as to which objects should be tracked and segmented.

For agents

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

get_harvested_code_for_paper("2001.05425")
get_code_for_paper("2001.05425")
have("2001.05425")

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

curl https://syntology.ai/api/ran/2001.05425.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.05425.svg)](https://syntology.ai/paper/2001.05425)

Connect an agent — have() is free.