SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.00482 · 2020

State-Aware Tracker for Real-Time Video Object Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

4 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 3 have no contract verdict; 1 failure of our instrument; 3 no recorded run), measured 2026-11-21; 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/2003.00482.json · badge: /api/ran/2003.00482.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
MegviiDetection/video_analyst canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
convert_numpy_to_tensor Ran
ran on a synthesized input
MegviiDetection/video_analyst/videoanalyst/utils/torch_module.py
code served (permissive licence) · get_code("6eaaca85a808b3e1")
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 2, dtype family float, shape (4, 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 collections.abc
import torch
import numpy as np

torch.manual_seed(0)

# Test case 1: numpy array
numpy_array = np.random.randn(4, 3).astype(np.float32)

# Test case 2: dict with image (HxWxC format)
dict_with_image = {
    'image': np.random.randn(5, 6, 3).astype(np.float32),
    'label': np.array([1, 2]).astype(np.float32),
    'metadata': 'some_string'
}

# Test case 3: list of numpy arrays
list_of_arrays = [
    np.random.randn(2, 4).astype(np.float32),
    np.random.randn(3, 2).astype(np.float32)
]

# Test case 4: nested structure with dict containing list
nested_dict = {
    'data': [np.random.randn(2, 3).astype(np.float32)],
    'values': np.array([5.0, 6.0]).astype(np.float32)
}

# Test case 5: plain Python object (non-numpy, non-dict, non-sequence)
plain_object = 42

ARGS = {
    'raw_data': numpy_array
}
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 Tensor, ndim 2, dtype family float, shape (4, 3) — shape (4, 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
move_data_to_device Ran
ran on a synthesized input
MegviiDetection/video_analyst/videoanalyst/utils/torch_module.py
code served (permissive licence) · get_code("d06d2a6e7019c137")
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 dict. 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

torch.manual_seed(0)

# Construct a dictionary with tensor values
data_dict = {
    "tensor_1": torch.randn(2, 4),
    "tensor_2": torch.randn(2, 3),
    "tensor_3": torch.randn(2, 5),
}

# Define the device (CPU only)
device = torch.device("cpu")

# Map all parameters to their values
ARGS = {
    "data_dict": data_dict,
    "dev": device,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
specify_task Ran
ran on a synthesized input
MegviiDetection/video_analyst/videoanalyst/config/config.py
code served (permissive licence) · get_code("df5b6d48d5678fc1")
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.

from yacs.config import CfgNode

cfg = CfgNode()

# Initialize the config with task structures
cfg['track'] = CfgNode()
cfg['track']['exp_name'] = 'unknown'

cfg['vos'] = CfgNode()
cfg['vos']['exp_name'] = 'unknown'

# Set one task to have a non-default exp_name so the function returns successfully
cfg['track']['exp_name'] = 'tracking_experiment'

ARGS = {
    'cfg': cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yacs — 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
to_numpy Ran
ran; our contract draft was wrong, not the code
MegviiDetection/video_analyst/main/cvt_trt.py
code served (permissive licence) · get_code("9d103c391b8dbe33")
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 2, dtype family float, shape (2, 4) 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 small tensor with requires_grad=True to test the gradient case
tensor_with_grad = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "tensor": tensor_with_grad
}
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 ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
build Not yet run
unverified (harvested, no recorded run)
MegviiDetection/video_analyst/videoanalyst/model/builder.py
code served (permissive licence) · get_code("e127c82cc613f1d9")
How it ran

no invocation recorded.

get_config Not yet run
unverified (harvested, no recorded run)
MegviiDetection/video_analyst/videoanalyst/model/builder.py
code served (permissive licence) · get_code("fa51e84d318a9b7d")
How it ran

no invocation recorded.

unwrap_model Not yet run
unverified (harvested, no recorded run)
MegviiDetection/video_analyst/videoanalyst/utils/torch_module.py
code served (permissive licence) · get_code("99a642ee770823da")
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, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
to_numpy 2 other papers
1 dated earlier, 1 later
2002.06604 (2020-02)
Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
2308.06904 (2023-08)
Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual Tracking
convert_numpy_to_tensor 1 other paper
1 later
Zhang_Spiking_Transformers_for_Event-Based_Single_Object_Tracking_CVPR_2022_paper (2022 (year only))
Spiking Transformers for Event-based Single Object Tracking
specify_task 1 other paper
1 later
Zhang_Spiking_Transformers_for_Event-Based_Single_Object_Tracking_CVPR_2022_paper (2022 (year only))
Spiking Transformers for Event-based Single Object Tracking
unwrap_model 1 other paper
1 later
Zhang_Spiking_Transformers_for_Event-Based_Single_Object_Tracking_CVPR_2022_paper (2022 (year only))
Spiking Transformers for Event-based Single Object Tracking

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we address the task of semi-supervised video object segmentation(VOS) and explore how to make efficient use of video property to tackle the challenge of semi-supervision. We propose a novel pipeline called State-Aware Tracker(SAT), which can produce accurate segmentation results with real-time speed. For higher efficiency, SAT takes advantage of the inter-frame consistency and deals with each target object as a tracklet. For more stable and robust performance over video sequences, SAT gets awareness for each state and makes self-adaptation via two feedback loops. One loop assists SAT in generating more stable tracklets. The other loop helps to construct a more robust and holistic target representation. SAT achieves a promising result of 72.3% J&F mean with 39 FPS on DAVIS2017-Val dataset, which shows a decent trade-off between efficiency and accuracy. Code will be released at github.com/MegviiDetection/video_analyst.

For agents

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

get_harvested_code_for_paper("2003.00482")
get_code_for_paper("2003.00482")
have("2003.00482")

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

curl https://syntology.ai/api/ran/2003.00482.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.00482.svg)](https://syntology.ai/paper/2003.00482)

Connect an agent — have() is free.