SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1812.05050 · 2018

Fast Online Object Tracking and Segmentation: A Unifying Approach

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 1 failure 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/1812.05050.json · badge: /api/ran/1812.05050.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
ezelikman/anonymal community (classifier label)
classifier basis not recorded on the link
6 ran · 4 no recorded run
FunctionStatusWhere it lives
conv2d_dw_group Ran
ran on a synthesized input
ezelikman/anonymal/models/rpn.py
code served (permissive licence) · get_code("ed07034dd18cfc8f")
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 4, dtype family float, shape (2, 3, 3, 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 torch.nn.functional as F

torch.manual_seed(0)

# Construct tiny valid tensors for the function
# x: input tensor with shape (batch, channel, height, width)
# kernel: kernel tensor with shape (batch, channel, kernel_h, kernel_w)

# The function expects:
# - x to have shape (batch_size, channels, height, width)
# - kernel to have shape (batch_size, channels, kernel_height, kernel_width)

# Creating small distinct sizes to probe dimensions:
batch_size = 2
num_channels = 3
input_height = 5
input_width = 4
kernel_height = 3
kernel_width = 3

x = torch.randn(batch_size, num_channels, input_height, input_width)
kernel = torch.randn(batch_size, num_channels, kernel_height, kernel_width)

ARGS = {
    'x': x,
    'kernel': kernel
}
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 Tensor, ndim 4, dtype family float, shape (2, 3, 3, 2) — shape (2, 3, 3, 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
ezelikman/anonymal/experiments/siammask_base/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

get_cls_loss Ran
ran on a synthesized input
ezelikman/anonymal/models/siamrpn.py
code served (permissive licence) · get_code("3f1957b700e9ed16")
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 0, dtype family float, shape () 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 torch.nn.functional as F

torch.manual_seed(0)

# Create prediction tensor (batch_size=4, num_classes=3)
# F.nll_loss expects log probabilities, so we use log_softmax output
batch_size = 4
num_classes = 3
pred = F.log_softmax(torch.randn(batch_size, num_classes), dim=1)

# Create label tensor with class indices (batch_size=4)
label = torch.randint(0, num_classes, (batch_size,))

# Create select tensor with indices to select from batch
# Using a non-empty tensor so len(select.size()) > 0
select = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    "pred": pred,
    "label": label,
    "select": select
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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_cls_loss Ran
ran on a synthesized input
ezelikman/anonymal/models/siammask.py
code served (permissive licence) · get_code("ef70c620a00de25b")
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 0, dtype family float, shape () 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 torch.nn.functional as F

torch.manual_seed(0)

# Create pred tensor: log probabilities for classification
# Shape: (batch_size, num_classes)
# F.nll_loss expects log probabilities as input
pred = torch.randn(2, 4)
pred = F.log_softmax(pred, dim=1)

# Create label tensor: class indices
# Shape: (batch_size,)
label = torch.tensor([0, 2])

# Create select tensor: indices to select from pred and label
# This will select both samples (indices 0 and 1)
select = torch.tensor([0, 1])

ARGS = {
    "pred": pred,
    "label": label,
    "select": select
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
select_cross_entropy_loss Ran
ran on a synthesized input
ezelikman/anonymal/models/siammask.py
code served (permissive licence) · get_code("8c846e3850e50c54")
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 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn.functional as F
from torch.autograd import Variable

torch.manual_seed(0)

# Create pred tensor: shape (2, 2) for binary classification
# The function expects pred to be reshaped to (-1, 2) and passed to F.nll_loss
# F.nll_loss expects log probabilities, so we use log_softmax
pred_raw = torch.randn(2, 2)
pred = F.log_softmax(pred_raw, dim=1)

# Create label tensor: shape (2,) with binary labels (0 or 1)
label = torch.tensor([1, 0], dtype=torch.long)

ARGS = {
    "pred": pred,
    "label": label,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
select_cross_entropy_loss Ran
ran on a synthesized input
ezelikman/anonymal/models/siamrpn.py
code served (permissive licence) · get_code("2d85fa7671a85da4")
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 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn.functional as F
from torch.autograd import Variable

torch.manual_seed(0)

# Create pred: should be shape (batch_size, num_classes) before view
# The function views it as (-1, 2), so we need it to work with that
# Let's make it (4, 2) so after view it's still (4, 2)
pred = torch.randn(4, 2)

# Create label: should be shape (batch_size,) before view
# The function views it as (-1,), so we need it to work with that
# Let's make it (4,) with binary labels (0 or 1)
label = torch.tensor([0, 1, 0, 1], dtype=torch.long)

ARGS = {
    "pred": pred,
    "label": label,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
crop_hwc Not yet run
unverified (harvested, no recorded run)
ezelikman/anonymal/datasets/siam_mask_dataset.py
code served (permissive licence) · get_code("3be374ea8fee76b5")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
ezelikman/anonymal/experiments/siammask_sharp/resnet.py
code served (permissive licence) · get_code("02b73f913b091c75")
How it ran

no invocation recorded.

resnet34 Not yet run
unverified (harvested, no recorded run)
ezelikman/anonymal/experiments/siammask_sharp/resnet.py
code served (permissive licence) · get_code("82928ae508d22d28")
How it ran

no invocation recorded.

weight_l1_loss Not yet run
unverified (harvested, no recorded run)
ezelikman/anonymal/models/siammask.py
code served (permissive licence) · get_code("27f3175caf7f84b6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 5 the same month, 4 later) and 4 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
conv3x3 686 other papers
79 dated earlier, 6 the same month, 601 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 89 other papers
7 dated earlier, 2 the same month, 80 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
resnet34 53 other papers
7 dated earlier, 2 the same month, 44 later
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 50 more not named here
weight_l1_loss 2 other papers
1 the same month, 1 later
1812.11703 (2018-12)
SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
1911.07241 (2019-11)
SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
get_cls_loss 1 other paper
1 the same month
1812.11703 (2018-12)
SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

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

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www.robots.ox.ac.uk/~qwang/SiamMask.

For agents

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

get_harvested_code_for_paper("1812.05050")
get_code_for_paper("1812.05050")
have("1812.05050")

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

curl https://syntology.ai/api/ran/1812.05050.json

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

[![Syntology run record](https://syntology.ai/api/ran/1812.05050.svg)](https://syntology.ai/paper/1812.05050)

Connect an agent — have() is free.