SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.02156 · NeurIPS · 2021

Do Different Tracking Tasks Require Different Appearance Models?

Philip Torr, Luca Bertinetto, Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 2 failures of our instrument; 11 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/2107.02156.json · badge: /api/ran/2107.02156.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
Zhongdao/UniTrack canonical (classifier label)
classifier basis: classifier_2025
6 ran · 11 no recorded run
FunctionStatusWhere it lives
From3D Ran
ran on a synthesized input · constructed an object; no result was computed
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("6bed795c8790b42f")
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 an instance of its own class, From3D: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Create a small 2D ResNet-like model that the From3D wrapper will use
class SimpleResNet(nn.Module):
    def __init__(self):
        super(SimpleResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 8, kernel_size=3, padding=1)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(8, 16, kernel_size=3, padding=1)
    
    def forward(self, x):
        # x shape: (N, C, h, w)
        x = self.conv1(x)
        x = self.relu(x)
        x = self.conv2(x)
        return x

# Create the 2D model
resnet_model = SimpleResNet()

ARGS = {
    "resnet": resnet_model
}
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 From3D — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a From3D 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
HighResolutionModule Ran
ran on a synthesized input · constructed an object; no result was computed
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("6cb64253bc2483ab")
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 an instance of its own class, HighResolutionModule: the run constructed the object and did not call it, so no result was computed. 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
import logging

torch.manual_seed(0)
logging.basicConfig(level=logging.ERROR)

# Define a simple residual block that the function expects
class SimpleBlock(nn.Module):
    expansion = 1
    
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(SimpleBlock, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes, momentum=0.1)
        self.relu = nn.ReLU(inplace=False)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes, momentum=0.1)
        self.downsample = downsample
        self.stride = stride
    
    def forward(self, x):
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out

ARGS = {
    'num_branches': 2,
    'blocks': SimpleBlock,
    'num_blocks': [2, 2],
    'num_inchannels': [4, 8],
    'num_channels': [4, 8],
    'fuse_method': 'sum',
    'multi_scale_output': True
}
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 HighResolutionModule — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a HighResolutionModule 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
RandomFeatGenerator Ran
ran on a synthesized input · constructed an object; no result was computed
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("24f302b7add67f84")
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 an instance of its own class, RandomFeatGenerator: the run constructed the object and did not call it, so no result was computed. 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 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

torch.manual_seed(0)

class Args:
    def __init__(self, down_factor, dim):
        self.down_factor = down_factor
        self.dim = dim

ARGS = {
    'args': Args(down_factor=2, dim=4)
}
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 RandomFeatGenerator — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RandomFeatGenerator 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
ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("5fb6217486f7e99c")
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 an instance of its own class, ResNet: the run constructed the object and did not call it, so no result was computed. 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
import torchvision.models.resnet as torch_resnet

torch.manual_seed(0)

# Create a minimal ResNet instance
# ResNet requires: block, layers, num_classes, and other optional args
# block: BasicBlock or Bottleneck class
# layers: list of layer repetitions [2, 2, 2, 2] for ResNet18

block = torch_resnet.BasicBlock
layers = [2, 2, 2, 2]
num_classes = 10

resnet_instance = torch_resnet.ResNet(
    block=block,
    layers=layers,
    num_classes=num_classes
)

ARGS = {
    'block': block,
    'layers': layers,
    'num_classes': num_classes,
    'zero_init_residual': False,
    'groups': 1,
    'width_per_group': 64,
    'replace_stride_with_dilation': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ResNet 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
_resnet Ran
ran; our contract draft was wrong, not the code
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("8a5d9f9460c91bb5")
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 ResNet. 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 torchvision.models.resnet import BasicBlock

torch.manual_seed(0)

# Create a minimal block class that satisfies ResNet requirements
block = BasicBlock

# Define layers configuration (e.g., for ResNet18: [2, 2, 2, 2])
layers = [2, 2, 2, 2]

# Set pretrained to False to avoid network calls
pretrained = False

# Set progress to False
progress = False

# Additional kwargs for ResNet initialization
kwargs = {
    'num_classes': 10
}

ARGS = {
    'arch': 'resnet18',
    'block': block,
    'layers': layers,
    'pretrained': pretrained,
    'progress': progress,
    'num_classes': 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
dets2obs Ran
ran; our contract draft was wrong, not the code
Zhongdao/UniTrack/demo/mot_demo.py
code served (permissive licence) · get_code("93ff6b09d3e38b8e")
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 ndarray, ndim 2, dtype family float, shape (2, 6) 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)

# dets: a tensor with shape (num_detections, 7)
# The function accesses columns 0,1,2,3,4,5,6
# It calls .cpu().numpy() on it
dets = torch.tensor([
    [10.0, 20.0, 50.0, 80.0, 0.9, 0.8, 1],
    [15.0, 25.0, 60.0, 90.0, 0.85, 0.75, 2]
], dtype=torch.float32)

# imginfo: a dict with 'height' and 'width' keys
imginfo = {
    'height': 480,
    'width': 640
}

# cls: a list/set of class indices to filter by
cls = [1, 2]

ARGS = {
    'dets': dets,
    'imginfo': imginfo,
    'cls': cls
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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, 6) — shape (2, 6) 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
HighResolutionNet Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("fe69a6b9983c5ce3")
How it ran

no invocation recorded.

get_cls_net Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("ec2a972e12e2c2f6")
How it ran

no invocation recorded.

load_tc_model Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("bb753455f7400311")
How it ran

no invocation recorded.

load_uvc_model Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("407da3ab43d8ba3f")
How it ran

no invocation recorded.

make_encoder Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("d3b2fda956486d2c")
How it ran

no invocation recorded.

partial_load Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("c0367497ab1f7faa")
How it ran

no invocation recorded.

resnet101 Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("33b995998b62c580")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("08e568179967e865")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("92b061ec78263602")
How it ran

no invocation recorded.

resnext101_32x8d Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("bf216e79a1ef8b76")
How it ran

no invocation recorded.

resnext50_32x4d Not yet run
unverified (harvested, no recorded run)
Zhongdao/UniTrack/model/model.py
code served (permissive licence) · get_code("8cc2e400c38e8730")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 later) and 12 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
resnet18
brick of this paper's assembly: helper
95 other papers
27 dated earlier, 65 later, 2 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
_resnet
brick of this paper's assembly: helper
8 other papers
2 dated earlier, 6 later
2103.10211 (2021-03)
Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning
2105.03245 (2021-05)
Adaptive Focus for Efficient Video Recognition
2204.04662 (2022-04)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
and 5 more not named here
resnet101
brick of this paper's assembly: helper
1 other paper
1 later
2208.06974 (2022-08)
Learning Semantic Correspondence with Sparse Annotations
resnet50
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2006.14613 (2020-06)
Space-Time Correspondence as a Contrastive Random Walk
resnext50_32x4d
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2008.04115 (2020-08)
T-GD: Transferable GAN-generated Images Detection Framework

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

Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of different experimental setups. As a consequence, the literature has fragmented too, and now novel approaches proposed by the community are usually specialised to fit only one specific setup. To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. UniTrack consists of a single and task-agnostic appearance model, which can be learned in a supervised or self-supervised fashion, and multiple "heads" that address individual tasks and do not require training. We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered. The framework also allows us to analyse appearance models obtained with the most recent self-supervised methods, thus extending their evaluation and comparison to a larger variety of important problems.

For agents

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

get_harvested_code_for_paper("2107.02156")
get_code_for_paper("2107.02156")
have("2107.02156")

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

curl https://syntology.ai/api/ran/2107.02156.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.02156.svg)](https://syntology.ai/paper/2107.02156)

Connect an agent — have() is free.