SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1609.01775 · 2016

Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking

arXiv · PDF · Open in the Atlas

Code that ran

13 of 23 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 9 have no contract verdict; 4 failures of our instrument; 10 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/1609.01775.json · badge: /api/ran/1609.01775.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
hh23333/tsd community (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
adhirajghosh/rptm_reid community (classifier label)
classifier basis not recorded on the link
6 ran · 6 no recorded run
FunctionStatusWhere it lives
L2Normalization Ran
ran on a synthesized input
adhirajghosh/rptm_reid/loss/losses.py
code served (permissive licence) · get_code("53aa000deefe4aa4")
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 (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 feature tensor with shape (batch_size=2, features=4)
ff = torch.randn(2, 4)

# Define the arguments dictionary
ARGS = {
    "ff": ff,
    "dim": 1
}
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 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
adhirajghosh/rptm_reid/model/resnet.py
code served (permissive licence) · get_code("dd1114865f06f0fd")
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 Conv2d. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
cosine_dist Ran
ran; our contract draft was wrong, not the code
hh23333/tsd/loss/triplet_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from stone96123/MDReID, is pointer only (licence: NONE) · get_code("71b4e1d375d8fd78")
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 stone96123/MDReID, 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.

cross_entropy_loss Ran
ran on a synthesized input
hh23333/tsd/loss/parsing_loss.py
code served (permissive licence) · get_code("89da1a43b987162b")
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)

# Set up tensors
batch_size = 2
num_classes = 4

# pred_class_outputs: logits tensor of shape (batch_size, num_classes)
pred_class_outputs = torch.randn(batch_size, num_classes)

# gt_classes: ground truth class indices of shape (batch_size,)
gt_classes = torch.tensor([0, 2], dtype=torch.long)

# eps: smoothing parameter (can be non-negative or negative)
eps = 0.1

# alpha: used when eps < 0 for soft label smoothing
alpha = 0.2

# weight: optional per-sample weights
weight = torch.tensor([1.0, 1.5], dtype=torch.float32)

ARGS = {
    "pred_class_outputs": pred_class_outputs,
    "gt_classes": gt_classes,
    "eps": eps,
    "alpha": alpha,
    "weight": weight,
}
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
diverse_loss Ran
ran on a synthesized input
hh23333/tsd/loss/diverse_loss.py
code served (permissive licence) · get_code("c70eb928d1b22780")
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)

# The function expects feats with shape (B, P, D)
# where B is batch size, P is number of parts, D is feature dimension
# We'll use:
# B = 2 (batch size)
# P = 3 (number of parts)
# D = 4 (feature dimension)

feats = torch.randn(2, 3, 4)

ARGS = {
    "feats": feats
}
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
diverse_loss_w Ran
ran on a synthesized input
hh23333/tsd/loss/diverse_loss.py
code served (permissive licence) · get_code("52904eaabb82770c")
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)

# Construct feats tensor: (B, P, feature_dim)
# B=2 (batch), P=5 (parts), feature_dim=4 (features)
feats = torch.randn(2, 5, 4)

# part_type can be None, 'eight', 'five', or 'three'
# Test with 'five' to match the number of parts P=5
part_type = 'five'

ARGS = {
    'feats': feats,
    'part_type': part_type,
}
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
euclidean_dist Ran
ran; our contract draft was wrong, not the code
hh23333/tsd/loss/triplet_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from stone96123/MDReID, is pointer only (licence: NONE) · get_code("5315f75bf5367f0a")
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 stone96123/MDReID, 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.

init_lr_scheduler Ran
ran on a synthesized input
adhirajghosh/rptm_reid/model/lr_schedulers.py
code served (permissive licence) · get_code("6fc6dc450dfb3503")
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 MultiStepLR. 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 torch.optim as optim

torch.manual_seed(0)

# Create a small model for the optimizer
model = nn.Linear(4, 2)

# Create an optimizer (required by init_lr_scheduler)
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Define ARGS dict with all parameters
ARGS = {
    'optimizer': optimizer,
    'lr_scheduler': 'multi_step',
    'stepsize': [20, 40],
    'gamma': 0.1
}
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 MultiStepLR — a MultiStepLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiStepLR 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
init_optimizer Ran
ran on a synthesized input
adhirajghosh/rptm_reid/model/optimizers.py
code served (permissive licence) · get_code("d7a1ddf6df1db746")
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 Adam. 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 simple model with named children for testing staged_lr
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
        self.layer3 = nn.Linear(2, 1)
    
    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return x

model = SimpleModel()

ARGS = {
    'model': model,
    'optim': 'adam',
    'lr': 0.003,
    'weight_decay': 0.0005,
    'momentum': 0.9,
    'sgd_dampening': 0,
    'sgd_nesterov': True,
    'rmsprop_alpha': 0.99,
    'adam_beta1': 0.9,
    'adam_beta2': 0.999,
    'staged_lr': False,
    'new_layers': None,
    'base_lr_mult': 0.1
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
normalize Ran
ran; our contract draft was wrong, not the code
hh23333/tsd/loss/triplet_loss.py
code served (permissive licence) · get_code("e3b2a83f52101f2d")
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 (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 batch size 2 and feature dimension 4
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "axis": -1
}
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 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
shuffle_unit Ran
ran on a synthesized input
hh23333/tsd/model/make_model.py
code served (permissive licence) · get_code("fa0d6dd791ce2927")
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 3, dtype family float, shape (2, 4, 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)

# Construct a small features tensor
# Shape: (batch_size, sequence_length, feature_dim)
# Using batch=2, sequence_length=5, feature_dim=4
features = torch.randn(2, 5, 4)

# shift parameter - used for cyclic shifting
shift = 2

# group parameter - used to reshape and transpose
group = 2

# begin parameter - starting index (default=1)
begin = 1

ARGS = {
    "features": features,
    "shift": shift,
    "group": group,
    "begin": begin
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
triplet_loss Ran
ran on a synthesized input
adhirajghosh/rptm_reid/loss/losses.py
code served (permissive licence) · get_code("1c6051bfb55a7834")
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 as nn

torch.manual_seed(0)

# The function expects:
# - features: a tensor of shape [batch_size * 3, feature_dim]
#   (anchor, positive, negative concatenated)
# - margin: a float value for MarginRankingLoss
# - batch_size: an int specifying the size of each triplet component
# - size_average: a bool (default True)

batch_size = 2
feature_dim = 4

# Create features tensor: [batch_size*3, feature_dim]
# This will be split into anchor, positive, negative
features = torch.randn(batch_size * 3, feature_dim)

margin = 1.0

ARGS = {
    "features": features,
    "margin": margin,
    "batch_size": batch_size,
    "size_average": 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 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
xent_loss Ran
ran on a synthesized input
adhirajghosh/rptm_reid/loss/losses.py
code served (permissive licence) · get_code("04762ad17d60a67b")
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 as nn

torch.manual_seed(0)

# The function expects:
# - output: a tensor that will be passed through LogSoftmax(dim=1)
# - trainY: a list/tensor of class indices for each sample
# - num_classes: an integer representing number of classes

batch_size = 2
num_classes = 4

# Create output tensor (batch_size x num_classes)
output = torch.randn(batch_size, num_classes)

# Create trainY as a list of class indices (one per sample in batch)
trainY = [0, 2]

ARGS = {
    "output": output,
    "trainY": trainY,
    "num_classes": num_classes
}
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
calculate_mask_loss Not yet run
unverified (harvested, no recorded run)
hh23333/tsd/loss/parsing_loss.py
code served (permissive licence) · get_code("5560633a659a5e4a")
How it ran

no invocation recorded.

make_bpb_jpm_loss Not yet run
unverified (harvested, no recorded run)
hh23333/tsd/loss/make_loss.py
code served (permissive licence) · get_code("1d3367aa654f6fc6")
How it ran

no invocation recorded.

make_bpb_loss Not yet run
unverified (harvested, no recorded run)
hh23333/tsd/loss/make_loss.py
code served (permissive licence) · get_code("02a7e5d591c4eda0")
How it ran

no invocation recorded.

make_loss Not yet run
unverified (harvested, no recorded run)
hh23333/tsd/loss/make_loss.py
code served (permissive licence) · get_code("098df16b204ff65f")
How it ran

no invocation recorded.

read_image Not yet run
unverified (harvested, no recorded run)
adhirajghosh/rptm_reid/datasets/data_loading.py
code served (permissive licence) · get_code("69175269b8ea0573")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
adhirajghosh/rptm_reid/model/resnet.py
code served (permissive licence) · get_code("9c78d4b83710bc10")
How it ran

no invocation recorded.

resnet50_fc512 Not yet run
unverified (harvested, no recorded run)
adhirajghosh/rptm_reid/model/resnet.py
code served (permissive licence) · get_code("6c52a307b6ae3c83")
How it ran

no invocation recorded.

se_resnet101 Not yet run
unverified (harvested, no recorded run)
adhirajghosh/rptm_reid/model/senet.py
code served (permissive licence) · get_code("2fb9c58575079d43")
How it ran

no invocation recorded.

se_resnet50 Not yet run
unverified (harvested, no recorded run)
adhirajghosh/rptm_reid/model/senet.py
code served (permissive licence) · get_code("d71b1988dd477f5f")
How it ran

no invocation recorded.

senet154 Not yet run
unverified (harvested, no recorded run)
adhirajghosh/rptm_reid/model/senet.py
code served (permissive licence) · get_code("07557401c090d0d5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 6 later) and 17 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
14 dated earlier, 672 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
normalize 29 other papers
29 later
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
1811.07130 (2018-11)
Batch DropBlock Network for Person Re-identification and Beyond
1902.09212 (2019-02)
Deep High-Resolution Representation Learning for Human Pose Estimation
and 26 more not named here
cosine_dist 15 other papers
15 later
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
2105.09701 (2021-05)
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 12 more not named here
euclidean_dist 15 other papers
15 later
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
2105.09701 (2021-05)
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 12 more not named here
shuffle_unit 3 other papers
3 later
2111.12084 (2021-11)
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
2302.14335 (2023-02)
DC-Former: Diverse and Compact Transformer for Person Re-identification
aaai_28398 (2024 (year only))
Heterogeneous Test-Time Training for Multi-Modal Person Re-identification
L2Normalization 1 other paper
1 later
2002.12186 (2020-02)
University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization

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

To help accelerate progress in multi-target, multi-camera tracking systems, we present (i) a new pair of precision-recall measures of performance that treats errors of all types uniformly and emphasizes correct identification over sources of error; (ii) the largest fully-annotated and calibrated data set to date with more than 2 million frames of 1080p, 60fps video taken by 8 cameras observing more than 2,700 identities over 85 minutes; and (iii) a reference software system as a comparison baseline. We show that (i) our measures properly account for bottom-line identity match performance in the multi-camera setting; (ii) our data set poses realistic challenges to current trackers; and (iii) the performance of our system is comparable to the state of the art.

For agents

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

get_harvested_code_for_paper("1609.01775")
get_code_for_paper("1609.01775")
have("1609.01775")

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

curl https://syntology.ai/api/ran/1609.01775.json

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

[![Syntology run record](https://syntology.ai/api/ran/1609.01775.svg)](https://syntology.ai/paper/1609.01775)

Connect an agent — have() is free.