SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.04427 · 2018

Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 failures of our instrument; 0 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/1809.04427.json · badge: /api/ran/1809.04427.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
longcw/MOTDT canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
youngbin-ro/Homography-based-MOTDT community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Homography Ran
ran on a synthesized input
youngbin-ro/Homography-based-MOTDT/utils/homography.py
code served (permissive licence) · get_code("72cacccc507d3508")
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 (3, 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 cv2
import numpy as np

# Create two small grayscale images for the function to work with
# ORB detector works on grayscale images
prev_img = np.random.randint(0, 256, (100, 100), dtype=np.uint8)
img = np.random.randint(0, 256, (100, 100), dtype=np.uint8)

# Add some features to ensure detectAndCompute finds keypoints and descriptors
# by adding some corners/edges
prev_img[20:30, 20:30] = 255
prev_img[70:80, 70:80] = 0
img[25:35, 25:35] = 255
img[65:75, 65:75] = 0

ARGS = {
    "img": img,
    "prev_img": prev_img,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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 (3, 3) — shape (3, 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
collate_fn Ran
ran on a synthesized input
longcw/MOTDT/datasets/mot_seq.py
code served (permissive licence) · get_code("3f794ea9524065ef")
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
import torch.utils.data as data

torch.manual_seed(0)

# The collate_fn function takes a 'data' parameter
# and returns data[0], which suggests it expects a list/batch
# where the first element is extracted and returned.
# This is typically used with a DataLoader that passes batches to collate_fn.

# Create sample data - a list containing one element
# (since collate_fn returns data[0])
sample_batch = [
    torch.randn(2, 4)  # Small tensor: batch size 2, dim 4
]

ARGS = {
    "data": sample_batch
}
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
crop_with_factor Ran
ran on a synthesized input
longcw/MOTDT/models/classification/classifier.py
code served (permissive licence) · get_code("95b19bc736eb6c2f")
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. 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 numpy as np
import cv2

# Create a small test image (4 rows, 6 columns, 3 channels for RGB)
test_image = np.random.randint(0, 256, size=(4, 6, 3), dtype=np.uint8)

ARGS = {
    'im': test_image,
    'dest_size': 100,
    'factor': 32,
    'pad_val': 0,
    'basedon': 'min'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
find_in_path Ran
ran on a synthesized input
longcw/MOTDT/bbox_setup.py
code served (permissive licence) · get_code("ca14946efd571693")
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 str. 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 os
from os.path import join as pjoin
import tempfile

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
search_dir_1 = pjoin(temp_dir, "dir1")
search_dir_2 = pjoin(temp_dir, "dir2")
os.makedirs(search_dir_1, exist_ok=True)
os.makedirs(search_dir_2, exist_ok=True)

# Create a test file in search_dir_1
test_file_name = "test_executable"
test_file_path = pjoin(search_dir_1, test_file_name)
with open(test_file_path, "w") as f:
    f.write("#!/bin/bash\necho test\n")

# Construct the search path
search_path = search_dir_1 + os.pathsep + search_dir_2

ARGS = {
    "name": "test_executable",
    "path": search_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
is_cuda Ran
ran on a synthesized input
longcw/MOTDT/models/net_utils.py
code served (permissive licence) · get_code("53812af9be145776")
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 bool, 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

ARGS = {
    "model": 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 bool, 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
set_optimizer_state_devices Ran
ran on a synthesized input
longcw/MOTDT/models/net_utils.py
code served (permissive licence) · get_code("7916e660fab536d3")
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. 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)

# Construct a minimal optimizer state dict
# The function iterates over state.items() and then v.keys()
# It checks if v[k2] has 'cuda' attribute (tensors do)
# and calls .cpu() or .cuda(device_id) on them

# Create some dummy tensors that will be in optimizer state
param_tensor_1 = torch.randn(2, 4)
param_tensor_2 = torch.randn(3, 5)
momentum_buffer_1 = torch.randn(2, 4)
momentum_buffer_2 = torch.randn(3, 5)

# Simulate optimizer state structure
# Typical state format: {param_id: {'momentum_buffer': tensor, ...}, ...}
state = {
    0: {
        'momentum_buffer': momentum_buffer_1,
        'step': torch.tensor(1),
    },
    1: {
        'momentum_buffer': momentum_buffer_2,
        'step': torch.tensor(2),
    }
}

ARGS = {
    'state': state,
    'device_id': None,
}
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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 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
find_in_path 2 other papers
1 dated earlier, 1 later
1609.03605 (2016-09)
Detecting Text in Natural Image with Connectionist Text Proposal Network
1908.11542 (2019-08)
Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement

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

Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks can handle noisy detection caused by occlusion. In order to apply optimal selection from a considerable amount of candidates in real-time, we present a novel scoring function based on a fully convolutional neural network, that shares most computations on the entire image. Moreover, we adopt a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of our tracker. Extensive experiments show that our tracker achieves real-time and state-of-the-art performance on a widely used people tracking benchmark.

For agents

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

get_harvested_code_for_paper("1809.04427")
get_code_for_paper("1809.04427")
have("1809.04427")

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

curl https://syntology.ai/api/ran/1809.04427.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.04427.svg)](https://syntology.ai/paper/1809.04427)

Connect an agent — have() is free.