SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.11813 · 2023

Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification

arXiv · PDF · Open in the Atlas

Code that ran

8 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; 3 failures of our instrument; 2 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/2302.11813.json · badge: /api/ran/2302.11813.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
gerardmaggiolino/deep-oc-sort canonical (classifier label)
classifier basis not recorded on the link
8 ran · 2 no recorded run
FunctionStatusWhere it lives
clip_boxes Ran
ran on a synthesized input
gerardmaggiolino/deep-oc-sort/trackers/motdt_tracker/reid_model.py
code served (permissive licence) · get_code("b5a232fabf1662a3")
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 numpy as np

# Create sample boxes in format [x1, y1, x2, y2, ...]
# Using 2 boxes with 4 coordinates each
boxes = np.array([
    [-10.5, -5.3, 150.2, 120.8],
    [30.1, 40.5, 200.9, 180.3]
], dtype=np.float32)

# Image shape as (height, width)
im_shape = (100, 200)

ARGS = {
    "boxes": boxes,
    "im_shape": im_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
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 (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
filter_targets Ran
ran on a synthesized input
gerardmaggiolino/deep-oc-sort/utils.py
code served (permissive licence) · get_code("efbd30e7a54d9bdc")
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 torch

torch.manual_seed(0)

# Construct online_targets: list of targets where each target is [x1, y1, x2, y2, id]
# We need targets that will pass and fail the filtering criteria
online_targets = [
    [10.0, 20.0, 50.0, 100.0, 1],      # Wide box, should pass
    [5.0, 10.0, 15.0, 12.0, 2],        # Very tall/vertical box, should fail (vertical)
    [30.0, 40.0, 31.0, 41.0, 3],       # Too small area, should fail
    [100.0, 150.0, 200.0, 250.0, 4],   # Large box, should pass
]

# aspect_ratio_thresh: threshold for width/height ratio to mark as vertical
aspect_ratio_thresh = 0.5

# min_box_area: minimum area for a box to be kept
min_box_area = 100.0

ARGS = {
    "online_targets": online_targets,
    "aspect_ratio_thresh": aspect_ratio_thresh,
    "min_box_area": min_box_area,
}
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 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
joint_stracks Ran
ran; our contract draft was wrong, not the code
gerardmaggiolino/deep-oc-sort/trackers/byte_tracker/byte_tracker.py
code served (permissive licence) · get_code("557de671825f7887")
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 list, 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.

import torch
import numpy as np

class Track:
    def __init__(self, track_id):
        self.track_id = track_id

torch.manual_seed(0)

track1 = Track(track_id=1)
track2 = Track(track_id=2)
track3 = Track(track_id=3)
track4 = Track(track_id=2)

tlista = [track1, track2]
tlistb = [track3, track4]

ARGS = {
    "tlista": tlista,
    "tlistb": tlistb
}
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 list, ndim 1, dtype family float — a list 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
linear_assignment Ran
ran; our contract draft was wrong, not the code
gerardmaggiolino/deep-oc-sort/trackers/byte_tracker/matching.py
code served (permissive licence) · get_code("fa0376e6b3c39f1b")
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 lap

# Create a small cost matrix for the linear assignment problem
# Shape: (4, 3) - 4 items to assign to 3 slots
cost_matrix = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0],
    [10.0, 11.0, 12.0]
], dtype=np.float64)

# Set threshold for cost limit
thresh = 15.0

ARGS = {
    "cost_matrix": cost_matrix,
    "thresh": thresh
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
lap, 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
make_layers Ran
ran on a synthesized input
gerardmaggiolino/deep-oc-sort/trackers/deepsort_tracker/reid_model.py
code served (permissive licence) · get_code("c0b3d0e6e5a858ad")
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 Sequential. 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)

ARGS = {
    "c_in": 3,
    "c_out": 64,
    "repeat_times": 2,
    "is_downsample": False
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
merge_matches Ran
ran on a synthesized input
gerardmaggiolino/deep-oc-sort/trackers/byte_tracker/matching.py
code served (permissive licence) · get_code("de19615aab6efe36")
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 scipy

# Construct valid arguments for merge_matches function
# The function takes m1, m2, and shape as parameters
# m1 and m2 are match arrays with pairs of indices
# shape is a tuple (O, P, Q) representing matrix dimensions

# Define dimensions
O = 5  # rows in first matrix
P = 4  # columns in first matrix, rows in second matrix
Q = 3  # columns in second matrix

# Create m1: matches between O and P (shape: (num_matches, 2))
# Each row is a pair (i, j) where i in [0, O) and j in [0, P)
m1 = np.array([
    [0, 0],
    [1, 1],
    [2, 2],
    [3, 3],
    [4, 1]
])

# Create m2: matches between P and Q (shape: (num_matches, 2))
# Each row is a pair (i, j) where i in [0, P) and j in [0, Q)
m2 = np.array([
    [0, 0],
    [1, 1],
    [2, 2],
    [3, 0]
])

# Define shape tuple
shape = (O, P, Q)

ARGS = {
    "m1": m1,
    "m2": m2,
    "shape": shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
preproc Ran
ran on a synthesized input
gerardmaggiolino/deep-oc-sort/dataset.py
code served (permissive licence) · get_code("e1c0bb70a54ac7db")
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 cv2
import numpy as np

# Create a small test image (4x3 RGB image)
test_image = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

# Define mean and std for normalization
mean = np.array([0.485, 0.456, 0.406])
std = np.array([0.229, 0.224, 0.225])

# Input size for preprocessing
input_size = (8, 8)

# Default swap parameter
swap = (2, 0, 1)

ARGS = {
    "image": test_image,
    "input_size": input_size,
    "mean": mean,
    "std": std,
    "swap": swap
}
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
sub_stracks Ran
ran; our contract draft was wrong, not the code
gerardmaggiolino/deep-oc-sort/trackers/byte_tracker/byte_tracker.py
code served (permissive licence) · get_code("322ac55b144012cf")
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 list, 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.

import torch
import numpy as np

class Track:
    def __init__(self, track_id):
        self.track_id = track_id

# Create two lists of tracks
tlista = [
    Track(track_id=1),
    Track(track_id=2),
    Track(track_id=3),
]

tlistb = [
    Track(track_id=2),
    Track(track_id=4),
]

ARGS = {
    'tlista': tlista,
    'tlistb': tlistb,
}
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 list, ndim 1, dtype family float — a list 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
load_net Not yet run
unverified (harvested, no recorded run)
gerardmaggiolino/deep-oc-sort/trackers/motdt_tracker/reid_model.py
code served (permissive licence) · get_code("f817f88d2e7ca234")
How it ran

no invocation recorded.

load_reid_model Not yet run
unverified (harvested, no recorded run)
gerardmaggiolino/deep-oc-sort/trackers/motdt_tracker/reid_model.py
code served (permissive licence) · get_code("8002b7c39cb1946f")
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 10 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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
joint_stracks 7 other papers
3 dated earlier, 4 later
1909.12605 (2019-09)
Towards Real-Time Multi-Object Tracking
2010.12138 (2020-10)
Rethinking the competition between detection and ReID in Multi-Object Tracking
2206.14651 (2022-06)
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
and 4 more not named here
sub_stracks 7 other papers
3 dated earlier, 4 later
1909.12605 (2019-09)
Towards Real-Time Multi-Object Tracking
2010.12138 (2020-10)
Rethinking the competition between detection and ReID in Multi-Object Tracking
2206.14651 (2022-06)
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
and 4 more not named here
linear_assignment 4 other papers
4 dated earlier
1909.12605 (2019-09)
Towards Real-Time Multi-Object Tracking
2010.12138 (2020-10)
Rethinking the competition between detection and ReID in Multi-Object Tracking
2110.06864 (2021-10)
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
and 1 more not named here
make_layers 4 other papers
4 dated earlier
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1904.07850 (2019-04)
Objects as Points
2004.10934 (2020-04)
YOLOv4: Optimal Speed and Accuracy of Object Detection
and 1 more not named here
merge_matches 4 other papers
4 dated earlier
1909.12605 (2019-09)
Towards Real-Time Multi-Object Tracking
2010.12138 (2020-10)
Rethinking the competition between detection and ReID in Multi-Object Tracking
2110.06864 (2021-10)
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
and 1 more not named here
clip_boxes 1 other paper
1 dated earlier
2110.06864 (2021-10)
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
load_net 1 other paper
1 dated earlier
2110.06864 (2021-10)
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
load_reid_model 1 other paper
1 dated earlier
2110.06864 (2021-10)
ByteTrack: Multi-Object Tracking by Associating Every Detection Box

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

Motion-based association for Multi-Object Tracking (MOT) has recently re-achieved prominence with the rise of powerful object detectors. Despite this, little work has been done to incorporate appearance cues beyond simple heuristic models that lack robustness to feature degradation. In this paper, we propose a novel way to leverage objects' appearances to adaptively integrate appearance matching into existing high-performance motion-based methods. Building upon the pure motion-based method OC-SORT, we achieve 1st place on MOT20 and 2nd place on MOT17 with 63.9 and 64.9 HOTA, respectively. We also achieve 61.3 HOTA on the challenging DanceTrack benchmark as a new state-of-the-art even compared to more heavily-designed methods. The code and models are available at \url{https://github.com/GerardMaggiolino/Deep-OC-SORT}.

For agents

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

get_harvested_code_for_paper("2302.11813")
get_code_for_paper("2302.11813")
have("2302.11813")

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

curl https://syntology.ai/api/ran/2302.11813.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.11813.svg)](https://syntology.ai/paper/2302.11813)

Connect an agent — have() is free.