SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.06029 · ICCV · 2021

Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking

Jenq-Neng Hwang, Mingli Song, Zuozhu Liu, Gaoang Wang, Renshu Gu, Weijie Hu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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 0 have no contract verdict; 2 failures of our instrument; 1 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/2108.06029.json · badge: /api/ran/2108.06029.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
GaoangW/LGMTracker community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
get_triplet_loss Ran
ran; our contract draft was wrong, not the code
GaoangW/LGMTracker/head_gnn.py
code served (permissive licence) · get_code("6a1703b22eab11a7")
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 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

torch.manual_seed(0)

# Create small feature tensor: batch_size=2, feature_dim=4
features = torch.randn(2, 4)

# Create labels tensor: batch_size=2
# Use different labels so we have positive and negative pairs
labels = torch.tensor([0, 1])

# Margin parameter
margin = 0.2

ARGS = {
    "features": features,
    "labels": labels,
    "margin": margin,
}
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 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
hard_example_mining Ran
ran; our contract draft was wrong, not the code
GaoangW/LGMTracker/head_gnn.py
code served (permissive licence) · get_code("c9c869553776bd12")
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 tuple, ndim 2, 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

torch.manual_seed(0)

# Create a small distance matrix (4x4)
# This represents pairwise distances between 4 samples
dist_mat = torch.tensor([
    [0.0, 1.5, 2.3, 3.1],
    [1.5, 0.0, 2.8, 3.5],
    [2.3, 2.8, 0.0, 1.2],
    [3.1, 3.5, 1.2, 0.0]
], dtype=torch.float32)

# Create labels for the 4 samples
# Labels indicate which class each sample belongs to
# Using 2 classes: samples 0,1 in class 0 and samples 2,3 in class 1
labels = torch.tensor([0, 0, 1, 1], dtype=torch.long)

ARGS = {
    "dist_mat": dist_mat,
    "labels": labels,
    "return_inds": False
}
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 tuple, ndim 2, dtype family float — a tuple 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
BoxEmb Not yet run
unverified (harvested, no recorded run)
GaoangW/LGMTracker/head_gnn.py
code served (permissive licence) · get_code("954685667afebf0a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motionbased trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging appearance information to assist object re-identification could resolve this challenge to some extent. However, doing so requires extra computation while appearance information is sensitive to occlusion as well. In this paper, we try to explore the significance of motion patterns for vehicle tracking without appearance information. We propose a novel approach that tackles the association issue for long-term tracking with the exclusive fully-exploited motion information. We address the tracklet embedding issue with the proposed reconstruct-to-embed strategy based on deep graph convolutional neural networks (GCN). Comprehensive experiments on the KITTIcar tracking dataset and UA-Detrac dataset show that the proposed method, though without appearance information, could achieve competitive performance with the state-ofthe-art (SOTA) trackers. The source code will be available at https://github.com/GaoangW/LGMTracker.

For agents

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

get_harvested_code_for_paper("2108.06029")
get_code_for_paper("2108.06029")
have("2108.06029")

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

curl https://syntology.ai/api/ran/2108.06029.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.06029.svg)](https://syntology.ai/paper/2108.06029)

Connect an agent — have() is free.