SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.07889 · CVPR · 2021

Learning a Proposal Classifier for Multiple Object Tracking

Changshui Zhang, Peng Dai, Wei Ding, Renliang Weng, Wongun Choi, Zhangping He

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2103.07889.json · badge: /api/ran/2103.07889.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
daip13/LPC_MOT community
Papers with Code archive
4 ran · 1 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
daip13/LPC_MOT/learnable_proposal_classifier/gcn_based_purity_network/dsgcn/models/dsgcn.py
code served (permissive licence) · get_code("96b7d80b1def4faf")
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, BasicBlock: 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 math
from torch.nn.parameter import Parameter

torch.manual_seed(0)

class GraphConv(nn.Module):
    def __init__(self, in_features, out_features, bias=False):
        super(GraphConv, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.weight = Parameter(torch.FloatTensor(in_features, out_features))
        if bias:
            self.bias = Parameter(torch.FloatTensor(out_features))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self):
        stdv = 1.0 / math.sqrt(self.weight.size(1))
        self.weight.data.uniform_(-stdv, stdv)
        if self.bias is not None:
            self.bias.data.uniform_(-stdv, stdv)

    def forward(self, x, adj, D=None):
        if x.dim() == 3:
            xw = torch.matmul(x, self.weight)
            output = torch.bmm(adj, xw)
        elif x.dim() == 2:
            xw = torch.mm(x, self.weight)
            output = torch.spmm(adj, xw)
        if D is not None:
            output = output * 1.0 / D
        return output

class BasicBlock(nn.Module):
    def __init__(self, inplanes, planes, freeze_bn, dropout=0.0):
        super(BasicBlock, self).__init__()
        self.gc = GraphConv(inplanes, planes)
        self.bn = nn.BatchNorm1d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.freeze_bn = freeze_bn
        if dropout > 0:
            self.dropout = nn.Dropout(p=dropout)
        else:
            self.dropout = None

    def forward(self, x, adj, index, D=None):
        x = self.gc(x, adj, D)
        bs, N, D_dim = x.shape
        x = x.view(-1, D_dim)
        x1 = x.sum(1)
        index1 = (x1 != 0).nonzero()
        index1 = index1.view(-1)
        if self.freeze_bn:
            self.bn.eval()
        x_new = x[index1]
        x_new = self.relu(x_new)
        x[index1] = x_new
        x = x.view(bs, N, D_dim)
        return x

inplanes = 3
planes = 5
freeze_bn = False
dropout = 0.1

x = torch.randn(2, 4, 3)
adj = torch.randn(2, 4, 4)
index = torch.tensor([0, 1, 2, 3])
D = torch.tensor([1.0, 1.0, 1.0, 1.0])

ARGS = {
    'inplanes': inplanes,
    'planes': planes,
    'freeze_bn': freeze_bn,
    'dropout': dropout
}
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 BasicBlock — 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 BasicBlock 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
GCN Ran
ran on a synthesized input · constructed an object; no result was computed
daip13/LPC_MOT/learnable_proposal_classifier/gcn_based_purity_network/dsgcn/models/dsgcn.py
code served (permissive licence) · get_code("748441f5b0d1ba43")
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, GCN: 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
import math

torch.manual_seed(0)

# Define planes configuration - list of hidden dimensions for each layer
planes = [8, 16]

# Feature dimensions
feature_dim = 4

# Whether input is featureless (use 1D embedding) or has features
featureless = False

# Number of output classes
num_classes = 2

# Batch normalization freeze
freeze_bn = True

# Dropout rate
dropout = 0.1

# Reduction method for pooling
reduce_method = 'max'

# Loss function type
lossfunc = 'CELoss'

ARGS = {
    'planes': planes,
    'feature_dim': feature_dim,
    'featureless': featureless,
    'num_classes': num_classes,
    'freeze_bn': freeze_bn,
    'dropout': dropout,
    'reduce_method': reduce_method,
    'lossfunc': lossfunc,
}
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 GCN — 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 GCN 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
GNN Ran
ran on a synthesized input · constructed an object; no result was computed
daip13/LPC_MOT/learnable_proposal_classifier/gcn_based_purity_network/dsgcn/models/dsgcn.py
code served (permissive licence) · get_code("7e35382b5c5a5ae5")
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, GNN: 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 DummyGNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(8, 2)
        self.softmax_fn = nn.Softmax(dim=1)
    
    def extract(self, feature_input, data2, data3):
        # Returns (logits, features)
        batch_size = feature_input.shape[0]
        logits = self.linear(feature_input.mean(dim=1))
        features = torch.randn(batch_size, 4)
        return logits, features
    
    def softmax(self, x):
        return self.softmax_fn(x)

# Create sample data for forward pass
batch_size = 2
reid_feature = torch.randn(batch_size, 1, 4)  # (batch, seq, dim)
spatem_feature = torch.randn(batch_size, 1, 4)  # (batch, seq, dim)
auxiliary_data = torch.randn(batch_size, 3)
purity_label = torch.tensor([0, 1], dtype=torch.long)

data = [reid_feature, spatem_feature, auxiliary_data, purity_label]

ARGS = {
    'planes': [64, 128],
    'feature_dim': 8,
    'featureless': False,
    'num_classes': 2,
    'dropout': 0.1,
    'reduce_method': 'max',
    'lossfunc': 'CELoss'
}
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 GNN — 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 GNN 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
GraphConv Ran
ran on a synthesized input · constructed an object; no result was computed
daip13/LPC_MOT/learnable_proposal_classifier/gcn_based_purity_network/dsgcn/models/dsgcn.py
code served (permissive licence) · get_code("d9c4fcd2b20442d2")
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, GraphConv: 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 math
import torch
import torch.nn as nn
from torch.nn.parameter import Parameter

torch.manual_seed(0)

class GraphConv(nn.Module):

    def __init__(self, in_features, out_features, bias=False):
        super(GraphConv, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.weight = Parameter(torch.FloatTensor(in_features, out_features))
        if bias:
            self.bias = Parameter(torch.FloatTensor(out_features))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self):
        stdv = 1.0 / math.sqrt(self.weight.size(1))
        self.weight.data.uniform_(-stdv, stdv)
        if self.bias is not None:
            self.bias.data.uniform_(-stdv, stdv)

    def forward(self, x, adj, D=None):
        if x.dim() == 3:
            xw = torch.matmul(x, self.weight)
            output = torch.bmm(adj, xw)
        elif x.dim() == 2:
            xw = torch.mm(x, self.weight)
            output = torch.spmm(adj, xw)
        if D is not None:
            output = output * 1.0 / D
        return output

    def __repr__(self):
        return self.__class__.__name__ + ' (' + str(self.in_features) + ' -> ' + str(self.out_features) + ')'

in_features = 4
out_features = 3
bias = False

# Create instance for forward pass test (2D case)
x_2d = torch.randn(2, 4)
adj_2d = torch.sparse_coo_tensor(
    indices=torch.tensor([[0, 1, 1], [0, 0, 1]]),
    values=torch.tensor([1.0, 1.0, 1.0]),
    size=(2, 2)
)
D_2d = torch.tensor(2.0)

# Create instance for forward pass test (3D case)
x_3d = torch.randn(2, 2, 4)
adj_3d = torch.randn(2, 2, 2)
D_3d = torch.tensor(2.0)

ARGS = {
    'in_features': in_features,
    'out_features': out_features,
    'bias': bias,
}
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 GraphConv — 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 GraphConv 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 Not yet run
unverified (harvested, no recorded run)
daip13/LPC_MOT/learnable_proposal_classifier/gcn_based_purity_network/dsgcn/models/dsgcn.py
code served (permissive licence) · get_code("f2496d122dcd0113")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 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.

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

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. However, it is not trivial to solve the data-association problem in an end-to-end fashion. In this paper, we propose a novel proposal-based learnable framework, which models MOT as a proposal generation, proposal scoring and trajectory inference paradigm on an affinity graph. This framework is similar to the two-stage object detector Faster RCNN, and can solve the MOT problem in a data-driven way. For proposal generation, we propose an iterative graph clustering method to reduce the computational cost while maintaining the quality of the generated proposals. For proposal scoring, we deploy a trainable graph-convolutional-network (GCN) to learn the structural patterns of the generated proposals and rank them according to the estimated quality scores. For trajectory inference, a simple deoverlapping strategy is adopted to generate tracking output while complying with the constraints that no detection can be assigned to more than one track. We experimentally demonstrate that the proposed method achieves a clear performance improvement in both MOTA and IDF1 with respect to previous state-ofthe-art on two public benchmarks. Our code is available at https://github.com/daip13/LPC_MOT.git.

For agents

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

get_harvested_code_for_paper("2103.07889")
get_code_for_paper("2103.07889")
have("2103.07889")

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

curl https://syntology.ai/api/ran/2103.07889.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.07889.svg)](https://syntology.ai/paper/2103.07889)

Connect an agent — have() is free.