SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.09953 · ECCV · 2022

Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction

Hae-Gon Jeon, Inhwan Bae, Jin-Hwi Park

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 1 has no contract verdict; 1 failure 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/2207.09953.json · badge: /api/ran/2207.09953.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
inhwanbae/GPGraph community
Papers with Code archive
2 ran · 2 no recorded run
FunctionStatusWhere it lives
GroupIntegrator Ran
ran on a synthesized input
inhwanbae/GPGraph/model_groupwrapper.py
code served (permissive licence) · get_code("d694c354b0cf85ed")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 5, 12, 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.nn as nn

class GroupIntegrator(nn.Module):

    def __init__(self, mix_type='mean', n_mix=3, out_channels=5, pred_seq_len=12):
        super().__init__()
        self.mix_type = mix_type
        self.pred_seq_len = pred_seq_len
        if mix_type == 'mlp':
            self.st_gcns_mix = nn.Sequential(nn.PReLU(), nn.Conv2d(out_channels * pred_seq_len * n_mix, out_channels * pred_seq_len, kernel_size=1))
        elif mix_type == 'cnn':
            self.st_gcns_mix = nn.Sequential(nn.PReLU(), nn.Conv2d(out_channels * n_mix, out_channels, kernel_size=(3, 1), padding=(1, 0)))

    def forward(self, v_stack):
        n_batch, n_ped = (v_stack[0].shape[0], v_stack[0].shape[3])
        if self.mix_type == 'sum':
            v = torch.stack(v_stack, dim=0).sum(dim=0)
        elif self.mix_type == 'mean':
            v = torch.stack(v_stack, dim=0).mean(dim=0)
        elif self.mix_type == 'mlp':
            v = torch.stack(v_stack, dim=0).mean(dim=0)
            v_stack = torch.cat(v_stack, dim=1).reshape(n_batch, -1, 1, n_ped)
            v = v + self.st_gcns_mix(v_stack).view(n_batch, -1, self.pred_seq_len, n_ped)
        elif self.mix_type == 'cnn':
            v = torch.stack(v_stack, dim=0).mean(dim=0)
            v = v + self.st_gcns_mix(torch.cat(v_stack, dim=1))
        else:
            raise NotImplementedError
        return v


INIT_ARGS = {
    'mix_type': 'mean',
    'n_mix': 3,
    'out_channels': 5,
    'pred_seq_len': 12,
}

ARGS = {
    'v_stack': [
        torch.randn(2, 5, 12, 4),
        torch.randn(2, 5, 12, 4),
        torch.randn(2, 5, 12, 4),
    ]
}

if __name__ == '__main__':
    model = GroupIntegrator(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float, shape (2, 5, 12, 4) — shape (2, 5, 12, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
generate_identity_matrix Ran
ran; our contract draft was wrong, not the code
inhwanbae/GPGraph/model_groupwrapper.py
code served (permissive licence) · get_code("828ed392be109d01")
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 list. 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)

# The function expects a tensor v with at least 4 dimensions
# It accesses v.size(2), v.size(3), v.device
# It calls torch.eye() and .repeat() on the result
# Create a 4D tensor with distinct sizes for each dimension
v = torch.randn(2, 3, 4, 5)

ARGS = {
    "v": v
}
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 list — a list 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
GPGraph Not yet run
unverified (harvested, no recorded run)
inhwanbae/GPGraph/model_groupwrapper.py
code served (permissive licence) · get_code("5c801e555d69de1c")
How it ran

no invocation recorded.

GroupGenerator Not yet run
unverified (harvested, no recorded run)
inhwanbae/GPGraph/model_groupwrapper.py
code served (permissive licence) · get_code("b9883ed59495d649")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
generate_identity_matrix
brick of this paper's assembly: helper
1 other paper
1 later
2307.09306 (2023-07)
EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting

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

Modeling the dynamics of people walking is a problem of long-standing interest in computer vision. Many previous works involving pedestrian trajectory prediction define a particular set of individual actions to implicitly model group actions. In this paper, we present a novel architecture named GP-Graph which has collective group representations for effective pedestrian trajectory prediction in crowded environments, and is compatible with all types of existing approaches. A key idea of GP-Graph is to model both individual-wise and group-wise relations as graph representations. To do this, GP-Graph first learns to assign each pedestrian into the most likely behavior group. Using this assignment information, GP-Graph then forms both intra-and inter-group interactions as graphs, accounting for human-human relations within a group and group-group relations, respectively. To be specific, for the intra-group interaction, we mask pedestrian graph edges out of an associated group. We also propose group pooling&unpooling operations to represent a group with multiple pedestrians as one graph node. Lastly, GP-Graph infers a probability map for socially-acceptable future trajectories from the integrated features of both group interactions. Moreover, we introduce a group-level latent vector sampling to ensure collective inferences over a set of possible future trajectories. Extensive experiments are conducted to validate the effectiveness of our architecture, which demonstrates consistent performance improvements with publicly available benchmarks. Code is publicly available at https://github.com/inhwanbae/GPGraph.

For agents

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

get_harvested_code_for_paper("2207.09953")
get_code_for_paper("2207.09953")
have("2207.09953")

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

curl https://syntology.ai/api/ran/2207.09953.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.09953.svg)](https://syntology.ai/paper/2207.09953)

Connect an agent — have() is free.