SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.00446 · 2024

Diving Deeper Into Pedestrian Behavior Understanding: Intention Estimation, Action Prediction, and Event Risk Assessment

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 5 failures of our instrument; 0 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/2407.00446.json · badge: /api/ran/2407.00446.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
aras62/PIE canonical (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
FunctionStatusWhere it lives
convert_to_imagewise_annt Ran
ran; our contract draft was wrong, not the code
aras62/PIE/visualization/model_visualize.py
code served (permissive licence) · get_code("3fcc2699b54fff2c")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Construct seq_data with the structure expected by the function
seq_data = {
    'image': [
        [
            'dataset1/video1/img001.jpg',
            'dataset1/video1/img002.jpg',
        ],
        [
            'dataset2/video2/img001.jpg',
            'dataset2/video2/img002.jpg',
        ]
    ],
    'obd_speed': [
        [30.5, 31.2],
        [25.0, 26.5]
    ],
    'vehicle_act': [
        [1, 1],
        [0, 0]
    ],
    'pid': [
        [[101], [102]],
        [[201], [202]]
    ],
    'event_frames': [
        [10, 20],
        [15, 25]
    ],
    'bbox': [
        [[10, 20, 100, 200], [15, 25, 110, 210]],
        [[20, 30, 120, 220], [25, 35, 130, 230]]
    ]
}

# Define data_fields to specify which fields to include
data_fields = ['speed', 'pid', 'event_frames', 'bbox', 'image']

ARGS = {
    'seq_data': seq_data,
    'data_fields': data_fields
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
convert_to_pedwise_annt Ran
ran; our contract draft was wrong, not the code
aras62/PIE/visualization/model_visualize.py
code served (permissive licence) · get_code("7c407082f2b33af0")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Construct seq_data dict with required fields
seq_data = {
    'pid': [
        [[1], [2], [3]],  # Frame 0: 3 pedestrians
        [[1], [2], [4]]   # Frame 1: 3 pedestrians (different set)
    ],
    'obd_speed': False,  # Will trigger fallback to vehicle_act
    'vehicle_act': [
        [10.5, 11.2, 12.1],  # Frame 0 speeds for 3 peds
        [10.8, 11.5, 12.4]   # Frame 1 speeds for 3 peds
    ],
    'bbox': [
        [[100, 200, 50, 60], [150, 210, 55, 65], [200, 220, 52, 62]],  # Frame 0
        [[105, 205, 50, 60], [155, 215, 55, 65], [205, 225, 52, 62]]   # Frame 1
    ],
    'event_frames': [
        [0, 1, 0],  # Frame 0 event flags
        [1, 0, 1]   # Frame 1 event flags
    ]
}

# Define data_fields to extract
data_fields = ['pid', 'speed', 'bbox', 'event_frames']

ARGS = {
    'seq_data': seq_data,
    'data_fields': data_fields
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, 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
get_base_metrics Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aras62/PIE/scenarioEval/action_evaluate.py
code served (permissive licence) · get_code("20a648679f9c7c6f")
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 dict. 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

# Set random seed for reproducibility
np.random.seed(0)

# Create ground truth labels (binary classification)
gt = np.array([0, 1, 0, 1, 1, 0, 1, 0])

# Create predictions - test with multi-dimensional case (probabilities for 2 classes)
pred = np.array([
    [0.1, 0.9],
    [0.8, 0.2],
    [0.3, 0.7],
    [0.2, 0.8],
    [0.1, 0.9],
    [0.9, 0.1],
    [0.4, 0.6],
    [0.7, 0.3]
])

# Data type string
d_type = "test"

# Averaging type for multi-class metrics
avg = "binary"

# Sample weights (optional)
sample_weight = np.array([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0])

ARGS = {
    "gt": gt,
    "pred": pred,
    "d_type": d_type,
    "avg": avg,
    "sample_weight": sample_weight
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, sklearn — 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
get_curve_metrics Ran
ran; our contract draft was wrong, not the code
aras62/PIE/scenarioEval/action_evaluate.py
code served (permissive licence) · get_code("cf86d1ee2b57344d")
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 dict. 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 numpy as np
from sklearn.metrics import roc_auc_score, balanced_accuracy_score, average_precision_score

torch.manual_seed(0)

# Binary classification case
gt_binary = np.array([0, 1, 0, 1])
pred_binary = np.array([0.1, 0.9, 0.2, 0.8])

# Multiclass case with shape (batch_size, num_classes)
gt_multiclass = np.array([0, 1, 2, 0])
pred_multiclass = np.array([
    [0.7, 0.2, 0.1],
    [0.1, 0.8, 0.1],
    [0.1, 0.2, 0.7],
    [0.6, 0.3, 0.1]
])

ARGS = {
    "gt": gt_binary,
    "pred": pred_binary,
    "d_type": "val",
    "avg": "binary"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, sklearn, 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
get_intention_labels Ran
ran; our contract draft was wrong, not the code
aras62/PIE/utilities/data_gen_utils.py
code served (permissive licence) · get_code("7f7d06181a31a410")
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
import numpy as np

torch.manual_seed(0)

# Construct data_raw with intention_prob
# The function iterates over data_raw['intention_prob']
# Each seq in that list is indexed with seq[0][0] to get a scalar probability
# Then it creates int_labels as [[i]] * len(seq)
data_raw = {
    'intention_prob': [
        # First sequence: 2D array where first element is [0.15]
        np.array([[0.15], [0.25], [0.35]]),
        # Second sequence: 2D array where first element is [0.75]
        np.array([[0.75], [0.85]]),
    ]
}

# Construct opts with num_int_class
opts = {
    'num_int_class': 3
}

ARGS = {
    'data_raw': data_raw,
    'opts': opts,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 — 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

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

In this paper, we delve into the pedestrian behavior understanding problem from the perspective of three different tasks: intention estimation, action prediction, and event risk assessment. We first define the tasks and discuss how these tasks are represented and annotated in two widely used pedestrian datasets, JAAD and PIE. We then propose a new benchmark based on these definitions, available annotations, and three new classes of metrics, each designed to assess different aspects of the model performance. We apply the new evaluation approach to examine four SOTA prediction models on each task and compare their performance w.r.t. metrics and input modalities. In particular, we analyze the differences between intention estimation and action prediction tasks by considering various scenarios and contextual factors. Lastly, we examine model agreement across these two tasks to show their complementary role. The proposed benchmark reveals new facts about the role of different data modalities, the tasks, and relevant data properties. We conclude by elaborating on our findings and proposing future research directions.

For agents

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

get_harvested_code_for_paper("2407.00446")
get_code_for_paper("2407.00446")
have("2407.00446")

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

curl https://syntology.ai/api/ran/2407.00446.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.00446.svg)](https://syntology.ai/paper/2407.00446)

Connect an agent — have() is free.