SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.05485 · 2021

Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 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/2104.05485.json · badge: /api/ran/2104.05485.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
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
ZeWang95/PedesPred reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
AlexNet Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/base_models.py
code served (permissive licence) · get_code("bfd1c2e7a1031af7")
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 Functional. 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 tensorflow as tf

ARGS = {
    'include_top': True,
    'weights': None,
    'input_tensor': None,
    'input_shape': (227, 227, 3),
    'pooling': None,
    'classes': 1000,
    'classifier_activation': 'softmax',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
C3DNet Ran
ran; our contract draft was wrong, not the code
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/base_models.py
code served (permissive licence) · get_code("70b7c46fc986de07")
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 Functional. 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.

from tensorflow.keras.layers import Input
import numpy as np

# Create input tensor
input_tensor = Input(shape=(16, 112, 112, 3))

# Define ARGS dict with all parameters
ARGS = {
    'freeze_conv_layers': False,
    'weights': None,
    'dense_activation': 'softmax',
    'dropout': 0.5,
    'include_top': False,
    'input_data': input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
attention_3d_block Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/action_predict.py
code served (permissive licence) · get_code("2e4849ab47d215d1")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

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

# Create a 3D tensor with shape (batch_size=2, time_steps=5, input_dim=4)
# This represents hidden states from a sequence model
batch_size = 2
time_steps = 5
input_dim = 4

hidden_states = tf.random.normal((batch_size, time_steps, input_dim))

# Define the arguments dictionary
ARGS = {
    'hidden_states': hidden_states,
    'dense_size': 128,
    'modality': '_test'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py recorded SymbolicTensor ndim 2, which disagrees with the fixture run
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
flip_pose Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/utils.py
code served (permissive licence) · get_code("12c03517dc631fb8")
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 numpy as np

torch_seed = 0

# Analyze the function:
# - Takes 'pose' parameter
# - Calls pose.copy() - so it needs to be a list or numpy array
# - Accesses pose[i] with integer indexing
# - Compares elements to 0 and 1
# - The flip_map has 36 elements, so pose should have 36 elements
# - Elements are numeric (compared with 0, 1, subtracted from 1)

# Create a valid pose - a list of 36 numeric values
pose = [0.5, 0.3, 0.0, 0.8, 0.2, 0.1, 0.9, 0.4, 0.6, 0.7, 
        0.0, 0.5, 0.3, 0.2, 0.1, 0.8, 0.4, 0.6, 0.7, 0.9,
        0.2, 0.0, 0.5, 0.3, 0.8, 0.1, 0.4, 0.6, 0.7, 0.9,
        0.2, 0.3, 0.5, 0.0, 0.8, 0.1]

ARGS = {
    "pose": pose
}
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 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
init_canvas Ran
ran; our contract draft was wrong, not the code
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/action_predict.py
code served (permissive licence) · get_code("7b821accd61062be")
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 3, dtype family int, shape (480, 640, 3) 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 cv2
import numpy as np

ARGS = {
    "width": 640,
    "height": 480,
    "color": (255, 128, 64)
}
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 ndarray, ndim 3, dtype family int, shape (480, 640, 3) — shape (480, 640, 3) 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
label_to_color_image Ran
ran, honoured the contract we drafted
ZeWang95/PedesPred/action_predict.py
code served (permissive licence) · get_code("6f9338c9156e1013")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 3, dtype family int, shape (2, 4, 3) 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 a small label array for testing
# The function expects a label array where each value is an index into the colormap
# Valid indices are 0-18 based on the colormap definition
label = np.array([[0, 1, 2, 3],
                  [11, 13, 14, 15]], dtype=np.uint8)

ARGS = {
    'label': label
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 3, dtype family int, shape (2, 4, 3) — shape (2, 4, 3) 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
convert_to_fcn Not yet run
unverified (harvested, no recorded run)
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/base_models.py
code served (permissive licence) · get_code("2076c411533f24d8")
How it ran

no invocation recorded.

get_pose Not yet run
unverified (harvested, no recorded run)
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/utils.py
code served (permissive licence) · get_code("3e3e8c2626b91285")
How it ran

no invocation recorded.

jitter_bbox Not yet run
unverified (harvested, no recorded run)
OSU-Haolin/Pedestrian_Crossing_Intention_Prediction/utils.py
code served (permissive licence) · get_code("abd490a9489f6a76")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Predicting vulnerable road user behavior is an essential prerequisite for deploying Automated Driving Systems (ADS) in the real-world. Pedestrian crossing intention should be recognized in real-time, especially for urban driving. Recent works have shown the potential of using vision-based deep neural network models for this task. However, these models are not robust and certain issues still need to be resolved. First, the global spatio-temproal context that accounts for the interaction between the target pedestrian and the scene has not been properly utilized. Second, the optimum strategy for fusing different sensor data has not been thoroughly investigated. This work addresses the above limitations by introducing a novel neural network architecture to fuse inherently different spatio-temporal features for pedestrian crossing intention prediction. We fuse different phenomena such as sequences of RGB imagery, semantic segmentation masks, and ego-vehicle speed in an optimum way using attention mechanisms and a stack of recurrent neural networks. The optimum architecture was obtained through exhaustive ablation and comparison studies. Extensive comparative experiments on the JAAD pedestrian action prediction benchmark demonstrate the effectiveness of the proposed method, where state-of-the-art performance was achieved. Our code is open-source and publicly available.

For agents

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

get_harvested_code_for_paper("2104.05485")
get_code_for_paper("2104.05485")
have("2104.05485")

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

curl https://syntology.ai/api/ran/2104.05485.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.05485.svg)](https://syntology.ai/paper/2104.05485)

Connect an agent — have() is free.