SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.03790 · 2020

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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 6 have no contract verdict; 0 failures 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/2006.03790.json · badge: /api/ran/2006.03790.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
xin71/MTTS-CAN canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
CAN Ran
ran on a synthesized input
xin71/MTTS-CAN/code/model.py
code served (permissive licence) · get_code("5e5bdb364e642d70")
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
import numpy as np

ARGS = {
    'nb_filters1': 32,
    'nb_filters2': 64,
    'input_shape': (32, 32, 3),
    'kernel_size': (3, 3),
    'dropout_rate1': 0.25,
    'dropout_rate2': 0.5,
    'pool_size': (2, 2),
    'nb_dense': 128,
}
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
detrend Ran
ran on a synthesized input
xin71/MTTS-CAN/code/inference_preprocess.py
code served (permissive licence) · get_code("9f063d3ca0da3fcd")
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 1, dtype family float, shape (8,) 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 signal for detrending
signal = np.array([1.0, 2.0, 3.5, 4.2, 5.1, 6.0, 7.5, 8.2], dtype=np.float64)

# Set smoothing parameter Lambda
Lambda = 100

ARGS = {
    "signal": signal,
    "Lambda": Lambda,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (8,) — shape (8,) 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
get_nframe_video Ran
ran on a synthesized input
xin71/MTTS-CAN/code/pre_process.py
code served (permissive licence) · get_code("78c50f6ccff6b241")
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 int, ndim 0, dtype family int, 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 h5py
import numpy as np
import tempfile
import os

# Create a temporary HDF5 file with the expected structure
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "test_video.h5")

# Create an HDF5 file with a 'dysub' dataset
with h5py.File(temp_path, 'w') as f:
    # Create a dysub dataset with shape (10, 5, 3) - 10 frames, 5x3 data
    dysub_data = np.random.rand(10, 5, 3).astype(np.float32)
    f.create_dataset('dysub', data=dysub_data)

ARGS = {
    'path': temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
get_nframe_video_val Ran
ran on a synthesized input
xin71/MTTS-CAN/code/pre_process.py
code served (permissive licence) · get_code("458a7fdb0e205e18")
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 int, ndim 0, dtype family int, 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 numpy as np
import scipy.io
import tempfile
import os

# Create a temporary .mat file with the required structure
temp_dir = tempfile.mkdtemp()
mat_path = os.path.join(temp_dir, "test_data.mat")

# Create a sample dXsub array with shape (5, 3) - 5 frames, 3 features
dXsub = np.random.randn(5, 3)
scipy.io.savemat(mat_path, {'dXsub': dXsub})

ARGS = {
    'path': mat_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
preprocess_raw_video Ran
ran on a synthesized input
xin71/MTTS-CAN/code/inference_preprocess.py
code served (permissive licence) · get_code("f67cd52ce15699d9")
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 4, dtype family float, shape (4, 36, 36, 6) 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
import cv2
import tempfile
import os

# Create a minimal test video file
def create_test_video(filepath, num_frames=5, height=100, width=120, fps=30):
    """Create a simple test video with colored frames."""
    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
    out = cv2.VideoWriter(filepath, fourcc, fps, (width, height))
    
    for frame_idx in range(num_frames):
        # Create a simple frame with varying colors
        frame = np.zeros((height, width, 3), dtype=np.uint8)
        # Add some variation across frames
        frame[:, :, 0] = (50 + frame_idx * 10) % 256  # Blue channel
        frame[:, :, 1] = (100 + frame_idx * 5) % 256  # Green channel
        frame[:, :, 2] = (150 - frame_idx * 3) % 256  # Red channel
        out.write(frame)
    
    out.release()

# Create temporary video file
temp_dir = tempfile.gettempdir()
video_path = os.path.join(temp_dir, 'test_video.mp4')
create_test_video(video_path, num_frames=5, height=100, width=120)

ARGS = {
    'videoFilePath': video_path,
    'dim': 36
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, matplotlib, numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (4, 36, 36, 6) — shape (4, 36, 36, 6) 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
split_subj Ran
ran on a synthesized input
xin71/MTTS-CAN/code/pre_process.py
code served (permissive licence) · get_code("043f5cee98e9150d")
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 tuple. 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 h5py
import numpy as np
import tempfile
import os

# Create a temporary directory and HDF5 file for testing
temp_dir = tempfile.mkdtemp()
h5_path = os.path.join(temp_dir, 'M.mat')

# Create sample data
# M should be a boolean array where rows are subjects and columns are CV splits
# We'll create a 5x3 array (5 subjects, 3 CV splits)
M_data = np.array([
    [True, False, False],
    [False, True, False],
    [True, False, True],
    [False, False, True],
    [False, True, False]
], dtype=bool)

# Write to HDF5 file (transposed as the function expects to transpose it)
with h5py.File(h5_path, 'w') as f:
    # The function does np.transpose on M, so we store the transposed version
    f.create_dataset('M', data=np.transpose(M_data))

# Create subject numbers
subNum = np.array([101, 102, 103, 104, 105])

# cv_split is an index into the columns of M (after transpose)
cv_split = 0

ARGS = {
    'data_dir': temp_dir,
    'cv_split': cv_split,
    'subNum': subNum
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
MT_CAN Not yet run
unverified (harvested, no recorded run)
xin71/MTTS-CAN/code/model.py
code served (permissive licence) · get_code("25437cf49e32cdbc")
How it ran

no invocation recorded.

TSM_Cov2D Not yet run
unverified (harvested, no recorded run)
xin71/MTTS-CAN/code/model.py
code served (permissive licence) · get_code("c9dce5ddd6127a4d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Telehealth and remote health monitoring have become increasingly important during the SARS-CoV-2 pandemic and it is widely expected that this will have a lasting impact on healthcare practices. These tools can help reduce the risk of exposing patients and medical staff to infection, make healthcare services more accessible, and allow providers to see more patients. However, objective measurement of vital signs is challenging without direct contact with a patient. We present a video-based and on-device optical cardiopulmonary vital sign measurement approach. It leverages a novel multi-task temporal shift convolutional attention network (MTTS-CAN) and enables real-time cardiovascular and respiratory measurements on mobile platforms. We evaluate our system on an Advanced RISC Machine (ARM) CPU and achieve state-of-the-art accuracy while running at over 150 frames per second which enables real-time applications. Systematic experimentation on large benchmark datasets reveals that our approach leads to substantial (20%-50%) reductions in error and generalizes well across datasets.

For agents

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

get_harvested_code_for_paper("2006.03790")
get_code_for_paper("2006.03790")
have("2006.03790")

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

curl https://syntology.ai/api/ran/2006.03790.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.03790.svg)](https://syntology.ai/paper/2006.03790)

Connect an agent — have() is free.