SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.05447 · 2023

From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 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/2312.05447.json · badge: /api/ran/2312.05447.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
FER-LMC/S2D canonical (classifier label)
classifier basis: census
11 ran · 3 no recorded run
FunctionStatusWhere it lives
crop_clip Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FER-LMC/S2D/datasets/functional.py
code served (permissive licence) · get_code("bc39b8ed5fefa7eb")
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 4, dtype family int; 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
import PIL
from PIL import Image

# Create a small numpy array-based clip
np_clip = [
    np.random.randint(0, 256, (100, 120, 3), dtype=np.uint8),
    np.random.randint(0, 256, (100, 120, 3), dtype=np.uint8),
]

# Create a small PIL Image-based clip
pil_clip = [
    Image.new('RGB', (120, 100), color=(73, 109, 137)),
    Image.new('RGB', (120, 100), color=(200, 150, 100)),
]

# Test with numpy arrays
ARGS = {
    'clip': np_clip,
    'min_h': 10,
    'min_w': 15,
    'h': 50,
    'w': 60,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 4, dtype family int — 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
feature2token Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FER-LMC/S2D/model_finetuning.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XiaokunFeng/ATCTrack, is pointer only (licence: NONE) · get_code("e35ba287fd7fef0b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XiaokunFeng/ATCTrack, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_loss_scale_for_deepspeed Ran
ran, honoured the contract we drafted
FER-LMC/S2D/engine_for_finetuning.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kangsankim07/videoicl, is pointer only (licence: NONE) · get_code("29416043c7035e7c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kangsankim07/videoicl, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_resize_sizes Ran
ran, honoured the contract we drafted
FER-LMC/S2D/datasets/functional.py
code served (permissive licence) · get_code("2b53e457d5632b4e")
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, ndim 1, dtype family int; 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 torch
import numpy as np

# Analyze the function: get_resize_sizes takes im_h (image height), 
# im_w (image width), and size (a target dimension). It uses basic 
# arithmetic operations on these numeric values and returns a tuple.

torch.manual_seed(0)

# Create simple numeric arguments
im_h = 480  # image height - distinct value
im_w = 640  # image width - distinct value
size = 256  # target resize dimension - distinct value

ARGS = {
    "im_h": im_h,
    "im_w": im_w,
    "size": size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple 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
resize_clip Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FER-LMC/S2D/datasets/functional.py
code served (permissive licence) · get_code("981936c73d3cdd12")
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 4, dtype family int; 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 numbers
import cv2
import numpy as np
import PIL
from PIL import Image

# Create a small numpy array clip (list of frames)
frame1 = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)
frame2 = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)
np_clip = [frame1, frame2]

# Create a PIL Image clip
pil_frame1 = Image.fromarray(np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8))
pil_frame2 = Image.fromarray(np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8))
pil_clip = [pil_frame1, pil_frame2]

ARGS = {
    'clip': np_clip,
    'size': 256,
    'interpolation': 'bilinear'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 4, dtype family int — 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
shear_x Ran
ran; our contract draft was wrong, not the code
FER-LMC/S2D/datasets/rand_augment.py
code served (permissive licence) · get_code("e866e1196986f728")
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 Image. 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 random
import PIL
from PIL import Image, ImageEnhance, ImageOps

# Create a simple PIL Image object
img = Image.new('RGB', (100, 100), color='red')

# Define ARGS dict with all parameters for shear_x
ARGS = {
    'img': img,
    'factor': 0.5,
    'resample': Image.BILINEAR,
    'fillcolor': (255, 255, 255)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
shear_y Ran
ran; our contract draft was wrong, not the code
FER-LMC/S2D/datasets/rand_augment.py
code served (permissive licence) · get_code("7b2503c99c9447fb")
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 Image. 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 random
import PIL
from PIL import Image, ImageEnhance, ImageOps

# Create a simple PIL Image for testing
img = Image.new('RGB', (100, 100), color='red')

# Define ARGS dict with all parameters for shear_y function
ARGS = {
    'img': img,
    'factor': 0.5,
    'resample': Image.BILINEAR,
    'fillcolor': (255, 255, 255)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
tensor_normalize Ran
ran, honoured the contract we drafted
FER-LMC/S2D/datasets/kinetics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kangsankim07/videoicl, is pointer only (licence: NONE) · get_code("14b3b13b2e7ee844")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kangsankim07/videoicl, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

token2feature Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FER-LMC/S2D/model_finetuning.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from XiaokunFeng/ATCTrack, is pointer only (licence: NONE) · get_code("dafcc70e40e4a867")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from XiaokunFeng/ATCTrack, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

train_class_batch Ran
ran; our contract draft was wrong, not the code
FER-LMC/S2D/engine_for_finetuning.py
code served (permissive licence) · get_code("6b9b585439223637")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 3)
        self.feature_layer = nn.Linear(8, 5)
    
    def forward(self, samples, a):
        x = self.linear1(samples)
        x = x + a
        feat = self.feature_layer(x)
        outputs = self.linear2(x)
        return outputs, feat

model = SimpleModel()

samples = torch.randn(2, 4)
a = torch.randn(2, 8)
target = torch.randint(0, 3, (2,))
criterion = nn.CrossEntropyLoss()

ARGS = {
    "model": model,
    "samples": samples,
    "a": a,
    "target": target,
    "criterion": criterion
}
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 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
translate_x_rel Ran
ran; our contract draft was wrong, not the code
FER-LMC/S2D/datasets/rand_augment.py
code served (permissive licence) · get_code("323759f906fbb394")
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 Image. 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 random
import PIL
from PIL import Image
import numpy as np

# Create a small PIL Image object for testing
# The function uses img.size[0] and img.transform()
test_img = Image.new('RGB', (100, 80), color='red')

# Define ARGS dict with all parameters for translate_x_rel
ARGS = {
    'img': test_img,
    'pct': 0.2,
    'resample': Image.BILINEAR,
    'fillcolor': (255, 255, 255)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
build_dataset Not yet run
unverified (harvested, no recorded run)
FER-LMC/S2D/datasets/datasets.py
code served (permissive licence) · get_code("f00a047305ea9335")
How it ran

no invocation recorded.

build_pretraining_dataset Not yet run
unverified (harvested, no recorded run)
FER-LMC/S2D/datasets/datasets.py
code served (permissive licence) · get_code("55b44eaa04001d35")
How it ran

no invocation recorded.

spatial_sampling Not yet run
unverified (harvested, no recorded run)
FER-LMC/S2D/datasets/kinetics.py
code served (permissive licence) · get_code("7e49117a60f3b108")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 11 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 1 the same month, 11 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
shear_x 27 other papers
15 dated earlier, 12 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 24 more not named here
shear_y 27 other papers
15 dated earlier, 12 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 24 more not named here
translate_x_rel 26 other papers
15 dated earlier, 11 later
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
2109.06165 (2021-09)
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
and 23 more not named here
get_loss_scale_for_deepspeed 15 other papers
7 dated earlier, 1 the same month, 7 later
2203.14415 (2022-03)
Mugs: A Multi-Granular Self-Supervised Learning Framework
2211.09120 (2022-11)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
2212.10368 (2022-12)
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
and 12 more not named here
tensor_normalize 15 other papers
7 dated earlier, 8 later
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
2211.09120 (2022-11)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
2307.02227 (2023-07)
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition
and 12 more not named here
crop_clip 13 other papers
9 dated earlier, 4 later
2112.02815 (2021-12)
Make It Move: Controllable Image-to-Video Generation with Text Descriptions
2209.10340 (2022-09)
FNeVR: Neural Volume Rendering for Face Animation
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
and 10 more not named here
get_resize_sizes 10 other papers
6 dated earlier, 4 later
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
2211.09120 (2022-11)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
2307.02227 (2023-07)
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition
and 7 more not named here
resize_clip 9 other papers
5 dated earlier, 4 later
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
2211.09120 (2022-11)
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
2307.02227 (2023-07)
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition
and 6 more not named here
spatial_sampling 2 other papers
2 later
2403.20254 (2024-03)
Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions
2406.07471 (2024-06)
OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding
feature2token 1 other paper
1 later
2507.19875 (2025-07)
ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking
token2feature 1 other paper
1 later
2507.19875 (2025-07)
ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking

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

Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations, e.g., insufficient quantity and diversity of pose, occlusion and illumination, as well as the inherent ambiguity of facial expressions. In contrast, static facial expression recognition (SFER) currently shows much higher performance and can benefit from more abundant high-quality training data. Moreover, the appearance features and dynamic dependencies of DFER remain largely unexplored. To tackle these challenges, we introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features, thereby significantly improving DFER performance. Firstly, we build and train an image model for SFER, which incorporates a standard Vision Transformer (ViT) and Multi-View Complementary Prompters (MCPs) only. Then, we obtain our video model (i.e., S2D), for DFER, by inserting Temporal-Modeling Adapters (TMAs) into the image model. MCPs enhance facial expression features with landmark-aware features inferred by an off-the-shelf facial landmark detector. And the TMAs capture and model the relationships of dynamic changes in facial expressions, effectively extending the pre-trained image model for videos. Notably, MCPs and TMAs only increase a fraction of trainable parameters (less than +10\%) to the original image model. Moreover, we present a novel Emotion-Anchors (i.e., reference samples for each emotion category) based Self-Distillation Loss to reduce the detrimental influence of ambiguous emotion labels, further enhancing our S2D. Experiments conducted on popular SFER and DFER datasets show that we achieve the state of the art.

For agents

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

get_harvested_code_for_paper("2312.05447")
get_code_for_paper("2312.05447")
have("2312.05447")

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

curl https://syntology.ai/api/ran/2312.05447.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.05447.svg)](https://syntology.ai/paper/2312.05447)

Connect an agent — have() is free.