SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.16640 · 2023

EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 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; 3 failures of our instrument; 6 no recorded run), measured 2026-11-21; 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/2310.16640.json · badge: /api/ran/2310.16640.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
nickyfot/emoclip canonical (classifier label)
classifier basis: census
4 ran · 6 no recorded run
FunctionStatusWhere it lives
CCC Ran
ran; our contract draft was wrong, not the code
nickyfot/emoclip/utils.py
code served (permissive licence) · get_code("1bf0d337eeb02b7c")
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 Tensor, ndim 1, dtype family float, shape (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

torch.manual_seed(0)

# Create two small tensors with shape (batch_size=2, features=4)
# The function computes correlation metrics along dim=0 (across batch)
a = torch.randn(2, 4)
b = torch.randn(2, 4)

ARGS = {
    "a": a,
    "b": b,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (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: none by the harness; any seed is in the setup block
PCC Ran
ran; our contract draft was wrong, not the code
nickyfot/emoclip/utils.py
code served (permissive licence) · get_code("69709fdf9daef9aa")
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 Tensor, ndim 1, dtype family float, shape (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

torch.manual_seed(0)

# Create two small tensors for testing PCC (Pearson Correlation Coefficient)
# Shape: (batch_size=2, features=4)
a = torch.randn(2, 4)
b = torch.randn(2, 4)

ARGS = {
    "a": a,
    "b": b,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (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: none by the harness; any seed is in the setup block
get_config Ran
ran; our contract draft was wrong, not the code
nickyfot/emoclip/config.py
code served (permissive licence) · get_code("6872ff3312de15d1")
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 Namespace. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 argparse
from datetime import datetime

torch.manual_seed(0)

# The function get_config takes sysv as parameter
# sysv should be a list of command-line arguments (like sys.argv[1:])

ARGS = {
    'sysv': [
        '--model_basename', 'test_model',
        '--local_rank', '0',
        '--exp_name', 'test_exp_2024_01_15-120000',
        '--fold', '1',
        '--emo', '0',
        '--pretrained', None,
        '--fromcheckpoint', None,
        '--finetune',
        '--text',
        '--visual',
        '--resample',
        '--log_dir', 'logs',
        '--batch_size', '32',
        '--num_epochs', '50',
        '--optim', 'SGD',
        '--lr', '0.001',
        '--wd', '0.0005',
        '--dataset_root', '/tmp/dataset',
        '--dataset_name', 'MAFW',
        '--input_shape', '224', '224',
        '--downsample', '2',
        '--clip_len', '32',
        '--debug',
    ]
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
load_frames Ran
ran, honoured the contract we drafted
nickyfot/emoclip/DataLoaders/utils.py
code served (permissive licence) · get_code("a029d2b4dcbbafcd")
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 Tensor, ndim 4, dtype family float, shape (2, 3, 3, 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 os
import tempfile
from PIL import Image
import torch
from torchvision import transforms

torch.manual_seed(0)

# Create a temporary directory with sample image files
temp_dir = tempfile.mkdtemp()

# Create 2 small dummy RGB images and save them
for i in range(2):
    img = Image.new('RGB', (4, 3), color=(i*50, i*100, i*150))
    img.save(os.path.join(temp_dir, f'frame_{i:03d}.png'))

# Define a simple time_transform callable that takes a list of frames and returns a subset
def sample_time_transform(frames):
    return frames[:2]  # Just return first 2 frames

ARGS = {
    'folder_path': temp_dir,
    'time_transform': sample_time_transform
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — 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, 3, 3, 4) — shape (2, 3, 3, 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: none by the harness; any seed is in the setup block
feat_scatter Not yet run
unverified (harvested, no recorded run)
nickyfot/emoclip/utils.py
code served (permissive licence) · get_code("65dccfb689803260")
How it ran

no invocation recorded.

get_afew_loaders Not yet run
unverified (harvested, no recorded run)
nickyfot/emoclip/DataLoaders/get_loader.py
code served (permissive licence) · get_code("3e9c6de2f1b19fb6")
How it ran

no invocation recorded.

get_dfew_loaders Not yet run
unverified (harvested, no recorded run)
nickyfot/emoclip/DataLoaders/get_loader.py
code served (permissive licence) · get_code("2209cf8a59150766")
How it ran

no invocation recorded.

get_loaders Not yet run
unverified (harvested, no recorded run)
nickyfot/emoclip/DataLoaders/get_loader.py
code served (permissive licence) · get_code("368b5461230215d6")
How it ran

no invocation recorded.

load_annotation Not yet run
unverified (harvested, no recorded run)
nickyfot/emoclip/DataLoaders/utils.py
code served (permissive licence) · get_code("409d90a67f7048de")
How it ran

no invocation recorded.

load_video Not yet run
unverified (harvested, no recorded run)
nickyfot/emoclip/DataLoaders/utils.py
code served (permissive licence) · get_code("b7d567db51876aea")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Facial Expression Recognition (FER) is a crucial task in affective computing, but its conventional focus on the seven basic emotions limits its applicability to the complex and expanding emotional spectrum. To address the issue of new and unseen emotions present in dynamic in-the-wild FER, we propose a novel vision-language model that utilises sample-level text descriptions (i.e. captions of the context, expressions or emotional cues) as natural language supervision, aiming to enhance the learning of rich latent representations, for zero-shot classification. To test this, we evaluate using zero-shot classification of the model trained on sample-level descriptions on four popular dynamic FER datasets. Our findings show that this approach yields significant improvements when compared to baseline methods. Specifically, for zero-shot video FER, we outperform CLIP by over 10\% in terms of Weighted Average Recall and 5\% in terms of Unweighted Average Recall on several datasets. Furthermore, we evaluate the representations obtained from the network trained using sample-level descriptions on the downstream task of mental health symptom estimation, achieving performance comparable or superior to state-of-the-art methods and strong agreement with human experts. Namely, we achieve a Pearson's Correlation Coefficient of up to 0.85 on schizophrenia symptom severity estimation, which is comparable to human experts' agreement. The code is publicly available at: https://github.com/NickyFot/EmoCLIP.

For agents

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

get_harvested_code_for_paper("2310.16640")
get_code_for_paper("2310.16640")
have("2310.16640")

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

curl https://syntology.ai/api/ran/2310.16640.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.16640.svg)](https://syntology.ai/paper/2310.16640)

Connect an agent — have() is free.