SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.08877 · ECCV · 2024

EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding

Wei-Shi Zheng, An-Lan Wang, Ling-An Zeng, Yuan-Ming Li, Wei-Jin Huang, Jing-Ke Meng

arXiv · PDF · Open in the Atlas

Code that ran

9 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; 8 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/2406.08877.json · badge: /api/ran/2406.08877.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
iSEE-Laboratory/EgoExo-Fitness canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
isee-laboratory/egoexo-fitness canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_cls_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iSEE-Laboratory/EgoExo-Fitness/CVSV_benchmark/utils/loss.py
code served (permissive licence) · get_code("39a90fc9acca4b61")
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 0, dtype family float, shape () as a later run recorded it. 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, 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
from torch.nn import CrossEntropyLoss

torch.manual_seed(0)

# Build pred tensor: shape (batch_size, num_classes)
# The function uses pred.transpose(0, 1)[labels] and pred[i, y+1:]
# so we need batch_size >= 2 and num_classes >= 2
batch_size = 2
num_classes = 4
pred = torch.randn(batch_size, num_classes)

# Build labels tensor: shape (batch_size,)
# labels should contain valid class indices (0 to num_classes-1)
labels = torch.tensor([0, 2])

ARGS = {
    "pred": pred,
    "labels": labels,
    "use_cosface": False
}
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 0, dtype family float, 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
correct_instance Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EgoExo-Fitness/GEV_benchmark/metrics.py
code served (permissive licence) · get_code("ce0528e216133256")
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 torch
import numpy as np

torch.manual_seed(0)

# Create small tensors for the function
# y and y_hat are probability tensors that will be compared
# They need to be batch_size x max_sequence_length
batch_size = 2
max_seq_len = 4

y = torch.rand(batch_size, max_seq_len)
y_hat = torch.rand(batch_size, max_seq_len)

# l_len contains the actual lengths for each sample in the batch
# Different sizes to distinguish from batch dimension
l_len = torch.tensor([3, 2])

ARGS = {
    "y": y,
    "y_hat": y_hat,
    "l_len": l_len,
    "return_correct_list": False
}
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 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
generate_sent_masks Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EgoExo-Fitness/CVSV_benchmark/utils/loss.py
code served (permissive licence) · get_code("477aef9087507741")
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 2, dtype family float, shape (2, 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)

batch_size = 2
max_seq_length = 4
source_lengths = torch.tensor([2, 3], dtype=torch.float)

ARGS = {
    "batch_size": batch_size,
    "max_seq_length": max_seq_length,
    "source_lengths": source_lengths,
}
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 2, dtype family float, shape (2, 4) — shape (2, 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_conv_params Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EgoExo-Fitness/GEV_benchmark/models/I3D.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from plrbear/pecop, is pointer only (licence: NONE) · get_code("0b19df9669841d40")
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 plrbear/pecop, 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_padding_shape Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iSEE-Laboratory/EgoExo-Fitness/GEV_benchmark/models/I3D.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from seominseok0429/inception-I3D-NON-LOCAL, is pointer only (licence: NONE) · get_code("45cc344e60f640a1")
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 seominseok0429/inception-I3D-NON-LOCAL, 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_rotate_degree Ran
ran, honoured the contract we drafted
isee-laboratory/egoexo-fitness/features/get_frame_features_CLIP.py
code served (permissive licence) · get_code("9f8affbde4fb584c")
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 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 torch

torch.manual_seed(0)

# The function takes a 'view' parameter and looks it up in a dictionary
# Valid views are: 'ego_m', 'ego_r', 'ego_l', 'exo_r', 'exo_l', 'exo_m'
# We'll test with one of the valid view strings

ARGS = {
    'view': 'ego_m'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
simplify_padding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iSEE-Laboratory/EgoExo-Fitness/GEV_benchmark/models/I3D.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from seominseok0429/inception-I3D-NON-LOCAL, is pointer only (licence: NONE) · get_code("81ec17604dc709cc")
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 seominseok0429/inception-I3D-NON-LOCAL, 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.

update_logit_scale Ran
ran; our contract draft was wrong, not the code
iSEE-Laboratory/EgoExo-Fitness/CVSV_benchmark/models/build_model.py
code served (permissive licence) · get_code("c3fda49fe8d9c72f")
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 SimpleModel. 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.logit_scale = nn.Parameter(torch.tensor(1.0))
        self.logit_scale2 = nn.Parameter(torch.tensor(2.0))

class WrappedModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.module = SimpleModel()

model = SimpleModel()

ARGS = {
    "model": model
}
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 SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
viterbi Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iSEE-Laboratory/EgoExo-Fitness/CVSV_benchmark/utils/loss.py
code served (permissive licence) · get_code("b60129c87f00c33d")
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 numpy as np

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

# Define parameters for the viterbi function
K = 4  # Number of hidden states
M = 3  # Number of observation symbols
T = 5  # Length of observation sequence

# Create observation sequence (integers from 0 to M-1)
y = np.array([0, 1, 2, 1, 0], dtype=int)

# Create state transition matrix A (K x K)
# Each row sums to 1 (valid probability distribution)
A = np.array([
    [0.7, 0.2, 0.05, 0.05],
    [0.1, 0.6, 0.2, 0.1],
    [0.05, 0.15, 0.7, 0.1],
    [0.2, 0.2, 0.2, 0.4]
], dtype=float)

# Create emission matrix B (K x M)
# Each row sums to 1 (valid probability distribution)
B = np.array([
    [0.5, 0.3, 0.2],
    [0.2, 0.5, 0.3],
    [0.3, 0.2, 0.5],
    [0.4, 0.4, 0.2]
], dtype=float)

# Create initial state probabilities Pi (K,)
# Sums to 1 (valid probability distribution)
Pi = np.array([0.25, 0.25, 0.25, 0.25], dtype=float)

ARGS = {
    'y': y,
    'A': A,
    'B': B,
    'Pi': Pi
}
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 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

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, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 1 later) and 4 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
get_padding_shape 9 other papers
8 dated earlier, 1 later
1705.07750 (2017-05)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
1711.07971 (2017-11)
Non-local Neural Networks
1912.06430 (2019-12)
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
and 6 more not named here
simplify_padding 7 other papers
7 dated earlier
1705.07750 (2017-05)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
1711.07971 (2017-11)
Non-local Neural Networks
Ding_Motion-Aware_Contrastive_Video_Representation_Learning_via_Foreground-Background_Merging_CVPR_2022_paper (2022 (year only))
Motion-aware Contrastive Video Representation Learning via Foreground-background Merging
and 4 more not named here
get_conv_params 5 other papers
5 dated earlier
1705.07750 (2017-05)
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
1711.07971 (2017-11)
Non-local Neural Networks
2204.03646 (2022-04)
FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment
and 2 more not named here
generate_sent_masks 1 other paper
1 dated earlier
2303.12370 (2023-03)
Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos
viterbi 1 other paper
1 dated earlier
2303.12370 (2023-03)
Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos

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

We present EgoExo-Fitness, a new full-body action understanding dataset, featuring fitness sequence videos recorded from synchronized egocentric and fixed exocentric (third-person) cameras. Compared with existing full-body action understanding datasets, EgoExo-Fitness not only contains videos from first-person perspectives, but also provides rich annotations. Specifically, two-level temporal boundaries are provided to localize single action videos along with sub-steps of each action. More importantly, EgoExo-Fitness introduces innovative annotations for interpretable action judgement-including technical keypoint verification, natural language comments on action execution, and action quality scores. Combining all of these, EgoExo-Fitness provides new resources to study egocentric and exocentric full-body action understanding across dimensions of "what", "when", and "how well". To facilitate research on egocentric and exocentric full-body action understanding, we construct benchmarks on a suite of tasks (i.e., action classification, action localization, cross-view sequence verification, cross-view skill determination, and a newly proposed task of guidance-based execution verification), together with detailed analysis. Data and code are available at https://github.com/iSEE-Laboratory/EgoExo-Fitness/tree/main.

For agents

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

get_harvested_code_for_paper("2406.08877")
get_code_for_paper("2406.08877")
have("2406.08877")

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

curl https://syntology.ai/api/ran/2406.08877.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.08877.svg)](https://syntology.ai/paper/2406.08877)

Connect an agent — have() is free.