SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.11646 · ICCV · 2021

Hand Image Understanding via Deep Multi-Task Learning

Ji Liu, Xiong Zhang, Cheng Yang, Jianchao Tan, Lei Wang, Hongmin Xu, Hongsheng Huang, Guozhu Peng

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2107.11646.json · badge: /api/ran/2107.11646.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
MandyMo/HIU-DMTL marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_backbone Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MandyMo/HIU-DMTL/hand_detection/model/model.py
code served (permissive licence) · get_code("c72842844140634a")
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)

# The function get_backbone takes s_backbone and pretrained as parameters
# It will attempt to import and instantiate resnet18
# Since we can't actually import a real resnet, we need to mock it

# Create a mock resnet18 class
class MockResNet18(nn.Module):
    def __init__(self, pretrained=True):
        super().__init__()
        self.pretrained = pretrained
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
        self.layer1 = nn.Sequential(nn.Conv2d(64, 64, 3, padding=1))
        self.layer2 = nn.Sequential(nn.Conv2d(64, 128, 3, padding=1))
        self.layer3 = nn.Sequential(nn.Conv2d(128, 256, 3, padding=1))
        self.layer4 = nn.Sequential(nn.Conv2d(256, 512, 3, padding=1))
    
    def forward(self, x):
        return x

# Mock the resnet module in sys.modules so import works
import sys
class MockResNetModule:
    @staticmethod
    def resnet18(pretrained=True):
        return MockResNet18(pretrained=pretrained)

sys.modules['resnet'] = MockResNetModule()

# Define ARGS with valid arguments for get_backbone
ARGS = {
    's_backbone': 'resnet18',
    'pretrained': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
resnet, 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
Model Not yet run
unverified (harvested, no recorded run)
MandyMo/HIU-DMTL/hand_detection/model/model.py
code served (permissive licence) · get_code("fdce4968186f142a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Analyzing and understanding hand information from multimedia materials like images or videos is important for many real world applications and remains active in research community. There are various works focusing on recovering hand information from single image, however, they usually solve a single task, for example, hand mask segmentation, 2D/3D hand pose estimation, or hand mesh reconstruction and perform not well in challenging scenarios. To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks. To achieve this goal, a cascaded multitask learning (MTL) backbone is designed to estimate the 2D heat maps, to learn the segmentation mask, and to generate the intermediate 3D information encoding, followed by a coarse-to-fine learning paradigm and a self-supervised learning strategy. Qualitative experiments demonstrate that our approach can recover reasonable mesh representations even in challenging situations. Quantitatively, our method significantly outperforms the state-of-the-art approaches on various widely-used datasets, in terms of diverse evaluation metrics https://github.com/MandyMo/HIU-DMTL.

For agents

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

get_harvested_code_for_paper("2107.11646")
get_code_for_paper("2107.11646")
have("2107.11646")

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

curl https://syntology.ai/api/ran/2107.11646.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.11646.svg)](https://syntology.ai/paper/2107.11646)

Connect an agent — have() is free.