SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.05269 · CVPR · 2021

Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection

Dacheng Tao, Changxing Ding, Xubin Zhong, Xian Qu

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 3 failures of our instrument; 5 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/2104.05269.json · badge: /api/ran/2104.05269.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
SherlockHolmes221/GGNet community
Papers with Code archive
4 ran · 5 no recorded run
FunctionStatusWhere it lives
make_hg_layer Ran
ran; our contract draft was wrong, not the code
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("4e867f9bb8fa3d46")
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 Sequential. 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)

ARGS = {
    'kernel': 3,
    'dim0': 4,
    'dim1': 8,
    'mod': 2,
    'layer': nn.Conv2d,
    'kwargs': {}
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make_kp_refine_layer Ran
ran; our contract draft was wrong, not the code
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("1920cb463dc81f29")
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 Sequential. 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
import math

torch.manual_seed(0)

ARGS = {
    'cnv_dim': 64,
    'out_dim': 16,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make_merge_layer Ran
ran; our contract draft was wrong, not the code
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("07caa911e46fcb23")
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 MergeUp. 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)

ARGS = {
    "dim": 4
}
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 MergeUp — a MergeUp output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MergeUp 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
make_pool_layer Ran
ran, honoured the contract we drafted
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("c2515898895b1abb")
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 Sequential. 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 make_pool_layer takes a single parameter 'dim'
# Looking at the body, it simply returns nn.Sequential()
# So 'dim' should be an integer representing a dimension size

ARGS = {
    "dim": 4
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
DCN_O1 Not yet run
unverified (harvested, no recorded run)
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("bd63aea09b264bb4")
How it ran

no invocation recorded.

DCNv2 Not yet run
unverified (harvested, no recorded run)
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("3cf5dcc1af6b904d")
How it ran

no invocation recorded.

HourglassNet Not yet run
unverified (harvested, no recorded run)
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("b0e1c96f1bffef2e")
How it ran

no invocation recorded.

exkp Not yet run
unverified (harvested, no recorded run)
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("917f6dc126915c11")
How it ran

no invocation recorded.

kp_module Not yet run
unverified (harvested, no recorded run)
SherlockHolmes221/GGNet/src/lib/models/networks/ggnet_hourglass_s1.py
code served (permissive licence) · get_code("1a25f1bbd0c62db2")
How it ran

no invocation recorded.

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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
make_pool_layer
brick of this paper's assembly: helper
3 other papers
3 dated earlier
1808.01244 (2018-08)
CornerNet: Detecting Objects as Paired Keypoints
1901.08043 (2019-01)
Bottom-up Object Detection by Grouping Extreme and Center Points
1904.08900 (2019-04)
CornerNet-Lite: Efficient Keypoint Based Object Detection
make_merge_layer
brick of this paper's assembly: helper
2 other papers
2 dated earlier
1808.01244 (2018-08)
CornerNet: Detecting Objects as Paired Keypoints
1904.08189 (2019-04)
CenterNet: Keypoint Triplets for Object Detection
DCNv2
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2103.13164 (2021-03)
M3DSSD: Monocular 3D Single Stage Object Detector

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

Modern human-object interaction (HOI) detection approaches can be divided into one-stage methods and twostage ones. One-stage models are more efficient due to their straightforward architectures, but the two-stage models are still advantageous in accuracy. Existing one-stage models usually begin by detecting predefined interaction areas or points, and then attend to these areas only for interaction prediction; therefore, they lack reasoning steps that dynamically search for discriminative cues. In this paper, we propose a novel one-stage method, namely Glance and Gaze Network (GGNet), which adaptively models a set of action-aware points (ActPoints) via glance and gaze steps. The glance step quickly determines whether each pixel in the feature maps is an interaction point. The gaze step leverages feature maps produced by the glance step to adaptively infer ActPoints around each pixel in a progressive manner. Features of the refined ActPoints are aggregated for interaction prediction. Moreover, we design an action-aware approach that effectively matches each detected interaction with its associated human-object pair, along with a novel hard negative attentive loss to improve the optimization of GGNet. All the above operations are conducted simultaneously and efficiently for all pixels in the feature maps. Finally, GGNet outperforms state-of-the-art methods by significant margins on both V-COCO and HICO-DET benchmarks. Code of GGNet is available at https: //github.com/SherlockHolmes221/GGNet.

For agents

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

get_harvested_code_for_paper("2104.05269")
get_code_for_paper("2104.05269")
have("2104.05269")

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

curl https://syntology.ai/api/ran/2104.05269.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.05269.svg)](https://syntology.ai/paper/2104.05269)

Connect an agent — have() is free.