SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.10437 · 2018

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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 4 have no contract verdict; 0 failures of our instrument; 1 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/1808.10437.json · badge: /api/ran/1808.10437.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
vt-vl-lab/iCAN canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
Get_next_sp Ran
ran on a synthesized input
vt-vl-lab/iCAN/lib/ult/ult.py
code served (permissive licence) · get_code("64a7d0d6f25b3640")
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 ndarray, ndim 3, dtype family float, shape (64, 64, 2) 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 numpy as np

# Construct valid arguments for Get_next_sp function
# The function takes human_box and object_box as parameters
# These should be bounding boxes represented as arrays/lists with 4 coordinates [x1, y1, x2, y3]

human_box = np.array([10, 20, 50, 80], dtype=float)
object_box = np.array([60, 30, 100, 90], dtype=float)

ARGS = {
    "human_box": human_box,
    "object_box": object_box
}
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 ndarray, ndim 3, dtype family float, shape (64, 64, 2) — shape (64, 64, 2) 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
apply_prior Ran
ran on a synthesized input
vt-vl-lab/iCAN/lib/ult/apply_prior.py
code served (permissive licence) · get_code("1a727db6002268bf")
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 3, dtype family float, shape (1, 1, 29) 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)

# The function accesses:
# - Object[4]: an integer indexing operation
# - prediction[0][0][...]: indexing into a 3D structure with integer indices

# Create Object as a list/tuple with at least 5 elements, with Object[4] being an integer
Object = [0, 1, 2, 3, 32, 5]  # Object[4] = 32

# Create prediction as a 3D tensor
# prediction[0][0][index] is accessed for indices up to 28
# Shape: (1, 1, 29) to accommodate all indices accessed (0-28)
prediction = torch.zeros(1, 1, 29)

ARGS = {
    "Object": Object,
    "prediction": prediction
}
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 Tensor, ndim 3, dtype family float, shape (1, 1, 29) — shape (1, 1, 29) 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
bb_IOU Ran
ran on a synthesized input
vt-vl-lab/iCAN/lib/ult/ult.py
code served (permissive licence) · get_code("a945b93e1e20006e")
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 float64, ndim 0, dtype family float; 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

# bb_IOU expects two bounding boxes, each with 4 coordinates: [xmin, ymin, xmax, ymax]
boxA = np.array([10.0, 20.0, 50.0, 60.0])
boxB = np.array([30.0, 40.0, 70.0, 80.0])

ARGS = {
    "boxA": boxA,
    "boxB": boxB,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
bbox_trans Ran
ran on a synthesized input
vt-vl-lab/iCAN/lib/ult/ult.py
code served (permissive licence) · get_code("e7e5af90a9931839")
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 2, dtype family float; 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

# Construct valid arguments for bbox_trans function
# The function takes:
# - human_box_ori: array-like bounding box for human
# - object_box_ori: array-like bounding box for object
# - ratio: string parameter (though it gets overridden in the function)
# - size: int parameter (default 64)

human_box_ori = np.array([10.0, 20.0, 50.0, 80.0])
object_box_ori = np.array([30.0, 40.0, 70.0, 90.0])
ratio = 'height'
size = 64

ARGS = {
    'human_box_ori': human_box_ori,
    'object_box_ori': object_box_ori,
    'ratio': ratio,
    'size': size
}
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, ndim 2, dtype family float — 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
download_file_from_google_drive Not yet run
unverified (harvested, no recorded run)
vt-vl-lab/iCAN/lib/ult/Download_data.py
code served (permissive licence) · get_code("dc1cace2b69b6f80")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 1 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
download_file_from_google_drive 5 other papers
5 later
1811.08264 (2018-11)
Transferable Interactiveness Knowledge for Human-Object Interaction Detection
1910.10261 (2019-10)
QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
Bae_Multi-View_Depth_Estimation_by_Fusing_Single-View_Depth_Probability_With_Multi-View_CVPR_2022_paper (2022 (year only))
Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
and 2 more not named here
apply_prior 1 other paper
1 later
1811.08264 (2018-11)
Transferable Interactiveness Knowledge for Human-Object Interaction Detection
bb_IOU 1 other paper
1 later
2004.08154 (2020-04)
Detailed 2D-3D Joint Representation for Human-Object Interaction
bbox_trans 1 other paper
1 later
2004.08154 (2020-04)
Detailed 2D-3D Joint Representation for Human-Object Interaction

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

Recent years have witnessed rapid progress in detecting and recognizing individual object instances. To understand the situation in a scene, however, computers need to recognize how humans interact with surrounding objects. In this paper, we tackle the challenging task of detecting human-object interactions (HOI). Our core idea is that the appearance of a person or an object instance contains informative cues on which relevant parts of an image to attend to for facilitating interaction prediction. To exploit these cues, we propose an instance-centric attention module that learns to dynamically highlight regions in an image conditioned on the appearance of each instance. Such an attention-based network allows us to selectively aggregate features relevant for recognizing HOIs. We validate the efficacy of the proposed network on the Verb in COCO and HICO-DET datasets and show that our approach compares favorably with the state-of-the-arts.

For agents

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

get_harvested_code_for_paper("1808.10437")
get_code_for_paper("1808.10437")
have("1808.10437")

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

curl https://syntology.ai/api/ran/1808.10437.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.10437.svg)](https://syntology.ai/paper/1808.10437)

Connect an agent — have() is free.