SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.14023 · 2020

Learning Human-Object Interaction Detection using Interaction Points

arXiv · PDF · Open in the Atlas

Code that ran

7 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, 1 violated it and 1 has no contract verdict; 4 failures of our instrument; 3 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/2003.14023.json · badge: /api/ran/2003.14023.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
vaesl/IP-Net canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
apply_prior Ran
ran on a synthesized input
vaesl/IP-Net/src/apply_prior.py
code served (permissive licence) · get_code("b9d92be6fa999216")
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 list, ndim 1, 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 torch
import numpy as np

torch.manual_seed(0)

# Create Object - needs to be indexable at position 4
# Object[4] is checked against various integer values throughout the function
Object = [0, 1, 2, 3, 32, 5, 6]  # Object[4] = 32

# Create prediction - needs to be a list/array with indices 0-28 that can be set to 0
# The function accesses indices: 0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 15, 16, 19, 20, 21, 24, 26, 28
prediction = [1.0] * 29  # Initialize with non-zero values

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 list, ndim 1, dtype family float — a list 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
clip_xyxy_to_image Ran
ran, violated the contract we drafted
vaesl/IP-Net/src/vsrl_eval.py
code served (permissive licence) · get_code("3dc1dc492dbbbf13")
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 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

# The function clips bounding box coordinates (x1, y1, x2, y2) to image boundaries
# Parameters: x1, y1, x2, y2 are coordinate values, height and width are image dimensions

# Create sample bounding box coordinates that may be outside image bounds
x1 = np.array([-5.0, 100.0])
y1 = np.array([10.0, -2.0])
x2 = np.array([50.0, 200.0])
y2 = np.array([60.0, 150.0])

# Image dimensions
height = 100
width = 150

ARGS = {
    "x1": x1,
    "y1": y1,
    "x2": x2,
    "y2": y2,
    "height": height,
    "width": width,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
compute_bin_loss Ran
ran; our contract draft was wrong, not the code
vaesl/IP-Net/src/lib/models/losses.py
code served (permissive licence) · get_code("65d7a40d70c53ed9")
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. 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 torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Analyze the function:
# - output: passed to F.cross_entropy, so should be (batch_size, num_classes) logits
# - target: passed to F.cross_entropy, so should be (batch_size,) with class indices
# - mask: has .expand_as(output) called on it, then .float() is called
#   mask should be broadcastable to output shape

batch_size = 2
num_classes = 4

# output: logits tensor (batch_size, num_classes)
output = torch.randn(batch_size, num_classes)

# target: class indices (batch_size,) with values in [0, num_classes)
target = torch.tensor([0, 2], dtype=torch.long)

# mask: should be broadcastable to output shape
# Can be a single value or smaller tensor that expands
mask = torch.ones(batch_size, 1)

ARGS = {
    "output": output,
    "target": target,
    "mask": mask,
}
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
compute_res_loss Ran
ran; our contract draft was wrong, not the code
vaesl/IP-Net/src/lib/models/losses.py
code served (permissive licence) · get_code("7df13fb9e54d592b")
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. 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for output and target
# batch_size=2, feature_dim=4
output = torch.randn(2, 4)
target = torch.randn(2, 4)

ARGS = {
    'output': output,
    'target': target,
}
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
compute_rot_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vaesl/IP-Net/src/lib/models/losses.py
code served (permissive licence) · get_code("8accefa95d8419ec")
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. 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 torch.nn.functional as F

torch.manual_seed(0)

# Create output tensor: shape (batch_size, 8) since output.view(-1, 8) is called
output = torch.randn(2, 8)

# Create target_bin tensor: shape (batch_size, 2) since target_bin.view(-1, 2) is called
# Values should be 0 or 1 for cross_entropy classification
target_bin = torch.tensor([[1, 0], [0, 1]], dtype=torch.long)

# Create target_res tensor: shape (batch_size, 2) since target_res.view(-1, 2) is called
# These are angle values that will have sin/cos applied
target_res = torch.randn(2, 2)

# Create mask tensor: shape (batch_size, 1) since mask.view(-1, 1) is called
# Mask should be binary or float values
mask = torch.tensor([[1], [1]], dtype=torch.float32)

ARGS = {
    'output': output,
    'target_bin': target_bin,
    'target_res': target_res,
    'mask': mask
}
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
get_overlap Ran
ran, honoured the contract we drafted
vaesl/IP-Net/src/vsrl_eval.py
code served (permissive licence) · get_code("d5a0b6aba0d66951")
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 ndarray, ndim 1, dtype family float, shape (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

# Create sample bounding boxes in format [xmin, ymin, xmax, ymax]
boxes = np.array([
    [10.0, 20.0, 50.0, 60.0],
    [30.0, 40.0, 70.0, 80.0]
], dtype=np.float32)

# Create a reference box in format [xmin, ymin, xmax, ymax]
ref_box = np.array([25.0, 35.0, 65.0, 75.0], dtype=np.float32)

ARGS = {
    "boxes": boxes,
    "ref_box": ref_box
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (2,) — shape (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
voc_ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vaesl/IP-Net/src/vsrl_eval.py
code served (permissive licence) · get_code("7c16bfea33d37328")
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 float64, ndim 0, dtype family float, 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 numpy as np

# voc_ap expects:
# - rec: array of recall values (monotonically increasing, values in [0,1])
# - prec: array of precision values (values in [0,1])
# Both should be 1D numpy arrays of the same length

# Create sample recall and precision arrays
# These represent typical precision-recall curve points
rec = np.array([0.1, 0.3, 0.5, 0.7, 0.9])
prec = np.array([0.95, 0.85, 0.75, 0.6, 0.4])

ARGS = {
    "rec": rec,
    "prec": prec,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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
DataParallel Not yet run
unverified (harvested, no recorded run)
vaesl/IP-Net/src/lib/models/data_parallel.py
code served (permissive licence) · get_code("ddb5a5004c8da97a")
How it ran

no invocation recorded.

ctdet_decode Not yet run
unverified (harvested, no recorded run)
vaesl/IP-Net/src/lib/models/decode.py
code served (permissive licence) · get_code("6992ab8e41a81b54")
How it ran

no invocation recorded.

data_parallel Not yet run
unverified (harvested, no recorded run)
vaesl/IP-Net/src/lib/models/data_parallel.py
code served (permissive licence) · get_code("61bf3906cbd2ee87")
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, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 8 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.

FunctionAlso present inEarliest-datedOthers named
data_parallel 9 other papers
7 dated earlier, 2 later
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1808.01244 (2018-08)
CornerNet: Detecting Objects as Paired Keypoints
and 6 more not named here
compute_bin_loss 6 other papers
3 dated earlier, 3 later
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1904.07850 (2019-04)
Objects as Points
2001.03343 (2020-01)
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
and 3 more not named here
compute_res_loss 6 other papers
3 dated earlier, 3 later
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1904.07850 (2019-04)
Objects as Points
2001.03343 (2020-01)
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
and 3 more not named here
compute_rot_loss 6 other papers
3 dated earlier, 3 later
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1904.07850 (2019-04)
Objects as Points
2001.03343 (2020-01)
RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving
and 3 more not named here
DataParallel 5 other papers
3 dated earlier, 2 later
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1904.07850 (2019-04)
Objects as Points
2001.04608 (2020-01)
Actions as Moving Points
and 2 more not named here
voc_ap 5 other papers
1 dated earlier, 4 later
1505.04474 (2015-05)
Visual Semantic Role Labeling
2004.00436 (2020-04)
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
2007.12107 (2020-07)
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
and 2 more not named here
get_overlap 3 other papers
2 dated earlier, 1 later
1505.04474 (2015-05)
Visual Semantic Role Labeling
1909.08453 (2019-09)
Pose-aware Multi-level Feature Network for Human Object Interaction Detection
2112.08647 (2021-12)
QAHOI: Query-Based Anchors for Human-Object Interaction Detection
clip_xyxy_to_image 2 other papers
1 dated earlier, 1 later
1505.04474 (2015-05)
Visual Semantic Role Labeling
2112.08647 (2021-12)
QAHOI: Query-Based Anchors for Human-Object Interaction Detection

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

Understanding interactions between humans and objects is one of the fundamental problems in visual classification and an essential step towards detailed scene understanding. Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them. Most existing HOI detection approaches are instance-centric where interactions between all possible human-object pairs are predicted based on appearance features and coarse spatial information. We argue that appearance features alone are insufficient to capture complex human-object interactions. In this paper, we therefore propose a novel fully-convolutional approach that directly detects the interactions between human-object pairs. Our network predicts interaction points, which directly localize and classify the inter-action. Paired with the densely predicted interaction vectors, the interactions are associated with human and object detections to obtain final predictions. To the best of our knowledge, we are the first to propose an approach where HOI detection is posed as a keypoint detection and grouping problem. Experiments are performed on two popular benchmarks: V-COCO and HICO-DET. Our approach sets a new state-of-the-art on both datasets. Code is available at https://github.com/vaesl/IP-Net.

For agents

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

get_harvested_code_for_paper("2003.14023")
get_code_for_paper("2003.14023")
have("2003.14023")

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

curl https://syntology.ai/api/ran/2003.14023.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.14023.svg)](https://syntology.ai/paper/2003.14023)

Connect an agent — have() is free.