SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1811.12596 · 2018

Parsing R-CNN for Instance-Level Human Analysis

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 4 have no contract verdict; 1 failure 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/1811.12596.json · badge: /api/ran/1811.12596.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
soeaver/Parsing-R-CNN canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
soeaver/RP-R-CNN community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
expand_boxes Ran
ran on a synthesized input
soeaver/Parsing-R-CNN/rcnn/modeling/parsing_rcnn/inference.py
code served (permissive licence) · get_code("eb0a4da500640f09")
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 2, dtype family float, shape (3, 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 numpy as np

# Create a small array of bounding boxes
# boxes should be shape (N, 4) where each row is [x1, y1, x2, y2]
# Using 3 boxes for variety
boxes = np.array([
    [10.0, 20.0, 50.0, 80.0],
    [15.0, 25.0, 60.0, 90.0],
    [5.0, 10.0, 40.0, 70.0]
], dtype=np.float32)

h = 100
w = 120

ARGS = {
    "boxes": boxes,
    "h": h,
    "w": w
}
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 2, dtype family float, shape (3, 4) — shape (3, 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
fast_hist Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
soeaver/Parsing-R-CNN/rcnn/modeling/parsing_rcnn/loss.py
code served (permissive licence) · get_code("d86fb168246b16a4")
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 2, dtype family int, shape (4, 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 numpy as np

# Analyze the function:
# - a: array-like, used with >= 0, < n comparisons, and .astype(int)
# - b: array-like, same shape as a, used in indexing
# - n: int, used as upper bound and for bincount minlength

# Create small numpy arrays for a and b
a = np.array([0, 1, 2, 3, 1, 2], dtype=np.int32)
b = np.array([0, 1, 2, 0, 1, 2], dtype=np.int32)
n = 4

ARGS = {
    "a": a,
    "b": b,
    "n": n
}
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 2, dtype family int, shape (4, 4) — shape (4, 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
make_divisible Ran
ran, honoured the contract we drafted
soeaver/RP-R-CNN/models/imagenet/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from rlqja1107/torch-LLM4SGG, is pointer only (licence: NONE) · get_code("3592f11df8bd6c1d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rlqja1107/torch-LLM4SGG, 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.

make_fc Ran
ran on a synthesized input
soeaver/Parsing-R-CNN/utils/net.py
code served (permissive licence) · get_code("90b6a6d04401dffb")
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 Linear. 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_in": 4,
    "hidden_dim": 8,
    "use_bn": False,
    "use_gn": False,
    "eps": 1e-05,
    "gn_group": 32,
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
model_se Ran
ran on a synthesized input
soeaver/Parsing-R-CNN/models/imagenet/mobilenet_v2.py
code served (permissive licence) · get_code("5bb786b973e17574")
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. 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 copy

torch.manual_seed(0)

# Based on the function body, ls_cfg is a nested list structure:
# - Outer list of layer configs
# - Each layer config is an iterable of layer specifications
# - Each layer specification is indexable (list/tuple) with at least 3 elements
# - Element at index [2] is set to se_ratio

# Creating a minimal valid ls_cfg structure
# This represents layer configurations where each layer has multiple specs
# and each spec has at least 3 elements (index 0, 1, 2)

ls_cfg = [
    [
        [1, 2, 0.5, "extra"],  # layer config 0, spec 0
        [3, 4, 0.5, "extra"],  # layer config 0, spec 1
    ],
    [
        [5, 6, 0.5],  # layer config 1, spec 0
        [7, 8, 0.5],  # layer config 1, spec 1
        [9, 10, 0.5],  # layer config 1, spec 2
    ],
]

se_ratio = 0.25

ARGS = {
    "ls_cfg": ls_cfg,
    "se_ratio": se_ratio,
}
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 list — a list 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
parsing_on_boxes Ran
ran on a synthesized input
soeaver/Parsing-R-CNN/rcnn/modeling/parsing_rcnn/loss.py
code served (permissive licence) · get_code("4c828714c7062f06")
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 int, shape (2, 16, 12) 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)

# parsing: tensor of shape (batch_size, height, width) containing parsing maps
parsing = torch.randint(0, 10, (2, 32, 32), dtype=torch.float32)

# rois: tensor of shape (batch_size, 4) containing bounding boxes [xmin, ymin, xmax, ymax]
rois = torch.tensor([
    [4.0, 6.0, 20.0, 24.0],
    [8.0, 10.0, 28.0, 30.0]
], dtype=torch.float32)

# heatmap_size: tuple (height, width) for resizing
heatmap_size = (16, 12)

ARGS = {
    'parsing': parsing,
    'rois': rois,
    'heatmap_size': heatmap_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 int, shape (2, 16, 12) — shape (2, 16, 12) 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
cal_one_mean_iou Not yet run
unverified (harvested, no recorded run)
soeaver/Parsing-R-CNN/rcnn/modeling/parsing_rcnn/loss.py
code served (permissive licence) · get_code("336b9f236eb0fd11")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
fast_hist 12 other papers
5 dated earlier, 7 later
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1702.01105 (2017-02)
Joint 2D-3D-Semantic Data for Indoor Scene Understanding
1806.07373 (2018-06)
Few-Shot Segmentation Propagation with Guided Networks
and 9 more not named here
make_divisible 8 other papers
1 dated earlier, 7 later · 1 only as an assembly brick
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
2209.12213 (2022-09)
ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement
2305.18980 (2023-05)
Multi-modal Queried Object Detection in the Wild
and 5 more not named here

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

Instance-level human analysis is common in real-life scenarios and has multiple manifestations, such as human part segmentation, dense pose estimation, human-object interactions, etc. Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance. In this paper, we present an end-to-end pipeline for solving the instance-level human analysis, named Parsing R-CNN. It processes a set of human instances simultaneously through comprehensive considering the characteristics of region-based approach and the appearance of a human, thus allowing representing the details of instances. Parsing R-CNN is very flexible and efficient, which is applicable to many issues in human instance analysis. Our approach outperforms all state-of-the-art methods on CIHP (Crowd Instance-level Human Parsing), MHP v2.0 (Multi-Human Parsing) and DensePose-COCO datasets. Based on the proposed Parsing R-CNN, we reach the 1st place in the COCO 2018 Challenge DensePose Estimation task. Code and models are public available.

For agents

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

get_harvested_code_for_paper("1811.12596")
get_code_for_paper("1811.12596")
have("1811.12596")

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

curl https://syntology.ai/api/ran/1811.12596.json

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

[![Syntology run record](https://syntology.ai/api/ran/1811.12596.svg)](https://syntology.ai/paper/1811.12596)

Connect an agent — have() is free.