SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.12115 · 2021

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

arXiv · PDF · Open in the Atlas

Code that ran

15 of 18 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; 4 honoured the contract we drafted, 1 violated it and 5 have no contract verdict; 5 failures of our instrument; 3 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/2103.12115.json · badge: /api/ran/2103.12115.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
amathislab/poet canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
pranoyr/pose-estimation-with-transformers community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
box_cxcywh_to_xyxy Ran
ran, honoured the contract we drafted
amathislab/poet/util/box_ops.py
code served (permissive licence) · get_code("e0a06ded5d4f6c3c")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# The function expects a tensor x with shape (..., 4) where the last dimension
# contains [center_x, center_y, width, height] values
# It unbinds the last dimension and converts to [x_min, y_min, x_max, y_max]

x = torch.tensor([
    [10.0, 20.0, 4.0, 6.0],
    [30.0, 40.0, 8.0, 10.0]
])

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
box_cxcywh_to_xyxy Ran
ran; our contract draft was wrong, not the code
pranoyr/pose-estimation-with-transformers/inference.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from ut-vision/ActionVOS, is pointer only (licence: NONE) · get_code("ef1a3e10a9dbf4a9")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, pranoyr/pose-estimation-with-transformers, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

box_iou Ran
ran, honoured the contract we drafted
amathislab/poet/util/box_ops.py
code served (permissive licence) · get_code("ce749f837424dd8c")
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 3, 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
from torchvision.ops.boxes import box_area

torch.manual_seed(0)

# Create two sets of bounding boxes in format [x1, y1, x2, y2]
# boxes1: 2 boxes
# boxes2: 3 boxes
boxes1 = torch.tensor([
    [0.0, 0.0, 2.0, 2.0],
    [1.0, 1.0, 3.0, 3.0]
], dtype=torch.float32)

boxes2 = torch.tensor([
    [0.0, 0.0, 1.0, 1.0],
    [1.5, 1.5, 2.5, 2.5],
    [2.0, 2.0, 4.0, 4.0]
], dtype=torch.float32)

ARGS = {
    "boxes1": boxes1,
    "boxes2": boxes2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
box_xyxy_to_cxcywh Ran
ran, honoured the contract we drafted
amathislab/poet/util/box_ops.py
code served (permissive licence) · get_code("031b02fb990284ba")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# The function expects a tensor x with shape (..., 4) where the last dimension
# contains [x0, y0, x1, y1] coordinates (xyxy format)
# It unbinds the last dimension and converts to center-xy, width, height format

x = torch.tensor([
    [10.0, 20.0, 30.0, 40.0],
    [5.0, 15.0, 25.0, 35.0]
])

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
build_JointDist Ran
ran on a synthesized input
amathislab/poet/util/kpts_ops.py
code served (permissive licence) · get_code("0561e24134a71f2d")
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 2, dtype family float, shape (2, 19) 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

torch.manual_seed(0)

SKELETON = [[16, 14], [14, 12], [17, 15], [15, 13], [12, 13], [6, 12], [7, 13], [6, 7], [6, 8], [7, 9], [8, 10], [9, 11], [2, 3], [1, 2], [1, 3], [2, 4], [3, 5], [4, 6], [5, 7]]

# Test with len(kpts) == 36 case (simplest)
# This expects kpts to have shape (batch_size, 36) where 36 = 18 joints * 2 coordinates
kpts = torch.randn(2, 36)

ARGS = {
    "kpts": kpts
}
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 2, dtype family float, shape (2, 19) — shape (2, 19) 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
build_SPR Ran
ran on a synthesized input
amathislab/poet/util/kpts_ops.py
code served (permissive licence) · get_code("83c26ff1ecd129cb")
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 2, dtype family float, shape (2, 9) 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

torch.manual_seed(0)

# Construct tensors
# keypoints: shape (batch_size, num_features) where num_features is divisible by 3
# The function accesses indices 0::3, 1::3 (x, y coordinates repeated)
keypoints = torch.randn(2, 9)  # batch=2, 9 features (3 keypoints with x,y,z each)

# center: shape (batch_size, 2) with center[:, 0] and center[:, 1] accessed
center = torch.randn(2, 2)  # batch=2, center has x and y coordinates

ARGS = {
    "keypoints": keypoints,
    "center": center,
}
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 2, dtype family float, shape (2, 9) — shape (2, 9) 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
build_matcher Ran
ran; our contract draft was wrong, not the code
pranoyr/pose-estimation-with-transformers/models/matcher.py
pointer only (licence: Apache-2.0) · get_code("35da0de247efc158")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, pranoyr/pose-estimation-with-transformers, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

convert_to_xywh Ran
ran, honoured the contract we drafted
amathislab/poet/datasets/coco_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("f31a58bf6457ced5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

crop Ran
ran on a synthesized input
amathislab/poet/datasets/transforms.py
code served (permissive licence) · get_code("57de633f747522fc")
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 torchvision.transforms.functional as F
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a small PIL image for testing
image = Image.new('RGB', (100, 100), color='red')

# Create target dict with boxes and keypoints
target = {
    'boxes': torch.tensor([
        [10.0, 10.0, 50.0, 50.0],
        [30.0, 30.0, 80.0, 80.0]
    ], dtype=torch.float32),
    'labels': torch.tensor([1, 2], dtype=torch.int64),
    'area': torch.tensor([1600.0, 2500.0], dtype=torch.float32),
    'iscrowd': torch.tensor([0, 0], dtype=torch.int64),
    'keypoints': torch.tensor([
        [15.0, 15.0, 1.0, 20.0, 20.0, 1.0, 25.0, 25.0, 1.0],
        [35.0, 35.0, 1.0, 40.0, 40.0, 1.0, 45.0, 45.0, 1.0]
    ], dtype=torch.float32),
}

# region: (i, j, h, w) - top, left, height, width of crop
region = (10, 10, 60, 60)

ARGS = {
    'image': image,
    'target': target,
    'region': region
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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
dice_loss Ran
ran, violated the contract we drafted
pranoyr/pose-estimation-with-transformers/models/segmentation.py
pointer only (licence: Apache-2.0) · get_code("ac8fe530cdad4d8c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, pranoyr/pose-estimation-with-transformers, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

evaluate Ran
ran; our contract draft was wrong, not the code
amathislab/poet/datasets/coco_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhangzang/contextdet, is pointer only (licence: NOASSERTION) · get_code("fe0ddcc2d420c9a0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yuhangzang/contextdet, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

hflip Ran
ran on a synthesized input
amathislab/poet/datasets/transforms.py
code served (permissive licence) · get_code("c7aac0bc5d5e58fb")
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 torchvision.transforms.functional as F
from PIL import Image

torch.manual_seed(0)

# Create a small PIL Image for testing
# hflip expects a PIL Image with .size attribute
image = Image.new('RGB', (640, 480))  # width=640, height=480

# Create target dict with boxes and keypoints
target = {
    'boxes': torch.tensor([
        [10.0, 20.0, 100.0, 200.0],
        [150.0, 50.0, 300.0, 400.0]
    ]),
    'keypoints': torch.tensor([
        [50.0, 60.0, 1.0, 70.0, 80.0, 1.0, 90.0, 100.0, 1.0, 110.0, 120.0, 1.0],
        [55.0, 65.0, 1.0, 75.0, 85.0, 1.0, 95.0, 105.0, 1.0, 115.0, 125.0, 1.0]
    ])
}

ARGS = {
    'image': image,
    'target': target
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — 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
kpts_xyxy_to_cxcydxdy Ran
ran on a synthesized input
amathislab/poet/util/kpts_ops.py
code served (permissive licence) · get_code("b6951516c57c12ab")
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 2, dtype family float, shape (2, 53) 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

torch.manual_seed(0)

# Create keypoints tensor: shape (batch_size, num_keypoints * 3)
# COCO has 17 keypoints, each with (x, y, confidence) = 51 values
batch_size = 2
num_keypoints = 17
keypoints = torch.randn(batch_size, num_keypoints * 3, dtype=torch.float32)

# Create center tensor: shape (batch_size, 2) with x, y coordinates
center = torch.randn(batch_size, 2, dtype=torch.float32)

# hierarchical parameter
hierarchical = False

ARGS = {
    'kpts': keypoints,
    'ctr': center,
    'hierarchical': hierarchical
}
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 2, dtype family float, shape (2, 53) — shape (2, 53) 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
rescale_bboxes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pranoyr/pose-estimation-with-transformers/inference.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from 116508/CF-Deformable-DETR, is pointer only (licence: Apache-2.0) · get_code("3e6fd166df697bf7")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, pranoyr/pose-estimation-with-transformers, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

sigmoid_focal_loss Ran
ran; our contract draft was wrong, not the code
pranoyr/pose-estimation-with-transformers/models/segmentation.py
pointer only (licence: Apache-2.0) · get_code("5c0711aada67957e")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, pranoyr/pose-estimation-with-transformers, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

build_matcher Not yet run
unverified (harvested, no recorded run)
amathislab/poet/models/matcher.py
code served (permissive licence) · get_code("e4d1a30dbec2707d")
How it ran

no invocation recorded.

build_transformer Not yet run
unverified (harvested, no recorded run)
pranoyr/pose-estimation-with-transformers/models/transformer.py
pointer only (licence: Apache-2.0) · get_code("302ec916d91b12a8")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, pranoyr/pose-estimation-with-transformers, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

build_transformer Not yet run
unverified (harvested, no recorded run)
amathislab/poet/models/transformer.py
code served (permissive licence) · get_code("de542ddb0a808b05")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 11 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 5 the same month, 11 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
sigmoid_focal_loss 56 other papers
2 dated earlier, 1 the same month, 53 later · 1 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 53 more not named here
box_cxcywh_to_xyxy 49 other papers
2 dated earlier, 1 the same month, 46 later · 11 only as an assembly brick
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
2011.10881 (2020-11)
Rethinking Transformer-based Set Prediction for Object Detection
2103.14259 (2021-03)
OTA: Optimal Transport Assignment for Object Detection
and 46 more not named here
box_xyxy_to_cxcywh 45 other papers
1 dated earlier, 1 the same month, 43 later · 20 only as an assembly brick
2011.10881 (2020-11)
Rethinking Transformer-based Set Prediction for Object Detection
2103.17154 (2021-03)
Learning Spatio-Temporal Transformer for Visual Tracking
2104.00969 (2021-04)
TubeR: Tubelet Transformer for Video Action Detection
and 42 more not named here
dice_loss 40 other papers
2 dated earlier, 38 later · 1 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2104.12763 (2021-04)
MDETR -Modulated Detection for End-to-End Multi-Modal Understanding
and 37 more not named here
build_transformer 32 other papers
1 dated earlier, 31 later
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2104.04369 (2021-04)
Video-aided Unsupervised Grammar Induction
2104.08541 (2021-04)
TransVG: End-to-End Visual Grounding with Transformers
and 29 more not named here
box_iou 24 other papers
23 later, 1 undated · 5 only as an assembly brick
2104.00969 (2021-04)
TubeR: Tubelet Transformer for Video Action Detection
2112.05375 (2021-12)
Rethinking the Two-Stage Framework for Grounded Situation Recognition
2203.01666 (2022-03)
Correlation-Aware Deep Tracking
and 21 more not named here
convert_to_xywh 24 other papers
2 dated earlier, 1 the same month, 21 later
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 21 more not named here
evaluate 23 other papers
2 dated earlier, 1 the same month, 20 later
1512.02325 (2015-12)
SSD: Single Shot MultiBox Detector
2010.04159 (2020-10)
Deformable DETR: Deformable Transformers for End-to-End Object Detection
2103.11731 (2021-03)
Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
and 20 more not named here
box_cxcywh_to_xyxy 9 other papers
9 later
Pan_Wnet_Audio-Guided_Video_Object_Segmentation_via_Wavelet-Based_Cross-Modal_Denoising_Networks_CVPR_2022_paper (2022 (year only))
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
2307.09356 (2023-07)
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
and 6 more not named here
rescale_bboxes 3 other papers
3 later
2110.00061 (2021-10)
PubTables-1M: Towards comprehensive table extraction from unstructured documents
ijcai2024_0084 (2024 (year only))
CF-Deformable DETR: An End-to-End Alignment-Free Model for Weakly Aligned Visible-Infrared Object Detection
2601.08728 (2026-01)
Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation
build_matcher 2 other papers
2 later
2303.00246 (2023-03)
ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution
2411.10293 (2024-11)
RETR: Multi-View Radar Detection Transformer for Indoor Perception

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

We propose an end-to-end trainable approach for multi-instance pose estimation, called POET (POse Estimation Transformer). Combining a convolutional neural network with a transformer encoder-decoder architecture, we formulate multiinstance pose estimation from images as a direct set prediction problem. Our model is able to directly regress the pose of all individuals, utilizing a bipartite matching scheme. POET is trained using a novel set-based global loss that consists of a keypoint loss, a visibility loss and a class loss. POET reasons about the relations between multiple detected individuals and the full image context to directly predict their poses in parallel. We show that POET achieves high accuracy on the COCO keypoint detection task while having less parameters and higher inference speed than other bottom-up and top-down approaches. Moreover, we show successful transfer learning when applying POET to animal pose estimation. To the best of our knowledge, this model is the first end-to-end trainable multi-instance pose estimation method and we hope it will serve as a simple and promising alternative.

For agents

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

get_harvested_code_for_paper("2103.12115")
get_code_for_paper("2103.12115")
have("2103.12115")

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

curl https://syntology.ai/api/ran/2103.12115.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.12115.svg)](https://syntology.ai/paper/2103.12115)

Connect an agent — have() is free.