KeypointRCNN
E431011
PyTorch torchvision model
deep learning model architecture
human pose estimation model
keypoint detection model
object detection model
KeypointRCNN is a deep learning model architecture in PyTorch’s torchvision library designed for object detection combined with human pose estimation via keypoint prediction.
All labels observed (1)
| Label | Occurrences |
|---|---|
| KeypointRCNN canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4326006 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KeypointRCNN Context triple: [torchvision, modelFamily, KeypointRCNN]
-
A.
DETR
DETR is the acronym for the former UK government Department of the Environment, Transport and the Regions, which was responsible for environmental policy, transport, and regional affairs.
-
B.
YOLO
"YOLO" is a comedic hip-hop song and music video by The Lonely Island, featuring Adam Levine and Kendrick Lamar, that parodies the phrase "you only live once" by humorously promoting extreme caution and risk avoidance.
-
C.
ResNeXt
ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.
-
D.
Fast Interaction Trigger detector
The Fast Interaction Trigger detector is a specialized subdetector of the ALICE experiment at CERN designed to rapidly identify and select particle collision events of interest for data acquisition.
-
E.
Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KeypointRCNN Target entity description: KeypointRCNN is a deep learning model architecture in PyTorch’s torchvision library designed for object detection combined with human pose estimation via keypoint prediction.
-
A.
DETR
DETR is the acronym for the former UK government Department of the Environment, Transport and the Regions, which was responsible for environmental policy, transport, and regional affairs.
-
B.
YOLO
"YOLO" is a comedic hip-hop song and music video by The Lonely Island, featuring Adam Levine and Kendrick Lamar, that parodies the phrase "you only live once" by humorously promoting extreme caution and risk avoidance.
-
C.
ResNeXt
ResNeXt is a deep convolutional neural network architecture that extends ResNet by using grouped convolutions and a split-transform-merge strategy to improve accuracy and efficiency in image recognition tasks.
-
D.
Fast Interaction Trigger detector
The Fast Interaction Trigger detector is a specialized subdetector of the ALICE experiment at CERN designed to rapidly identify and select particle collision events of interest for data acquisition.
-
E.
Very Deep Convolutional Networks for Large-Scale Image Recognition
"Very Deep Convolutional Networks for Large-Scale Image Recognition" is the influential 2014 research paper that introduced the VGG family of deep convolutional neural network architectures, demonstrating that significantly increasing network depth with small convolutional filters leads to substantial improvements in image classification performance.
- F. None of above. chosen
Statements (45)
| Predicate | Object |
|---|---|
| instanceOf |
PyTorch torchvision model
ⓘ
deep learning model architecture ⓘ human pose estimation model ⓘ keypoint detection model ⓘ object detection model ⓘ |
| basedOn |
Mask R-CNN
ⓘ
linked to:
MaskRCNN
|
| documentation | https://pytorch.org/vision/stable/models/keypoint_rcnn.html ⓘ |
| extends |
Faster R-CNN
ⓘ
linked to:
FasterRCNN
|
| framework | PyTorch ⓘ |
| hasComponent |
RPN head
ⓘ
backbone network ⓘ box head ⓘ keypoint head ⓘ |
| hasPretrainedWeightsFor |
COCO keypoints
ⓘ
linked to:
COCO
|
| hyperparameter |
RPN anchor aspect ratios
ⓘ
RPN anchor sizes ⓘ image size ⓘ number of keypoints ⓘ |
| implementedIn | Python ⓘ |
| inputType | RGB image ⓘ |
| library |
torchvision
ⓘ
linked to:
torchvision (ecosystem)
|
| outputType |
bounding boxes with scores
ⓘ
class labels ⓘ keypoint coordinates ⓘ keypoint visibility flags ⓘ |
| providedBy |
torchvision.models.detection
ⓘ
linked to:
torchvision (ecosystem)
|
| repository | https://github.com/pytorch/vision ⓘ |
| supports |
GPU acceleration
ⓘ
batched inference ⓘ bounding box prediction ⓘ end-to-end training ⓘ instance-level detection ⓘ keypoint heatmap prediction ⓘ |
| task |
human pose estimation
ⓘ
keypoint prediction ⓘ object detection ⓘ |
| trainingObjective |
bounding box regression loss
ⓘ
classification loss ⓘ keypoint localization loss ⓘ |
| typicalBackbone |
ResNet-101-FPN
ⓘ
linked to:
FPN
ResNet-50-FPN ⓘ
linked to:
ResNet
|
| useCase |
human pose estimation in images
ⓘ
person detection with keypoints ⓘ |
| uses |
Region Proposal Network
ⓘ
RoIAlign ⓘ
linked to:
MaskRCNN
|
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: KeypointRCNN Description of subject: KeypointRCNN is a deep learning model architecture in PyTorch’s torchvision library designed for object detection combined with human pose estimation via keypoint prediction.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject linked to:
torchvision (ecosystem)