Pose Estimation MCQ 15 Questions
Time: ~25 mins Advanced

Pose Estimation MCQ

Locate body joints in images—single or crowded scenes—with heatmaps, associations, or top-down detectors.

Easy: 5 Q Medium: 6 Q Hard: 4 Q
Joints

K keypoints

Heatmap

Per joint

Multi-person

Parse

PAFs / graph

Link limbs

Human pose from pixels

Pose estimation predicts 2D (or 3D) locations of anatomical joints. Top-down methods detect people then estimate pose per crop; bottom-up methods predict all joints then group them (e.g. Part Affinity Fields). Datasets like COCO define a standard skeleton and metrics (OKS).

OKS / PCK

Object Keypoint Similarity generalizes AP to keypoints using scale-normalized distance thresholds.

Key ideas

Keypoints

Wrist, elbow, hip, etc., as (x,y) or heatmap peaks.

Heatmap head

One channel per joint; argmax or refinement for location.

Top-down

Person detector → single-person pose network per box.

Bottom-up

All joints + pairwise cues to assemble instances.

Typical stack

backbone → heatmaps / offsets → grouping or single-person decode

Pro tip: Occlusion and rare poses hurt both paradigms—data augmentation and 3D priors help in video.