HUMAN_POV
HUMAN POVORGANIZING3D HAND POSE

Tidying and Organizing Room

The person organizes the room by gathering and folding clothes, cleaning up scattered items like shoes, and ironing garments.

Environment / Living room with an ironing station and a storage area.

EGOCENTRIC CAPTURE
Tidying and Organizing Room egocentric capture
STILL FRAME
Tidying and Organizing Room still frame

Scene Analysis

Objects and actions detected in the capture, segmented with SAM3 and labeled with a vision model.

Detected Objects
chairstable with floral clothironing boardclothesshoesspray bottleironlaundry basket
Detected Actions
picking up scattered shoesplacing shoes in an organized mannergathering clothes for ironingironing clothesfolding clothesplacing clothes in a basket or designated area

Interactive 3D Hand Pose

21 landmarks per hand, both hands. Drag to orbit, scrub the timeline, toggle each hand.

LOADING 3D HAND POSE...

Transcript

Frame-aligned narration of the demonstration.

0:00 - 0:50

I see some scattered shoes on the floor and start picking them up one by one to organize them.

0:51 - 1:40

I gather the shoes near the ironing station, making sure each pair is neatly placed together.

1:41 - 2:30

I notice some clothes draped over the chair and start folding one of the shirts while preparing to iron others.

2:31 - 3:20

I set one of the shirts on the ironing board and start ironing it, smoothing the fabric as I go.

3:21 - 4:10

I fold the freshly ironed shirt neatly and organize it with other clothes on the table.

4:11 - 5:00

I place the folded clothes into a laundry basket and reach for a pair of pants to iron next.

5:01 - 6:00

After ironing the pair of pants, I carefully fold it, ensuring everything looks neat and wrinkle-free.

6:01 - 6:54

I continue folding some black fabric, possibly a t-shirt or towel, and place it with the rest of the neatly organized items.

Sample Specs

Task Family
Organizing
Duration
6.9 minutes
Frames
12,419
Frame Rate
30 fps
Resolution
Egocentric
Hand Landmarks
21 x 2 hands, per frame