| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://siming.fun/PoseScript
x-github-request-id: 4812:3A7A40:94254F:A64090:6952E4CC
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 20:30:06 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210020-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767040206.359534,VS0,VE200
vary: Accept-Encoding
x-fastly-request-id: 0c6161801ed12df5c4ff97ecae9016ce2495f90f
content-length: 162
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://siming.fun/PoseScript/
access-control-allow-origin: *
expires: Mon, 29 Dec 2025 20:40:06 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: F051:444BC:956C7F:A78658:6952E4CE
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 20:30:07 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210085-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767040207.879238,VS0,VE203
vary: Accept-Encoding
x-fastly-request-id: fdace0a905a93248e84d167ede6492c9abe0539f
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
x-origin-cache: HIT
last-modified: Tue, 18 Nov 2025 07:59:19 GMT
access-control-allow-origin: *
etag: W/"691c2757-29c1"
expires: Mon, 29 Dec 2025 20:40:07 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: E375:2118F1:93B996:A5D326:6952E4CE
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 20:30:07 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210085-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767040207.095970,VS0,VE212
vary: Accept-Encoding
x-fastly-request-id: bacae719c19668cb14d35b5d5281ac0e031f8f31
content-length: 3481
Siming Fan's Home Page
VideoLLM Retrieves Video Frames
Large-scale (18.6M instances) Synthetic Pose Text Annotation
(a) Single-frame pose + Tracking visualization, image version of PoseScript, the text on the image describes the pose of the current bbox person. Double-click to zoom in for detailed annotations, including text, MPJPE (mean per-joint position error), and Y-axis orientation (±180 degrees for front view).
(b) Dual-frame pose description change + second-frame pose description visualization (non-tracking version), image version of PoseFix, hover to pause.
Fine-grained (Action/Pose) Text Description to Locate Video Frames
(Hover to zoom in)
PoseScript
Open-source Projects in SenseTime Research
2024 MultiModal Frame Retrieval in Video and Editing
BestMoment Annotation Example using our pipeline and GPT4o API, which is the best in action retrieval.
This dataset aims to address the issues of high cost (￥0.03/character) in manual annotation and low accuracy (accuracy manual:GPT:ours=95%:70%:95%) in GPT4o annotation for pose description. It is divided into two versions: (a) single-frame pose description and (b) dual-frame pose change description, used for training text-to-frame models and image editing models.