A closed-loop streaming gesture generator that anchors each clip to a retrieved tail pose and re-generates the clip toward that pose, reducing long-horizon drift in co-speech motion.
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring
A closed-loop streaming gesture generator that anchors each clip to a retrieved tail pose and re-generates the clip toward that pose, reducing long-horizon drift in co-speech motion.