Unverified50% confidenceFactExact time
Environment-Aware Retargeting (EAR) combines the reconstructed scene geometry information with the head and gripper trajectories in the demonstration to determine the robot pose and generate collision-aware joint targets and base targets.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPose estimation infers head orientation and body posture by detecting human keypoints, while gaze estimation further estimates the direction of eye fixation.70% similarUnverifiedScroll-triggered interactions typically rely on the Intersection Observer API or scroll event listeners, calculating the percentage position of an element within the viewport to control animations.65% similarUnverified人类眼球的扫视运动本身呈现分形特征，观看分形图像时扫视路径也呈分形模式64% similarUnverifiedUsing detected keypoints to rotate and scale a face into a standard pose (face alignment) before extracting feature vectors can greatly improve feature stability.64% similarUnverified3D-guided neural rendering uses geometric data such as depth buffers, normal maps, and motion vectors as explicit inputs to neural networks to better understand the spatial positional relationships of objects in a scene.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130377API
curl https://kongchang.com/api/v1/knowledge/claims/1130377MCP
get_claim(id=1130377)