MediaPipe Hands: On-device Real-time Hand Tracking

cs.SD 2025-09 conditional novelty 7.0 of 10

A multimodal dataset of 21 hours of amateur piano practice with synchronized video, audio, MIDI, hand landmarks, and fingering pseudo-labels, plus benchmarks for audio-only and audio-visual transcription.

cs.HC 2025-09 conditional novelty 7.0 of 10

A headset-mounted RGB camera and a lightweight vision model detect finger-to-skin touches with about 95% frame accuracy and estimate press force, enabling uninstrumented, calibration-free on-body touch input.

cs.RO 2026-07 conditional novelty 6.0 of 10

A hybrid kinesthetic-arm-plus-webcam-hand teleoperation interface achieved 17x/3x higher demonstration throughput than vision baselines and trained a 90%-success pick-and-place policy in a ten-person study.

cs.RO 2026-07 conditional novelty 6.0 of 10

Novel person re-identification with continual adaptation plus submap LiDAR SLAM, ground-aware filtering, Gaussian Scan Context, and multi-modal semantic mapping improve robotic contextual awareness for HRC and navigation.

cs.RO 2026-07 conditional novelty 6.0 of 10

DemoBridge retargets single-view human hand demonstrations into physics-validated, collision-aware robot trajectories via whole-trajectory optimization and simulation-in-the-loop re-planning.

cs.AI 2026-05 conditional novelty 6.0 of 10

Public-space gesture failures form six working classes—model-output degeneration, temporal mismatch, scale instability, coordinate mismatch, lifecycle failure, and feedback mismatch—revealing a recognition-to-interaction gap.

cs.HC 2025-09 conditional novelty 6.0 of 10

A headset-integrated system detects touch contact and hover distance on everyday surfaces by analyzing shadows cast by worn infrared emitters, without instrumenting the surface or hands.

cs.CV 2025-06 conditional novelty 6.0 of 10

Using 3D hand meshes instead of depth maps to guide diffusion inpainting improves malformed hand refinement and enables training-free hand pose transformation.

cs.CV 2026-07 accept novelty 5.0 of 10

Adding 695 synthetic or derived training images did not improve a YOLOv8n campus-waste detector over the real-only baseline; image source mattered more than image count.

quant-ph 2026-04 unverdicted novelty 5.0 of 10

Three scheduling strategies for hybrid quantum-HPC systems cut classical resource use by up to 64% or boost QPU utilization depending on workload balance, validated on real hardware.

cs.CL 2025-10 conditional novelty 5.0 of 10

In a motion-capture study of one ASL instructor-student pair, STEM signs in dialogue were 24.6-44.6% shorter than isolated vocabulary signs, with repeated-mention compression absent in a monologue - evidence of intera...

physics.atom-ph 2025-08 unverdicted novelty 5.0 of 10

A 0.12 s accelerometer dead time in an atom-interferometer dynamic gravimeter introduces roughly 8 mGal of measurement noise, which the paper attributes to high-frequency aliasing and analyzes with a derived frequency...

cs.HC 2025-08 conditional novelty 5.0 of 10

A multimodal framework and visualization system, reCAPit, automatically extracts activity, attention, and topic segments from workshop recordings to help analysts trace how design decisions emerged.

cs.CV 2025-11 conditional novelty 4.0 of 10

TrackStudio packages MediaPipe and Anipose into a GUI with new validation on 76 participants; it shows stable self-consistency, but its error claims lack ground-truth comparison.

cs.RO 2025-09 conditional novelty 4.0 of 10

A transformer with an engineered finger-to-object angle feature matches a geometric baseline (90% accuracy) for pointing target prediction on a small tabletop dataset.