SOURCE-LINKED INTELLIGENCE

Reliable Egocentric Action Anticipation via Temporal Reliability Suppression and Compositional Graph Decoding

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Wearable action anticipation systems must remain reliable despite missing frames, masking, and sensor noise, yet existing egocentric anticipation methods largely assume clean observations. We identify two complementary failure modes under temporal corruption: unreliable temporal evidence during encoding and implausible, low-support verb-noun compositions during decoding. We address them with a lightweight framework combining Temporal Reliability Suppression (TRS) and Robust Verb-Noun Graph (RVG) decoding. TRS predicts a per-frame suppression score from the projected input embedding and uses it

Read original source ↗ Open in workspace

recordType

paper

region

Global