Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
cs.CV, cs.AI
Submitted: 2026-06-03
Updated: 2026-10-12
Terminology
Sources
- PREGO: online mistake detection in PRocedural EGOcentric videos
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
- Procedural Mistake Detection via Action Effect Modeling
- PALM: Predicting Actions through Language Models
- Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling
- IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting
- Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
- StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
- PrISM-Observer: Intervention Agent to Help Users Perform Everyday Procedures Sensed using a Smartwatch
- Proactive Assistant Dialogue Generation from Streaming Egocentric Videos
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models