EgoSAT is the first benchmark unifying retrospective, online, and prospective reasoning tasks in egocentric streaming video to evaluate VLMs, revealing struggles with temporal modeling and mis-calibration.
arXiv preprint arXiv:2412.21080 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Memento captures verbal queries with spatiotemporal contexts, discovers recurring interest patterns, and proactively delivers updated AR responses when matching situations are detected.
A new memory system for social robots selectively stores multimodal memories by emotional salience and novelty, achieving 0.506 Spearman correlation in selectivity and up to 13% better Recall@1 in multimodal retrieval.
citing papers explorer
-
EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding
EgoSAT is the first benchmark unifying retrospective, online, and prospective reasoning tasks in egocentric streaming video to evaluate VLMs, revealing struggles with temporal modeling and mis-calibration.
-
Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant
Memento captures verbal queries with spatiotemporal contexts, discovers recurring interest patterns, and proactively delivers updated AR responses when matching situations are detected.
-
Human-Inspired Context-Selective Multimodal Memory for Social Robots
A new memory system for social robots selectively stores multimodal memories by emotional salience and novelty, achieving 0.506 Spearman correlation in selectivity and up to 13% better Recall@1 in multimodal retrieval.