MARS converts long videos to captions and summaries, maintains modality-specific memories, and deploys an agent to select evidence or answer, placing second on the CASTLE Challenge leaderboard.
Ego-exo4d: Understanding skilled human activity from first- and third-person perspec- tives
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
MARS converts long videos to captions and summaries, maintains modality-specific memories, and deploys an agent to select evidence or answer, placing second on the CASTLE Challenge leaderboard.