AURA-MFM aligns IMU, third-person video, motion capture, and text in one embedding space and reports much higher zero-shot activity recognition than IMU2CLIP, though the baseline comparison is confounded by dataset mismatch.
An image is worth 16x16 words: Transformers for image recognition at scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Multimodal Foundation Model for Cross-Modal Retrieval and Activity Recognition Tasks
AURA-MFM aligns IMU, third-person video, motion capture, and text in one embedding space and reports much higher zero-shot activity recognition than IMU2CLIP, though the baseline comparison is confounded by dataset mismatch.