EVA02-AT combines full-dimension spatial and temporal rotary position embeddings with a symmetric multi-similarity loss to improve egocentric video-text retrieval.
Egocentric video-language pretraining,
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
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization
EVA02-AT combines full-dimension spatial and temporal rotary position embeddings with a symmetric multi-similarity loss to improve egocentric video-text retrieval.