Frozen BLIP-2 representations, used via structured-text decoding and feature concatenation, achieve state-of-the-art results on four dynamic scene understanding benchmarks.
End-to- end object detection with transformers
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
-
Dynamic Scene Understanding from Vision-Language Representations
Frozen BLIP-2 representations, used via structured-text decoding and feature concatenation, achieve state-of-the-art results on four dynamic scene understanding benchmarks.