Encoding video as a small set of object tokens, produced by off-the-shelf detection, segmentation, and tracking models, improves video QA accuracy and enables video-based referring in a 7B video-LLM.
Spice: Semantic propositional image cap- tion evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VideoOrion: Tokenizing Object Dynamics in Videos
Encoding video as a small set of object tokens, produced by off-the-shelf detection, segmentation, and tracking models, improves video QA accuracy and enables video-based referring in a 7B video-LLM.