A state-space model with transfer state processes videos chunk by chunk, carries the hidden state forward, and performs online dense video captioning with the same state as full-sequence processing.
Vid2seq: Large-scale pretraining of a visual language model for dense video captioning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Time-Scaling State-Space Models for Dense Video Captioning
A state-space model with transfer state processes videos chunk by chunk, carries the hidden state forward, and performs online dense video captioning with the same state as full-sequence processing.