MCAM is a video captioning model combining 3DResNet and VidSwin features with a graph-inspired fusion module, reporting mixed gains on BDD-X and CoVLA but failing to implement the promised causal reasoning.
Spatio-temporal dynamics and se- mantic attribute enriched visual encoding for video caption- ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding
MCAM is a video captioning model combining 3DResNet and VidSwin features with a graph-inspired fusion module, reporting mixed gains on BDD-X and CoVLA but failing to implement the promised causal reasoning.