Login / Signup
A Compositional Framework for Grounding Language Inference, Generation, and Acquisition in Video.
Haonan Yu
N. Siddharth
Andrei Barbu
Jeffrey Mark Siskind
Published in:
J. Artif. Intell. Res. (2015)
Keyphrases
</>
main contribution
language learning
video streams
multimedia
real time
spatio temporal
video sequences
theoretical framework
bayesian networks
video content
bayesian framework
statistical inference
generation process
inference process
abductive reasoning
video classification
declarative language