Login / Signup
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition.
Rameswar Panda
Chun-Fu Chen
Quanfu Fan
Ximeng Sun
Kate Saenko
Aude Oliva
Rogério Feris
Published in:
CoRR (2021)
Keyphrases
</>
multi modal
visual recognition
multi modality
semantic concepts
video search
object recognition
video frames
image annotation
computer vision
image segmentation
image analysis
action recognition
video streams
human activities
human actions
audio visual