Login / Signup
Video Q &A based on two-stage deep exploration of temporally-evolving features with enhanced cross-modal attention mechanism.
Yuanmao Luo
Ruomei Wang
Fuwei Zhang
Fan Zhou
Mingyang Liu
Jiawei Feng
Published in:
Neural Comput. Appl. (2024)
Keyphrases
</>
cross modal
multi modal
image features
video clips
low level
co occurrence
multimedia
video streams
video data
feature extraction
feature vectors
visual features
video sequences
high level
semantic concepts
feature selection
attention mechanism