Login / Signup
Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains.
Rohan Myer Krishnan
Zitian Tang
Zhiqiu Yu
Chen Sun
Published in:
CoRR (2023)
Keyphrases
</>
multimedia
video sequences
real world
video data
video analysis
multi modal
data sets
video clips
video streams
spatio temporal
metadata
computer vision
spatial and temporal
video retrieval
neural network
real time
video database
digital video
visual analysis