Zero-Shot Video Captioning by Evolving Pseudo-tokens.

Yoad Tewel Yoav Shalev Roy Nadler Idan Schwartz Lior Wolf

Published in: BMVC (2023)

Keyphrases

video sequences
video streams
video data
multimedia
video analysis
key frames
video frames
dynamic scenes
video images

digital video
video surveillance
data sets
video processing
video clips
video search
video content
real time video
spatial and temporal

real time
event detection
spatial temporal
online video
neural network
video summarization
learning algorithm
spatio temporal

surveillance videos
multiresolution
video database
object detection
multi view
space time
video retrieval
object categories