Visually grounded few-shot word acquisition with fewer shots.

Leanne Nortje Benjamin van Niekerk Herman Kamper

Published in: INTERSPEECH (2023)

Keyphrases

video shots
key frames
shot detection
video data
video sequences
news video
visual features
temporal segmentation

shot boundary detection
co occurrence
video indexing
video material
video content
video streams
gradual transitions
n gram

visual content
word recognition
video retrieval
video summarization
detection algorithm
keywords
shot transitions
video segmentation

video clips
sports video
related words
video database
video analysis
low level features
moving objects