Sign in
Conditional Video-Text Reconstruction Network with Cauchy Mask for Weakly Supervised Temporal Sentence Grounding.
Jueqi Wei
Yuanwu Xu
Mohan Chen
Yuejie Zhang
Rui Feng
Shang Gao
Published in:
ICME (2023)
Keyphrases
</>
weakly supervised
semantic attributes
weakly labeled
video sequences
topic models
object class
information retrieval
semi supervised
three dimensional
video frames
video data
semantic information
bayesian networks
text documents
low level features
superpixels
object detectors
natural language processing