Government Of India
A-
A
A+
AVVP Audio Visual Video Parsing
Audio Visual Video Parsing
About Dataset
We present a novel approach to the Audio-visual video parsing task that takes into cognizance how event categories bind to audio and visual modalities. The proposed parsing approach simultaneously detects the temporal boundaries of such events.
Dataset Metadata
CC0 1.0 Public Domain
Global
Sector Agnostic
IIT Bombay
Structured
NA
NA
N.A.
28/04/25 08:26:31
Open
Hosted
Activity Overview
0
21 
548 
764.22 KB
Tags
- No Tags Found!!
License Control
CC0 1.0 Public Domain
clqg-master ( 24 files, 3 directories )
configs
7 files
data
7 files
.DS_Store
8 KB
average_chk.sh
252 Bytes
cnn_text_discriminator.py
21.76 KB
data_iterator.py
14.06 KB
evaluate.py
10.06 KB
evaluate.sh
113 Bytes
gan_train.py
10.34 KB
gan_train.sh
98 Bytes
This preview shows 10 out of 27 items. Load more
Data Quality Score Beta
Version Control
Version 1(764.22 KB)
- admin·9 month(s) ago
- chevron_right
clqg-master
- chevron_right
configs
- chevron_right
data
.DS_Store
average_chk.sh
cnn_text_discriminator.py
data_iterator.py
evaluate.py
evaluate.sh
gan_train.py
gan_train.sh
- more_horiz 17 more
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.