paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
Audio Classification
벤치마크
Audio Classification on DCASE
10개 결과 ·
⬇ CSV
·
JSON
Top-1 Accuracy
93
94
95
96
97
2019-11
2026-09
XDC — 95.0 (2019-11-28)
XDC — 95.0 (2019-11-28)
XDC — 95.0 (2019-11-28)
XDC — 95.0 (2019-11-28)
CrissCross (AudioSet) — 97.0 (2021-11-09)
CrissCross (Kinetics-400) — 96.0 (2021-11-09)
CrissCross (Kinetics-Sound) — 93.0 (2021-11-09)
CrissCross (AudioSet) — 97.0 (2021-11-09)
CrissCross (Kinetics-400) — 96.0 (2021-11-09)
CrissCross (Kinetics-Sound) — 93.0 (2021-11-09)
XDC — 95.0 (2019-11-28)
CrissCross (AudioSet) — 97.0 (2021-11-09)
2019-11-28 — XDC: Top-1 Accuracy 95.0
2021-11-09 — CrissCross (AudioSet): Top-1 Accuracy 97.0
Rank
Model
Top-1 Accuracy
PRE-TRAINING DATASET
Paper
Code
Year
1
CrissCross (AudioSet)
97
AudioSet
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
pritamqu/CrissCross
2021
2
CrissCross (Kinetics-400)
96
Kinetics-400
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
pritamqu/CrissCross
2021
3
XDC
95
IG-Random
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
HumamAlwassel/XDC
2019
3
XDC
95
AudioSet
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
HumamAlwassel/XDC
2019
5
CrissCross (Kinetics-Sound)
93
Kinetics-Sound
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
pritamqu/CrissCross
2021
6
CrissCross (AudioSet)
97
AudioSet
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
pritamqu/CrissCross
2021
7
CrissCross (Kinetics-400)
96
Kinetics-400
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
pritamqu/CrissCross
2021
8
XDC
95
IG-Random
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
HumamAlwassel/XDC
2019
8
XDC
95
AudioSet
Self-Supervised Learning by Cross-Modal Audio-Video Clustering
HumamAlwassel/XDC
2019
10
CrissCross (Kinetics-Sound)
93
Kinetics-Sound
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
pritamqu/CrissCross
2021
1–10 / 10
페이지당
10
20
50
100