Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization

Benchmark Model Rank Results
temporal-action-localization-on-activitynetAVFusion#12mAP: 36.82mAP IOU@0.5: 54.34mAP IOU@0.75: 37.66mAP IOU@0.95: 8.93
temporal-action-localization-on-thumos14AVFusion#20Avg mAP (0.3:0.7): 53.3mAP IOU@0.3: 70.1mAP IOU@0.4: 64.9