most citedModality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection

1 citations · 1 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2022★ 1 cited

Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection

Jiashuo Yu, Jinyu Liu, Ying Cheng +2

Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual…

cs.CV2022

Self-Supervised Video Representation Learning with Motion-Contrastive Perception

Jinyu Liu, Ying Cheng, Yuejie Zhang +2

Visual-only self-supervised learning has achieved significant improvement in video representation learning. Existing related methods encourage models to learn video representations…