CHAN: Cross-Modal Hybrid Attention Network for Temporal Language Grounding in Videos

Keyphrases

• Attention Fusion 100%
• Attention Matrix 33%
• Attention Weight 33%
• Co-attention 33%
• Cross-modal Attention 33%
• Cross-modal Interaction 33%
• Fusion Module 33%
• Gated Self-attention 33%
• Global Semantics 33%
• Ground Performance 33%
• Hybrid Attention 100%
• Intramodal 33%
• Modal Fusion 33%
• Parallel Attention 33%
• Temporal Grounding 100%
• Untrimmed Video 33%
• Video Content 33%
• Video Segment 33%

Computer Science

• Attention (Machine Learning) 100%
• Experimental Result 50%