GCMA: Generative Cross-Modal Transferable Adversarial Attacks from Images to Videos.
Kai ChenZhipeng WeiJingjing ChenZuxuan WuYu-Gang JiangPublished in: ACM Multimedia (2023)
Keyphrases
- cross modal
- image retrieval
- image data
- visual data
- visual similarity
- image database
- image features
- perceptual information
- image collections
- web images
- image understanding
- image annotation
- test images
- multi modal
- high dimensional
- video sequences
- similarity search
- visual concepts
- multimedia retrieval
- feature vectors
- object recognition