A Hierarchical Framwork with Improved Loss for Large-scale Multi-modal Video Identification.
Shichuan ZhangZengming TangHao PanXinyu WeiJun HuangPublished in: ACM Multimedia (2019)
Keyphrases
- multi modal
- video search
- semantic concepts
- video sequences
- multimedia
- multi modality
- video data
- video content
- video streams
- multiple modalities
- video frames
- image annotation
- high dimensional
- audio visual
- video database
- video retrieval
- humanoid robot
- image processing
- spatial and temporal
- cross modal
- image classification
- uni modal