Tencent AVS: A Holistic Ads Video Dataset for Multi-Modal Scene Segmentation.
Jie JiangZhimin LiJiangfeng XiongRongwei QuanQinglin LuWei LiuPublished in: IEEE Access (2022)
Keyphrases
- multi modal
- scene segmentation
- video dataset
- video search
- action recognition
- video sequences
- video data
- video frames
- object tracking
- indoor scenes
- visual information
- semantic concepts
- high dimensional
- video clips
- audio visual
- machine learning
- image annotation
- medical images
- web pages
- image database
- keywords
- image sequences