Transformer Based Multimodal Scene Recognition in Soccer Videos.
Yaozong GanRen TogoTakahiro OgawaMiki HaseyamaPublished in: ICME Workshops (2022)
Keyphrases
- scene recognition
- soccer video
- video analysis
- object recognition
- scene understanding
- event detection
- object detection
- probabilistic latent semantic analysis
- scene classification
- video streams
- video data
- image representation
- multi modal
- sports video
- information retrieval
- audio visual
- computer vision
- search engine
- probabilistic model
- video sequences
- image segmentation
- multimedia