Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection.
Sanghyun WooKwanyong ParkSeoung Wug OhIn So KweonJoon-Young LeePublished in: CoRR (2022)
Keyphrases
- object detectors
- object detection
- video dataset
- video data
- video images
- video frames
- video sequences
- object recognition
- video content
- image data
- input image
- learning algorithm
- visual data
- video database
- successive frames
- image features
- video classification
- textual descriptions
- images and video sequences
- multimedia
- video analysis
- image sequences
- image retrieval
- image database
- image classification
- test images
- sports video
- natural language descriptions
- input video
- video indexing
- space time
- content based retrieval
- video segments
- video search
- key frames
- video retrieval
- video clips
- bounding box
- object segmentation