UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition.
Xiaohan DingYiyuan ZhangYixiao GeSijie ZhaoLin SongXiangyu YueYing ShanPublished in: CoRR (2023)
Keyphrases
- image recognition
- point cloud
- audio video
- multimedia
- structure from motion
- stereo camera
- point sets
- pattern recognition
- image classification
- laser scanner
- face recognition
- point cloud data
- multi party
- online video
- service management
- feature space
- machine learning
- high dimensional
- affine invariant
- hough transform
- image features
- image retrieval
- image processing
- computer vision
- neural network