Back to Search
Start Over
Action Recognition with Spatial-Temporal Representation Analysis Across Grassmannian Manifold and Euclidean Space
- Source :
- ICIP
- Publication Year :
- 2018
- Publisher :
- IEEE, 2018.
-
Abstract
- Action recognition plays an important character for numerous tasks of video area. Although previous works often learn the appearance and motion information with Convolutional Neural Networks (CNNs), they ignore the corresponding space structures of video representation. In this work, we address action recognition task with a Spatial-Temporal representation analysis algorithm Across Grassmannian manifold and Euclidean space (ST-AGE), which considers the appearance and motion information of video samples in an unified framework. For each video sample, we extract temporal features with classical CNNs (e.g., ConvNet, VGG, ResNet) and motion representation with the trajectory tracking method. Both spatial and temporal information can be then analyzed by embedding them on the Grassmannian manifold and Euclidean space, and an appropriate multi-kernel SVM is further conducted. Comprehensive evaluations on HMDB-51 and UCF-101 datasets demonstrate the significant superiority of STAGE over other state-of-the-art for human action recognition.
- Subjects :
- Artificial neural network
Computer science
Euclidean space
business.industry
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Representation (systemics)
Motion (geometry)
Pattern recognition
02 engineering and technology
010501 environmental sciences
01 natural sciences
Convolutional neural network
Manifold
Support vector machine
0202 electrical engineering, electronic engineering, information engineering
Embedding
020201 artificial intelligence & image processing
Artificial intelligence
business
0105 earth and related environmental sciences
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2018 25th IEEE International Conference on Image Processing (ICIP)
- Accession number :
- edsair.doi...........1d5f6bc1bd00c4875ff1e643d5711add