Dynamic Image Networks for Action Recognition
University of Oxford · Australian National University · +1 more institution
Abstract
We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis especially when convolutional neural networks (CNNs) are used. The dynamic image is based on the rank pooling concept and is obtained through the parameters of a ranking machine that encodes the temporal evolution of the frames of the video. Dynamic images are obtained by directly applying rank pooling on the raw image pixels of a video producing a single RGB image per video. This idea is simple but powerful as it enables the use of existing CNN models directly on video data with fine-tuning. We present an efficient and effective approximate rank pooling operator, speeding it up orders of magnitude…
Citation impact
- FWCI
- 52.37
- Percentile
- 100%
- References
- 44
Authors
5Topics & keywords
- Pooling
- Computer science
- Artificial intelligence
- Convolutional neural network
- Rank (graph theory)
- Representation (politics)
- Pattern recognition (psychology)
- RGB color model