Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain
With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the two most common problematic issues related to video processing algorithms. Most of the existing methods mainly focused on increasing accuracy by exploring consecutive frames, which is laborious and cannot be considered for real-time applications. Since videos are mostly stored and transmitted in compressed format, these kinds of videos are available on many devices. Compressed videos contain a multitude of beneficial information, such as motion vectors and quantized coefficients. Proper use of this available information can greatly improve the video understanding methods' performance. This paper presents an approach for using residual data, available in compressed videos directly, which can be obtained by a light partially decoding procedure. In addition, a method for accumulating similar residuals is proposed, which dramatically reduces the number of processed frames for action recognition. Applying neural networks exclusively for accumulated residuals in the compressed domain accelerates performance, while the classification results are highly competitive with raw video approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionVideo UnderstandingSimilar Papers 제목 키워드 기반
Dynamic Image Networks for Action Recognition
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 …
Action RecognitionTemporal Action LocalizationTemporal Residual Networks for Dynamic Scene Recognition
This paper combines three contributions to establish a new state-of-the-art in dynamic scene recognition. First, we present a novel ConvNet architecture based on temporal residual units that is fully convolutional in spa…
Action RecognitionScene RecognitionTemporal Action LocalizationOnline Action Recognition based on Incremental Learning of Weighted Covariance Descriptors
Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from unsegmented streams of data in a continuous manner. One way for online recognition is based …
Action RecognitionIncremental LearningTemporal Action LocalizationMulti-scale Deep Neural Networks for Solving High Dimensional PDEs
In this paper, we propose the idea of radial scaling in frequency domain and activation functions with compact support to produce a multi-scale DNN (MscaleDNN), which will have the multi-scale capability in approximating…
Vocal Bursts Intensity PredictionResiduals-based Offline Reinforcement Learning
Offline reinforcement learning (RL) has received increasing attention for learning policies from previously collected data without interaction with the real environment, which is particularly important in high-stakes app…
Reinforcement LearningOffline RL