Dynamic Sampling Networks for Efficient Action Recognition in Videos

by   Yin-Dong Zheng, et al.

The existing action recognition methods are mainly based on clip-level classifiers such as two-stream CNNs or 3D CNNs, which are trained from the randomly selected clips and applied to densely sampled clips during testing. However, this standard setting might be suboptimal for training classifiers and also requires huge computational overhead when deployed in practice. To address these issues, we propose a new framework for action recognition in videos, called Dynamic Sampling Networks (DSN), by designing a dynamic sampling module to improve the discriminative power of learned clip-level classifiers and as well increase the inference efficiency during testing. Specifically, DSN is composed of a sampling module and a classification module, whose objective is to learn a sampling policy to on-the-fly select which clips to keep and train a clip-level classifier to perform action recognition based on these selected clips, respectively. In particular, given an input video, we train an observation network in an associative reinforcement learning setting to maximize the rewards of the selected clips with a correct prediction. We perform extensive experiments to study different aspects of the DSN framework on four action recognition datasets: UCF101, HMDB51, THUMOS14, and ActivityNet v1.3. The experimental results demonstrate that DSN is able to greatly improve the inference efficiency by only using less than half of the clips, which can still obtain a slightly better or comparable recognition accuracy to the state-of-the-art approaches.


page 1

page 3

page 11


SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition

While many action recognition datasets consist of collections of brief, ...

Temporal Segment Networks for Action Recognition in Videos

Deep convolutional networks have achieved great success for image recogn...

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

Action recognition is an open and challenging problem in computer vision...

Efficient Action Recognition Using Confidence Distillation

Modern neural networks are powerful predictive models. However, when it ...

GCF-Net: Gated Clip Fusion Network for Video Action Recognition

In recent years, most of the accuracy gains for video action recognition...

Skimming and Scanning for Untrimmed Video Action Recognition

Video action recognition (VAR) is a primary task of video understanding,...

Combining Deep Learning Classifiers for 3D Action Recognition

The popular task of 3D human action recognition is almost exclusively so...

Please sign up or login with your details

Forgot password? Click here to reset