scholarly journals Efficient Video Classification Using Fewer Frames

2019 ◽  
Author(s):  
Shweta Bhardwaj ◽  
Mukundhan Srinivasan ◽  
Mitesh M. Khapra
Keyword(s):  
Video Classification ◽  
Efficient Video

scholarly journals Watching a Small Portion could be as Good as Watching All: Towards Efficient Video Classification

2018 ◽  
Author(s):  
Hehe Fan ◽  
Zhongwen Xu ◽  
Linchao Zhu ◽  
Chenggang Yan ◽  
Jianjun Ge ◽  
...  
Keyword(s):  
Large Scale ◽  
Sampling Rate ◽  
Computational Cost ◽  
Confidence Score ◽  
Video Content ◽  
Video Classification ◽  
Video Frames ◽  
Similar Accuracy ◽  
Efficient Video

We aim to significantly reduce the computational cost for classification of temporally untrimmed videos while retaining similar accuracy. Existing video classification methods sample frames with a predefined frequency over entire video. Differently, we propose an end-to-end deep reinforcement approach which enables an agent to classify videos by watching a very small portion of frames like what we do. We make two main contributions. First, information is not equally distributed in video frames along time. An agent needs to watch more carefully when a clip is informative and skip the frames if they are redundant or irrelevant. The proposed approach enables the agent to adapt sampling rate to video content and skip most of the frames without the loss of information. Second, in order to have a confident decision, the number of frames that should be watched by an agent varies greatly from one video to another. We incorporate an adaptive stop network to measure confidence score and generate timely trigger to stop the agent watching videos, which improves efficiency without loss of accuracy. Our approach reduces the computational cost significantly for the large-scale YouTube-8M dataset, while the accuracy remains the same.

scholarly journals FASTER Recurrent Networks for Efficient Video Classification

2020 ◽  
Vol 34 (07) ◽  
pp. 13098-13105 ◽  
Author(s):  
Linchao Zhu ◽  
Du Tran ◽  
Laura Sevilla-Lara ◽  
Yi Yang ◽  
Matt Feiszli ◽  
...  
Keyword(s):  
Video Sequence ◽  
State Of The Art ◽  
Temporal Structure ◽  
Computational Cost ◽  
Recurrent Network ◽  
Recurrent Networks ◽  
Video Classification ◽  
Spatio Temporal ◽  
Temporal Redundancy ◽  
Efficient Video

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10× while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.

scholarly journals Space-Time Separate Modeling for Efficient Video Classification

2021 ◽  
Vol 2024 (1) ◽  
pp. 012063
Author(s):  
Pei Cao ◽  
Shuo Wang ◽  
Jinmeng Wu ◽  
Yanbin Hao
Keyword(s):  
Space Time ◽  
Video Classification ◽  
Efficient Video

Efficient Video Compression Algorithm in Secure Image Communication

2019 ◽  
Author(s):  
Bernatin T ◽  
Godwin premi M.S. ◽  
Narmadha R ◽  
Sahaya Anselin Nisha A
Keyword(s):  
Video Compression ◽  
Compression Algorithm ◽  
Image Communication ◽  
Efficient Video

A lazy feature selection method for multi-label classification

2021 ◽  
Vol 25 (1) ◽  
pp. 21-34
Author(s):  
Rafael B. Pereira ◽  
Alexandre Plastino ◽  
Bianca Zadrozny ◽  
Luiz H.C. Merschmann
Keyword(s):  
Feature Selection ◽  
Text Categorization ◽  
Feature Selection Method ◽  
Selection Method ◽  
Video Classification ◽  
Classification Problems ◽  
Class Label ◽  
New Feature ◽  
Feature Selection Techniques ◽  
Biomolecular Analysis

In many important application domains, such as text categorization, biomolecular analysis, scene or video classification and medical diagnosis, instances are naturally associated with more than one class label, giving rise to multi-label classification problems. This has led, in recent years, to a substantial amount of research in multi-label classification. More specifically, feature selection methods have been developed to allow the identification of relevant and informative features for multi-label classification. This work presents a new feature selection method based on the lazy feature selection paradigm and specific for the multi-label context. Experimental results show that the proposed technique is competitive when compared to multi-label feature selection techniques currently used in the literature, and is clearly more scalable, in a scenario where there is an increasing amount of data.

Sign in / Sign up

Export Citation Format

Share Document