Loss Switching Fusion with Similarity Search for Video Classification

Research output: Contribution to journalConference article

Abstract

From video streaming to security and surveillance applications , video data play an important role in our daily living today. However, managing a large amount of video data and retrieving the most useful information for the user remain a challenging task. In this paper, we propose a novel video classification system that would benefit the scene understanding task. We define our classification problem as classifying background and foreground motions using the same feature representation for outdoor scenes. This means that the feature representation needs to be robust enough and adaptable to different classification tasks. We propose a lightweight Loss Switching Fusion Network (LSFNet) for the fusion of spatiotemporal descriptors and a similarity search scheme with soft voting to boost the classification performance. The proposed system has a variety of potential applications such as content-based video clustering, video filtering, etc. Evaluation results on two private industry datasets show that our system is robust in both classifying different background motions and detecting human motions from these background motions.
Original languageEnglish
Number of pages5
JournalProceedings of the 26th International Conference on Image Processing (ICIP2019)
Publication statusAccepted/In press - 27 Jun 2019
EventIEEE International Conference on Image Processing 2019 - Taipai, Taiwan, Province of China
Duration: 22 Sep 201925 Sep 2019
http://2019.ieeeicip.org/

Fingerprint

Fusion reactions
Video streaming
Industry

Cite this

@article{a1bd4e2e8a64456ebe85d2ed402b6996,
title = "Loss Switching Fusion with Similarity Search for Video Classification",
abstract = "From video streaming to security and surveillance applications , video data play an important role in our daily living today. However, managing a large amount of video data and retrieving the most useful information for the user remain a challenging task. In this paper, we propose a novel video classification system that would benefit the scene understanding task. We define our classification problem as classifying background and foreground motions using the same feature representation for outdoor scenes. This means that the feature representation needs to be robust enough and adaptable to different classification tasks. We propose a lightweight Loss Switching Fusion Network (LSFNet) for the fusion of spatiotemporal descriptors and a similarity search scheme with soft voting to boost the classification performance. The proposed system has a variety of potential applications such as content-based video clustering, video filtering, etc. Evaluation results on two private industry datasets show that our system is robust in both classifying different background motions and detecting human motions from these background motions.",
keywords = "cs.CV, cs.LG",
author = "Lei Wang and Huynh, {Du Q.} and Mansour, {Moussa Reda}",
year = "2019",
month = "6",
day = "27",
language = "English",
journal = "Proceedings of the 26th International Conference on Image Processing (ICIP2019)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - Loss Switching Fusion with Similarity Search for Video Classification

AU - Wang, Lei

AU - Huynh, Du Q.

AU - Mansour, Moussa Reda

PY - 2019/6/27

Y1 - 2019/6/27

N2 - From video streaming to security and surveillance applications , video data play an important role in our daily living today. However, managing a large amount of video data and retrieving the most useful information for the user remain a challenging task. In this paper, we propose a novel video classification system that would benefit the scene understanding task. We define our classification problem as classifying background and foreground motions using the same feature representation for outdoor scenes. This means that the feature representation needs to be robust enough and adaptable to different classification tasks. We propose a lightweight Loss Switching Fusion Network (LSFNet) for the fusion of spatiotemporal descriptors and a similarity search scheme with soft voting to boost the classification performance. The proposed system has a variety of potential applications such as content-based video clustering, video filtering, etc. Evaluation results on two private industry datasets show that our system is robust in both classifying different background motions and detecting human motions from these background motions.

AB - From video streaming to security and surveillance applications , video data play an important role in our daily living today. However, managing a large amount of video data and retrieving the most useful information for the user remain a challenging task. In this paper, we propose a novel video classification system that would benefit the scene understanding task. We define our classification problem as classifying background and foreground motions using the same feature representation for outdoor scenes. This means that the feature representation needs to be robust enough and adaptable to different classification tasks. We propose a lightweight Loss Switching Fusion Network (LSFNet) for the fusion of spatiotemporal descriptors and a similarity search scheme with soft voting to boost the classification performance. The proposed system has a variety of potential applications such as content-based video clustering, video filtering, etc. Evaluation results on two private industry datasets show that our system is robust in both classifying different background motions and detecting human motions from these background motions.

KW - cs.CV

KW - cs.LG

M3 - Conference article

JO - Proceedings of the 26th International Conference on Image Processing (ICIP2019)

JF - Proceedings of the 26th International Conference on Image Processing (ICIP2019)

ER -