@inproceedings{singh-etal-2021-efficient,
title = "An Efficient Keyframes Selection Based Framework for Video Captioning",
author = "Singh, Alok and
Sanayai Meetei, Loitongbam and
Singh, Salam Michael and
Singh, Thoudam Doren and
Bandyopadhyay, Sivaji",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.29",
pages = "240--250",
abstract = "Describing a video is a challenging yet attractive task since it falls into the intersection of computer vision and natural language generation. The attention-based models have reported the best performance. However, all these models follow similar procedures, such as segmenting videos into chunks of frames or sampling frames at equal intervals for visual encoding. The process of segmenting video into chunks or sampling frames at equal intervals causes encoding of redundant visual information and requires additional computational cost since a video consists of a sequence of similar frames and suffers from inescapable noise such as uneven illumination, occlusion and motion effects. In this paper, a boundary-based keyframes selection approach for video description is proposed that allow the system to select a compact subset of keyframes to encode the visual information and generate a description for a video without much degradation. The proposed approach uses 3 4 frames per video and yields competitive performance over two benchmark datasets MSVD and MSR-VTT (in both English and Hindi).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2021-efficient">
<titleInfo>
<title>An Efficient Keyframes Selection Based Framework for Video Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loitongbam</namePart>
<namePart type="family">Sanayai Meetei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="given">Michael</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thoudam</namePart>
<namePart type="given">Doren</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Describing a video is a challenging yet attractive task since it falls into the intersection of computer vision and natural language generation. The attention-based models have reported the best performance. However, all these models follow similar procedures, such as segmenting videos into chunks of frames or sampling frames at equal intervals for visual encoding. The process of segmenting video into chunks or sampling frames at equal intervals causes encoding of redundant visual information and requires additional computational cost since a video consists of a sequence of similar frames and suffers from inescapable noise such as uneven illumination, occlusion and motion effects. In this paper, a boundary-based keyframes selection approach for video description is proposed that allow the system to select a compact subset of keyframes to encode the visual information and generate a description for a video without much degradation. The proposed approach uses 3 4 frames per video and yields competitive performance over two benchmark datasets MSVD and MSR-VTT (in both English and Hindi).</abstract>
<identifier type="citekey">singh-etal-2021-efficient</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.29</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>240</start>
<end>250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Efficient Keyframes Selection Based Framework for Video Captioning
%A Singh, Alok
%A Sanayai Meetei, Loitongbam
%A Singh, Salam Michael
%A Singh, Thoudam Doren
%A Bandyopadhyay, Sivaji
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F singh-etal-2021-efficient
%X Describing a video is a challenging yet attractive task since it falls into the intersection of computer vision and natural language generation. The attention-based models have reported the best performance. However, all these models follow similar procedures, such as segmenting videos into chunks of frames or sampling frames at equal intervals for visual encoding. The process of segmenting video into chunks or sampling frames at equal intervals causes encoding of redundant visual information and requires additional computational cost since a video consists of a sequence of similar frames and suffers from inescapable noise such as uneven illumination, occlusion and motion effects. In this paper, a boundary-based keyframes selection approach for video description is proposed that allow the system to select a compact subset of keyframes to encode the visual information and generate a description for a video without much degradation. The proposed approach uses 3 4 frames per video and yields competitive performance over two benchmark datasets MSVD and MSR-VTT (in both English and Hindi).
%U https://aclanthology.org/2021.icon-main.29
%P 240-250
Markdown (Informal)
[An Efficient Keyframes Selection Based Framework for Video Captioning](https://aclanthology.org/2021.icon-main.29) (Singh et al., ICON 2021)
ACL
- Alok Singh, Loitongbam Sanayai Meetei, Salam Michael Singh, Thoudam Doren Singh, and Sivaji Bandyopadhyay. 2021. An Efficient Keyframes Selection Based Framework for Video Captioning. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 240–250, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).