Filters








58,377 Hits in 7.3 sec

From Text Detection in Videos to Person Identification

Johann Poignant, Laurent Besacier, Georges Quenot, Franck Thollard
2012 2012 IEEE International Conference on Multimedia and Expo  
We present in this article a video OCR system that detects and recognizes overlaid texts in video as well as its application to person identification in video documents. We proceed in several steps.  ...  The semi-supervised adaptation of this system to a particular video type (video broadcast from a French TV) is proposed and evaluated.  ...  Identification of a person that appears in videos raises a lot of interest in the information research community.  ... 
doi:10.1109/icme.2012.119 dblp:conf/icmcs/PoignantBQT12 fatcat:5vrtesrrvrf7lph2eyhboh4s7y

Running Event Visualization using Videos from Multiple Cameras [article]

Yeshwanth Napolean, Priadi Teguh Wibowo, Jan van Gemert
2019 arXiv   pre-print
One is scene text detection which recognizes the runners by detecting a unique 'bib number' attached to their clothes and the other is person re-identification which detects the runners based on their  ...  The bib numbers of runners known to occur in the frame are used to filter irrelevant text and numbers detected. Except for this filtering step, no supervisory signal is used.  ...  In this work, we use scene text recognition both as a baseline and to collect training samples for a person re-identification method downstream in our pipeline for runner identification.  ... 
arXiv:1909.02835v1 fatcat:bbnkoeg2tbd6rahkg3zjmtubxa

Automated Sports Player Performance Analysis: A Survey

احمد نادى, أمل أبوطبل, Ayman Atia
2021 النشرة المعلوماتیة فی الحاسبات والمعلومات  
In order to make the automatic sports video analysis realized, there is a necessity for player identification across sports.  ...  Identifying players in sports videos is a major research challenge due to low video resolution per player, camera perspective, variation of the posture of player, illumination conditions, variety of sports  ...  PLAYER IDENTIFICATION BASED PERSON RE-ID The player identification from medium distance in basketball broadcast videos is formulated as a person re-identification problem in which the player is recognized  ... 
doi:10.21608/fcihib.2021.61283.1019 fatcat:gt57kgphgffp5ai262jxam3qqm

Text detection and recognition for person identification in videos

Johann Poignant, Franck Thollard, Georges Quenot, Laurent Besacier
2011 2011 9th International Workshop on Content-Based Multimedia Indexing (CBMI)  
This article presents a demo of person search in audiovisual broadcast using only the text available in a video and in resources external to the video.  ...  We also present the different steps used to recognize characters in video for multi-modal person recognition systems.  ...  Conclusion and further work This work allows us to assess the contribution that OCR can provide person name detection from video.  ... 
doi:10.1109/cbmi.2011.5972553 dblp:conf/cbmi/PoignantTQB11 fatcat:mhfwza5fqzbxraudq3cbqhqcea

An attribute based news video indexing

Ichiro Ide, Reiko Hamada, Shuichi Sakai, Hideohiko Tanaka
2001 Proceedings of the 2001 ACM workshops on Multimedia multimedia information retrieval - MULTIMEDIA '01  
The overall result showed comparable performance to existing systems in the case of personal name -character indexing.  ...  In this paper, both text and image attribute analysis is briefly introduced, and the result of the final indexing is displayed.  ...  names derived from texts in the video [8] .  ... 
doi:10.1145/500951.500955 fatcat:7hhpof7jynhxjas46zkug3xndi

An attribute based news video indexing

Ichiro Ide, Reiko Hamada, Shuichi Sakai, Hideohiko Tanaka
2001 Proceedings of the 2001 ACM workshops on Multimedia multimedia information retrieval - MULTIMEDIA '01  
The overall result showed comparable performance to existing systems in the case of personal name -character indexing.  ...  In this paper, both text and image attribute analysis is briefly introduced, and the result of the final indexing is displayed.  ...  names derived from texts in the video [8] .  ... 
doi:10.1145/500933.500955 dblp:conf/mm/IdeHST01 fatcat:i2uptdm6cjccnmjkt2v7ilmgy4

Fusion of Speech, Faces and Text for Person Identification in TV Broadcast [chapter]

Hervé Bredin, Johann Poignant, Makarand Tapaswi, Guillaume Fortier, Viet Bac Le, Thibault Napoleon, Hua Gao, Claude Barras, Sophie Rosset, Laurent Besacier, Jakob Verbeek, Georges Quénot (+2 others)
2012 Lecture Notes in Computer Science  
Speaker identification (and face recognition) can be greatly improved when combined with name detection through video optical character recognition.  ...  In this paper, we describe, evaluate and discuss QCompere consortium submissions to the 2012 Repere evaluation campaign dry-run.  ...  Similarly, visual person recognition cannot rely on name detection in overlaid text, for instance.  ... 
doi:10.1007/978-3-642-33885-4_39 fatcat:k4tsmhlqgbhb3n276byfpjaewm

CIMWOS: A MULTIMEDIA, MULTIMODAL AND MULTILINGUAL INDEXING AND RETRIEVAL SYSTEM

H. PAPAGEORGIOU, A. PROTOPAPAS
2003 Digital Media Processing for Multimedia Interactive Services  
Image processing includes video segmentation and key frame extraction, face detection and face identification, object and scene recognition, video text detection and character recognition.  ...  An ergonomic and user-friendly web-based interface allows the user to efficiently retrieve video segments by a combination of media description, content metadata and natural language text.  ...  A central problem in face recognition is to distinguish between variations in appearance of the same person due to such differences from variations between different persons.  ... 
doi:10.1142/9789812704337_0102 fatcat:vjhi65k6x5d43drbjokwqze7r4

Automatic person information extraction using overlay text in television news interview videos

Sanghee Lee, Kanghyun Jo
2017 2017 IEEE 15th International Conference on Industrial Informatics (INDIN)  
To make the automatic person indexing of interview video in the TV news program, this paper proposes the method to only detect the name text line among the whole overlay texts in one frame.  ...  Many overlay texts are artificially superimposed on the broadcasting videos by humans. These texts provide additional information to the audiovisual content.  ...  Among these applications, the identification of the person from the overlaid text raises a lot of interest in the information research community.  ... 
doi:10.1109/indin.2017.8104837 dblp:conf/indin/LeeJ17 fatcat:fovbyjlgezhv3jgkimy5rabytu

Novel Methods for Forensic Multimedia Data Analysis: Part II [chapter]

Petra Perner
2020 Digital Forensic Science [Working Title]  
We address our work toward speech, video and images, handwriting and text documents.  ...  The methods and techniques will form a toolkit that can be used for different cases in a court of law in order to extract information from different multimedia sources.  ...  Blind methods for detecting image forgery In order to trust the information extracted from images and videos, it is necessary to make sure that the image and video have been recorded by a camera and that  ... 
doi:10.5772/intechopen.92548 fatcat:oo2pjx6la5eqzm3rcph6bog6ie

De-identification for privacy protection in multimedia content: A survey

Slobodan Ribaric, Aladdin Ariyaeeinia, Nikola Pavesic
2016 Signal processing. Image communication  
De-identification is one of the main approaches to privacy protection in multimedia contents (text, still images, audio and video sequences and their combinations).  ...  It is a process for concealing or removing personal identifiers, or replacing them by surrogate personal identifiers in personal information in order to prevent the disclosure and use of data for purposes  ...  It is also the result of activities in COST Action IC1206 "De-identification for Privacy Protection in Multimedia Content".  ... 
doi:10.1016/j.image.2016.05.020 fatcat:lumwotiefzfqxpuxgkeym56dyy

Multi-Modal Person-Profiles from Broadcast News Video

Charlie K. Dagli, Sharad V. Rao, Thomas S. Huang
2007 Multimedia and Expo, 2007 IEEE International Conference on  
Indexing videos in this matter helps facilitate a unique way to create multimedia person databases automatically, as well as for attacking existing video analysis tasks.  ...  In this work we propose the holistic use of both audio, visual and textual information for the automatic indexing of broadcast news video to create person-profiles.  ...  The text data in this work was obtained from transcripts from LexisNexis (www.lexisnexis.com) and were mined to discover all the names of speakers in a particular news video.  ... 
doi:10.1109/icme.2007.4284961 dblp:conf/icmcs/DagliRH07 fatcat:pjnfvpnt25eprbb2bsiqxyrpre

Key Event Detection in Video using ASR and Visual Data

Niraj Shrestha, Aparna N. Venkitasubramanian, Marie-Francine Moens
2014 Proceedings of the Third Workshop on Vision and Language  
The error is only slightly higher when using ASR output in the detection of key events and their participants in the wedding videos compared to the results obtained with subtitles.  ...  In this paper, we present preliminary work on key event detection in British royal wedding videos using automatic speech recognition (ASR) and visual data.  ...  than trying to align all persons mentioned in the texts.  ... 
doi:10.3115/v1/w14-5407 dblp:conf/acl-vl/ShresthaVM14 fatcat:gjy447zno5etnjo23zdztlmkzi

Scene understanding for identifying persons in TV shows: Beyond face authentication

Mickael Rouvier, Benoit Favre, Meriem Bendris, Delphine Charlet, Geraldine Damnati
2014 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI)  
In this paper, we focus on the problem of person identification beyond face authentication in order to improve the identification results and not only where the face is detectable.  ...  Our goal is to automatically identify people in TV news and debates without any predefined dictionary of people.  ...  Amongst overlaid text boxes that can be detected in a video, we need to distinguish OPNs (that present a person on screen) from other texts (such as titles, locations, time, etc).  ... 
doi:10.1109/cbmi.2014.6849829 dblp:conf/cbmi/RouvierFBCD14 fatcat:m7zmsup6f5d4hemhpxvhj3t4ii

Comparison of Text Beginning Frame Detection Methods in News Video Sequences
뉴스 비디오 시퀀스에서 텍스트 시작 프레임 검출 방법의 비교

Sanghee Lee, Jungil Ahn, Kanghyun Jo
2016 Journal of Broadcast Engineering  
This paper proposes the identification of the overlay text beginning frame to help the detection and recognition of the overlay text in news videos.  ...  To make this indexing system in the TV news program, it is important to detect and recognize the texts.  ...  person indexing of interview video in TV news program.  ... 
doi:10.5909/jbe.2016.21.3.307 fatcat:s6c6bbb5mzhylofe3ollsashwq
« Previous Showing results 1 — 15 out of 58,377 results