The purpose of this project is to focus in exploring deep learning methods for multimodal person recognition in video sequences. The project will be carried out in the context of unsupervised person annotation systems for broadcast TV programs. Person annotation aims to determining who and where appears in a video sequence. We decide to improve the detection, recognition and track of the text in that systems. We examine different techniques and implementations obtaining a great results for each block of the project and this evaluations gives us some future developments to improve more the system.El propósito de este proyecto es centrarse en la exploración de métodos de aprendizaje profundo para el reconocimiento de personas multimodales en ...
Television networks need to monitorize, adding metadatas to the contents, everything that happens in...
International audienceThis paper describes a multi-modal person recognition system for video broadca...
The annotation of video streams by automatic content analysis is a growing field of research. The po...
The purpose of this project is to focus in exploring deep learning methods for multimodal person rec...
In the recent years, the demand for unsupervised annotation tools to annotate and classify large aud...
Nowadays, Artificial Intelligence in computation vision is widely used, and there are constant impro...
In unsupervised identity recognition in video sequences systems, which is a very active field of res...
In the recent years, the demand for video tools to automatically annotate and classify large audiovi...
Recogniton of peple by speech and face in TV shows. Participation in the international competition M...
The enormous amount of visual data generated nowadays creates a strong need for annotation tools to ...
The main topics addressed in this thesis are the use of active learning and deep learning methods in...
This paper describes a multi-modal person recognition sys-tem for video broadcast developed for part...
L'analyse automatique de contenu des vidéos en vue de leur annotation est un domaine de recherche en...
Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona...
International audienceIn this paper an approach to human annotation propagation for person identific...
Television networks need to monitorize, adding metadatas to the contents, everything that happens in...
International audienceThis paper describes a multi-modal person recognition system for video broadca...
The annotation of video streams by automatic content analysis is a growing field of research. The po...
The purpose of this project is to focus in exploring deep learning methods for multimodal person rec...
In the recent years, the demand for unsupervised annotation tools to annotate and classify large aud...
Nowadays, Artificial Intelligence in computation vision is widely used, and there are constant impro...
In unsupervised identity recognition in video sequences systems, which is a very active field of res...
In the recent years, the demand for video tools to automatically annotate and classify large audiovi...
Recogniton of peple by speech and face in TV shows. Participation in the international competition M...
The enormous amount of visual data generated nowadays creates a strong need for annotation tools to ...
The main topics addressed in this thesis are the use of active learning and deep learning methods in...
This paper describes a multi-modal person recognition sys-tem for video broadcast developed for part...
L'analyse automatique de contenu des vidéos en vue de leur annotation est un domaine de recherche en...
Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona...
International audienceIn this paper an approach to human annotation propagation for person identific...
Television networks need to monitorize, adding metadatas to the contents, everything that happens in...
International audienceThis paper describes a multi-modal person recognition system for video broadca...
The annotation of video streams by automatic content analysis is a growing field of research. The po...