Two Are Better than One: When Audio Comes to the Rescue of Video

نویسندگان

  • Alberto Albiol
  • Luis Torres
  • Edward J. Delp
چکیده

This paper presents a system that automatically recognizes people in video sequences. To that end, audio and video information is used to obtain a confidence value that indicates the likelihood that a specific person appears in a video shot. Finally, a post-classifier is used to fuse audio and visual confidence values. The system has been tested on several news sequences and the results indicate that a significant improvement in the recognition rate can be achieved when both modalities are used together.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

P1: Negative Television and Memory

According to reports about 30-thousand people spent watching television had the impact on their memory and recall that the results showed no differences between men and women. The people who watched less than an hour a day did better at every memory function. As these contributors watched negative political ads, physiological responses indicated that their body was reflexively preparing to move...

متن کامل

A statistical approach to classify Skype traffic

Abstract- Skype is one of the most powerful and high-quality chat tools that allows its users to use of many services such as: transferring audio, sending messages, video conferencing and audio for free. Skype traffic has a lot of Internet traffic. Hence, Internet service providers need to identify traffic to do the quality of service and network management. On the other hand, Skype developers ...

متن کامل

Face Recognition: When Audio Comes to the Rescue of Video

This paper presents a system that automatically recognizes people in video sequences. To that end, audio and video information is used to obtain confidence values that indicate the likelihood that a specific person appears in a video shot. Finally, a post-classifier is used to fuse audio and visual confidence values. The system has been tested on several news sequences and the results indicate ...

متن کامل

Vodcast: A Breakthrough in Developing Incidental Vocabulary Learning

Incidental vocabulary learning is often seen as superior to direct instruction on many occasions. Meanwhile, upon the emergence of the World Wide Web, second language (SL) learners have been introduced to 'podcasts' (recorded audio and video online broadcasts) which could be authentic sources of vocabulary learning. The relatively recent phenomenon of video podcast (vodcast) might be considered...

متن کامل

Task-Based Listening Assessment and the Influence of Construct-Irrelevant Variance

Task-based listening tests such as IELTS require testees to listen to some information on a CD and simultaneously answer the related items. To answer such items, testees are expected to comprehend, analyze, compare and infer pieces of information while listening to the incoming audio material. The present research attempted to investigate whether the two major characteristics of question type a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003