Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Sridhar Swaminathan"'
Publikováno v:
Neurocomputing. 398:185-196
Storing and processing millions of parameters in deep neural networks is highly challenging during the deployment of model in real-time application on resource constrained devices. Popular low-rank approximation approach singular value decomposition
Autor:
Rajkumar Kannan, Frederic Andres, Kalaiarasi Sonai Muthu Anbananthen, Sridhar Swaminathan, Gheorghita Ghinea
Publikováno v:
International Journal of Multimedia Data Engineering and Management. 10:1-26
Video summarization condenses a video by extracting its informative and interesting segments. In this article, a novel video summarization approach is proposed based on spatiotemporal salient region detection. The proposed approach first segments a v
Publikováno v:
IAIT
Social media is more and more utilized by people around the world to express their feelings and opinions in the kind of short text messages. Twitter has been a rapidly growing microblogging social networking website where people express their opinion
Publikováno v:
BigMM
Multimodal emotion recognition is a challenging task because emotions can be expressed through various forms and modalities. It can be applied in various fields, for example, human-computer interaction, crime, healthcare, multimedia retrieval, etc. I
Publikováno v:
International Journal of Computer Applications. 180:22-30
Publikováno v:
IEEE Signal Processing Letters. 22:686-690
In this letter, a novel salient region detection approach is proposed. Firstly, color contrast cue and color distribution cue are computed by exploiting patch level and region level image abstractions in a unified way, where these two cues are fused
Publikováno v:
Information Processing & Management. 51:286-305
A novel personalized semantic movie summarization approach is proposed.User's subjective preferences are exploited for personalized movie summarization.An extensive user study demonstrates the advantages of the proposed system.A subjective study show
Publikováno v:
ICAPR
This paper presents a new methodology to extract discriminative features from images, that are robust and invariant to image blur and JPEG compression. The local patches are quantized in the polar geometric structure using Log Polar Transformation (L
Detecting salient objects from images and videos has many useful applications in computer vision. In this paper, a novel spatiotemporal salient region detection approach is proposed. The proposed approach computes spatiotemporal saliency by estimatin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::712382f76fc167afda86e6e42e55745e
http://bura.brunel.ac.uk/handle/2438/11462
http://bura.brunel.ac.uk/handle/2438/11462
Publikováno v:
ISSPIT
This paper presents a new methodology for image description to extract discriminative features from images, that are robust and invariant to illumination changes. The proposed approach describes the image features using multisupport interest regions.