2016
DOI: 10.48550/arxiv.1604.03498
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring

Wenying Ma,
Liangliang Cao,
Lei Yu
et al.

Abstract: Fisher vector has been widely used in many multimedia retrieval and visual recognition applications with good performance. However, the computation complexity prevents its usage in real-time video monitoring. In this work, we proposed and implemented GPU-FV, a fast Fisher vector extraction method with the help of modern GPUs. The challenge of implementing Fisher vector on GPUs lies in the data dependency in feature extraction and expensive memory access in Fisher vector computing. To handle these challenges, w… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2018
2018
2018
2018

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 26 publications
0
1
0
Order By: Relevance
“…Wang et al further analyzed the workload of SIFT in [16] and proposed to distribute the feature extraction tasks to CPU and GPU, such that a speed of 10 fps for a 320 × 256 image and 41% energy consumption reduction can be achieved. Besides SIFT, the speeded-up robust feature (SURF) [3], [18] and fisher vectors (FV) [19] were also explored in implementing using GPU platform, and around an order of magnitude speedup was achieved compared to CPU based implementation. Besides hand-crafted features, recently convolutional neural network based features have achieved promising performance in various computer vision tasks such as image classification [20] and retrieval [21].…”
Section: B Review Of Gpu Based Feature Extractionmentioning
confidence: 99%
“…Wang et al further analyzed the workload of SIFT in [16] and proposed to distribute the feature extraction tasks to CPU and GPU, such that a speed of 10 fps for a 320 × 256 image and 41% energy consumption reduction can be achieved. Besides SIFT, the speeded-up robust feature (SURF) [3], [18] and fisher vectors (FV) [19] were also explored in implementing using GPU platform, and around an order of magnitude speedup was achieved compared to CPU based implementation. Besides hand-crafted features, recently convolutional neural network based features have achieved promising performance in various computer vision tasks such as image classification [20] and retrieval [21].…”
Section: B Review Of Gpu Based Feature Extractionmentioning
confidence: 99%