Internet video category recognition

Grant Schindler; Larry Zitnick; Matthew Brown

doi:10.1109/CVPRW.2008.4562960

Internet video category recognition

Grant Schindler, Larry Zitnick, Matthew Brown

Department of Computer Science

Research output: Contribution to conference › Paper › peer-review

21 Citations (SciVal)

234 Downloads (Pure)

Abstract

In this paper, we examine the problem of internet video categorization. Specifically, we explore the representation of a video as a ldquobag of wordsrdquo using various combinations of spatial and temporal descriptors. The descriptors incorporate both spatial and temporal gradients as well as optical flow information. We achieve state-of-the-art results on a standard human activity recognition database and demonstrate promising category recognition performance on two new databases of approximately 1000 and 1500 online user-submitted videos, which we will be making available to the community.

Original language	English
DOIs	https://doi.org/10.1109/CVPRW.2008.4562960
Publication status	Published - Jun 2008
Event	CVPRW '08: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008 - Anchorage Duration: 23 Jun 2008 → 28 Jun 2008

Conference

Conference	CVPRW '08: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008
City	Anchorage
Period	23/06/08 → 28/06/08

Access to Document

10.1109/CVPRW.2008.4562960

Brown_iv_2008.pdf
© 2008 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Accepted author manuscript, 2.14 MB

Cite this

@conference{02d7dace163b408ebf433fa5f736c104,

title = "Internet video category recognition",

abstract = "In this paper, we examine the problem of internet video categorization. Specifically, we explore the representation of a video as a ldquobag of wordsrdquo using various combinations of spatial and temporal descriptors. The descriptors incorporate both spatial and temporal gradients as well as optical flow information. We achieve state-of-the-art results on a standard human activity recognition database and demonstrate promising category recognition performance on two new databases of approximately 1000 and 1500 online user-submitted videos, which we will be making available to the community.",

author = "Grant Schindler and Larry Zitnick and Matthew Brown",

year = "2008",

month = jun,

doi = "10.1109/CVPRW.2008.4562960",

language = "English",

note = "CVPRW '08: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008 ; Conference date: 23-06-2008 Through 28-06-2008",

}

TY - CONF

T1 - Internet video category recognition

AU - Schindler, Grant

AU - Zitnick, Larry

AU - Brown, Matthew

PY - 2008/6

Y1 - 2008/6

N2 - In this paper, we examine the problem of internet video categorization. Specifically, we explore the representation of a video as a ldquobag of wordsrdquo using various combinations of spatial and temporal descriptors. The descriptors incorporate both spatial and temporal gradients as well as optical flow information. We achieve state-of-the-art results on a standard human activity recognition database and demonstrate promising category recognition performance on two new databases of approximately 1000 and 1500 online user-submitted videos, which we will be making available to the community.

AB - In this paper, we examine the problem of internet video categorization. Specifically, we explore the representation of a video as a ldquobag of wordsrdquo using various combinations of spatial and temporal descriptors. The descriptors incorporate both spatial and temporal gradients as well as optical flow information. We achieve state-of-the-art results on a standard human activity recognition database and demonstrate promising category recognition performance on two new databases of approximately 1000 and 1500 online user-submitted videos, which we will be making available to the community.

UR - http://dx.doi.org/10.1109/CVPRW.2008.4562960

U2 - 10.1109/CVPRW.2008.4562960

DO - 10.1109/CVPRW.2008.4562960

M3 - Paper

T2 - CVPRW '08: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008

Y2 - 23 June 2008 through 28 June 2008

ER -

Internet video category recognition

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this