TRECVID 2012 GENIE: Multimedia event detection and recounting

A. G. Amitha Perera; Sangmin Oh; Megha Pandey; Tianyang Ma; Anthony Hoogs; Arash Vahdat; Kevin Cannons; Hossein Hajimirsadeghi; Greg Mori; Scott McCloskey; Ben Miller; Sharath Venkatesha; Pedro Davalos; Pradipto Das; Chenliang Xu; Jason Corso; Rohini Srihari; Ilseo Kim; You Chi Cheng; Zhen Huang; Chin Hui Lee; Kevin Tang; L. Fei-Fei; Daphne Koller

TRECVID 2012 GENIE: Multimedia event detection and recounting

A. G. Amitha Perera, Sangmin Oh, Megha Pandey, Tianyang Ma, Anthony Hoogs, Arash Vahdat, Kevin Cannons, Hossein Hajimirsadeghi, Greg Mori, Scott McCloskey, Ben Miller, Sharath Venkatesha, Pedro Davalos, Pradipto Das, Chenliang Xu, Jason Corso, Rohini Srihari, Ilseo Kim, You Chi Cheng, Zhen HuangChin Hui Lee, Kevin Tang, L. Fei-Fei, Daphne Koller

Department of Computer Science

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

5 Scopus citations

Abstract

Our MED 12 system is an extension of our MED 11 system [12], and consists of a collection of lowlevel and high-level features, feature-specific classifiers built upon those features, and a fusion system that combines features both through mid-level kernel fusion and score fusion. We have incorporated large number of audio-visual features in our new system and incorporated diverse types of standard and newly developed event agents which learn the salient audio-visual characteristics of event classes. The combination of additional features and newly developed powerful event agents improve our MED performance substantially beyond our MED 11 results. In addition, our MER 12 submissions reported recounting of specified clips for all five MER events and additionally provided MER results for all the clips detected by MED system. Our MER system generated recounting of detections based on CDR features and synopsis provided as part of the EventKits and DEVT datasets. The MER evaluation results are promising for event-level discrimination, and indicated further improvement to be made for clip-level discrimination.

Original language	English
State	Published - 2012
Event	TREC Video Retrieval Evaluation, TRECVID 2012 - Gaithersburg, MD, United States Duration: 26 Nov 2012 → 28 Nov 2012

Conference

Conference	TREC Video Retrieval Evaluation, TRECVID 2012
Country/Territory	United States
City	Gaithersburg, MD
Period	26/11/12 → 28/11/12

Cite this

Amitha Perera, A. G., Oh, S., Pandey, M., Ma, T., Hoogs, A., Vahdat, A., Cannons, K., Hajimirsadeghi, H., Mori, G., McCloskey, S., Miller, B., Venkatesha, S., Davalos, P., Das, P., Xu, C., Corso, J., Srihari, R., Kim, I., Cheng, Y. C., ... Koller, D. (2012). TRECVID 2012 GENIE: Multimedia event detection and recounting. Paper presented at TREC Video Retrieval Evaluation, TRECVID 2012, Gaithersburg, MD, United States.

@conference{a729114cca734f5ca15c3058ff257f56,

title = "TRECVID 2012 GENIE: Multimedia event detection and recounting",

abstract = "Our MED 12 system is an extension of our MED 11 system [12], and consists of a collection of lowlevel and high-level features, feature-specific classifiers built upon those features, and a fusion system that combines features both through mid-level kernel fusion and score fusion. We have incorporated large number of audio-visual features in our new system and incorporated diverse types of standard and newly developed event agents which learn the salient audio-visual characteristics of event classes. The combination of additional features and newly developed powerful event agents improve our MED performance substantially beyond our MED 11 results. In addition, our MER 12 submissions reported recounting of specified clips for all five MER events and additionally provided MER results for all the clips detected by MED system. Our MER system generated recounting of detections based on CDR features and synopsis provided as part of the EventKits and DEVT datasets. The MER evaluation results are promising for event-level discrimination, and indicated further improvement to be made for clip-level discrimination.",

author = "{Amitha Perera}, {A. G.} and Sangmin Oh and Megha Pandey and Tianyang Ma and Anthony Hoogs and Arash Vahdat and Kevin Cannons and Hossein Hajimirsadeghi and Greg Mori and Scott McCloskey and Ben Miller and Sharath Venkatesha and Pedro Davalos and Pradipto Das and Chenliang Xu and Jason Corso and Rohini Srihari and Ilseo Kim and Cheng, {You Chi} and Zhen Huang and Lee, {Chin Hui} and Kevin Tang and L. Fei-Fei and Daphne Koller",

year = "2012",

language = "English",

note = "TREC Video Retrieval Evaluation, TRECVID 2012 ; Conference date: 26-11-2012 Through 28-11-2012",

}

Amitha Perera, AG, Oh, S, Pandey, M, Ma, T, Hoogs, A, Vahdat, A, Cannons, K, Hajimirsadeghi, H, Mori, G, McCloskey, S, Miller, B, Venkatesha, S, Davalos, P, Das, P, Xu, C, Corso, J, Srihari, R, Kim, I, Cheng, YC, Huang, Z, Lee, CH, Tang, K, Fei-Fei, L & Koller, D 2012, 'TRECVID 2012 GENIE: Multimedia event detection and recounting', Paper presented at TREC Video Retrieval Evaluation, TRECVID 2012, Gaithersburg, MD, United States, 26/11/12 - 28/11/12.

TY - CONF

T1 - TRECVID 2012 GENIE

T2 - TREC Video Retrieval Evaluation, TRECVID 2012

AU - Amitha Perera, A. G.

AU - Oh, Sangmin

AU - Pandey, Megha

AU - Ma, Tianyang

AU - Hoogs, Anthony

AU - Vahdat, Arash

AU - Cannons, Kevin

AU - Hajimirsadeghi, Hossein

AU - Mori, Greg

AU - McCloskey, Scott

AU - Miller, Ben

AU - Venkatesha, Sharath

AU - Davalos, Pedro

AU - Das, Pradipto

AU - Xu, Chenliang

AU - Corso, Jason

AU - Srihari, Rohini

AU - Kim, Ilseo

AU - Cheng, You Chi

AU - Huang, Zhen

AU - Lee, Chin Hui

AU - Tang, Kevin

AU - Fei-Fei, L.

AU - Koller, Daphne

PY - 2012

Y1 - 2012

N2 - Our MED 12 system is an extension of our MED 11 system [12], and consists of a collection of lowlevel and high-level features, feature-specific classifiers built upon those features, and a fusion system that combines features both through mid-level kernel fusion and score fusion. We have incorporated large number of audio-visual features in our new system and incorporated diverse types of standard and newly developed event agents which learn the salient audio-visual characteristics of event classes. The combination of additional features and newly developed powerful event agents improve our MED performance substantially beyond our MED 11 results. In addition, our MER 12 submissions reported recounting of specified clips for all five MER events and additionally provided MER results for all the clips detected by MED system. Our MER system generated recounting of detections based on CDR features and synopsis provided as part of the EventKits and DEVT datasets. The MER evaluation results are promising for event-level discrimination, and indicated further improvement to be made for clip-level discrimination.

AB - Our MED 12 system is an extension of our MED 11 system [12], and consists of a collection of lowlevel and high-level features, feature-specific classifiers built upon those features, and a fusion system that combines features both through mid-level kernel fusion and score fusion. We have incorporated large number of audio-visual features in our new system and incorporated diverse types of standard and newly developed event agents which learn the salient audio-visual characteristics of event classes. The combination of additional features and newly developed powerful event agents improve our MED performance substantially beyond our MED 11 results. In addition, our MER 12 submissions reported recounting of specified clips for all five MER events and additionally provided MER results for all the clips detected by MED system. Our MER system generated recounting of detections based on CDR features and synopsis provided as part of the EventKits and DEVT datasets. The MER evaluation results are promising for event-level discrimination, and indicated further improvement to be made for clip-level discrimination.

UR - http://www.scopus.com/inward/record.url?scp=84905227466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905227466&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84905227466

Y2 - 26 November 2012 through 28 November 2012

ER -

TRECVID 2012 GENIE: Multimedia event detection and recounting

Abstract

Conference

Other files and links

Fingerprint

Cite this