Filters








44,728 Hits in 6.1 sec

Building A Large Concept Bank for Representing Events in Video [article]

Yin Cui, Dong Liu, Jiawei Chen, Shih-Fu Chang
2014 arXiv   pre-print
We train a Multiple Kernel Linear SVM for each discovered concept as a concept detector in Concept Bank.  ...  To construct the Concept Bank, we first gather a comprehensive event collection from WikiHow, a collaborative writing project that aims to build the world's largest manual for any possible How-To event  ...  Figure 1 illustrates an overview of how we build the proposed Concept Bank and use it to represent an event video.  ... 
arXiv:1403.7591v1 fatcat:yqkloogmrvfxfipgh75zpdcoaa

Masoud Mazloom

Unknown
2017 ACM SIGMultimedia Records  
We start from a large bank of concept detectors for representing events.  ...  In this thesis we aim to represent an event in a video using semantic features. We start from a bank of concept detectors for representing events in video.  ... 
doi:10.1145/3129151.3129158 fatcat:dy52usoz5bdjjczt63x2gxpl34

Zero-Shot Event Detection Using Multi-modal Fusion of Weakly Supervised Concepts

Shuang Wu, Sravanthi Bondugula, Florian Luisier, Xiaodan Zhuang, Pradeep Natarajan
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
We leverage video and image collections with free-form text descriptions from widely available web sources to learn a large bank of concepts, in addition to using several off-the-shelf concept detectors  ...  , speech, and video text for representing videos.  ...  For the video, we apply a bank of concept detectors to obtain a textual representation of the video using a vector of detection scores.  ... 
doi:10.1109/cvpr.2014.341 dblp:conf/cvpr/WuBLZN14 fatcat:ep7juxwv2jgubhlx3ezgyjomrq

VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products [article]

Xintong Han, Bharat Singh, Vlad I. Morariu, Larry S. Davis
2017 arXiv   pre-print
The retrieved web images representing the query and each database video are treated as unordered collections of images, and each collection is represented using a single Fisher Vector built on CNN features  ...  We also provide a direct comparison on standard datasets between two different paradigms for automatic video retrieval - zero-shot learning and on-the-fly retrieval.  ...  ACKNOWLEDGMENT The authors would like to thank Yin Cui, Guangnan Ye, and Yitong Li for providing the AP for each event of their methods.  ... 
arXiv:1512.03384v3 fatcat:buorruy7pbfkfjw3g6npa53kg4

Semantic-Based Video Retrieval Survey

Shaimaa Toriah Mohamed Toriah, Atef Zaki Ghalwash, Aliaa A. A. Youssif
2018 Journal of Computer and Communications  
Video represents a rich source of information. Thus, there is an urgent need to retrieve, organize, and automate videos.  ...  Video retrieval is a vital process in multimedia applications such as video search engines, digital museums, and video-on-demand broadcasting.  ...  The first stage builds concepts vector which represents the textual event query that is called Event detector. The second one is concerned with calculating the videos model vectors.  ... 
doi:10.4236/jcc.2018.68003 fatcat:qfep2py7ufhwxea7vazpujltja

Multimedia event detection with multimodal feature fusion and temporal concept localization

Sangmin Oh, Scott McCloskey, Ilseo Kim, Arash Vahdat, Kevin J. Cannons, Hossein Hajimirsadeghi, Greg Mori, A. G. Amitha Perera, Megha Pandey, Jason J. Corso
2013 Machine Vision and Applications  
We present a system for multimedia event detection.  ...  Second, we show a novel latent SVM model which learns and localizes discriminative high-level concepts in cluttered video sequences.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright thereon.  ... 
doi:10.1007/s00138-013-0525-x fatcat:m5grko5ls5denhtst2btnwdmmy

Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition [article]

Tim Althoff, Hyun Oh Song, Trevor Darrell
2014 arXiv   pre-print
In this paper, we propose an image representation, called Detection Bank, based on the detection images from a large number of windowed object detectors where an image is represented by different statistics  ...  Recognition or retrieval of events and activities can be improved if specific discriminative objects are detected in a video sequence.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
arXiv:1405.7102v2 fatcat:t7etwujxn5b43pesmcxl64njbm

Event-Driven Semantic Concept Discovery by Exploiting Weakly Tagged Internet Images

Jiawei Chen, Yin Cui, Guangnan Ye, Dong Liu, Shih-Fu Chang
2014 Proceedings of International Conference on Multimedia Retrieval - ICMR '14  
Analysis and detection of complex events in videos require a semantic representation of the video content.  ...  for real-world video event detection problems.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes not withstanding any copyright annotation thereon.  ... 
doi:10.1145/2578726.2578729 dblp:conf/mir/ChenCYLC14 fatcat:hcu3ctla35dh5enksh5cqlhp7u

Zero-Example Multimedia Event Detection and Recounting with Unsupervised Evidence Localization

Yi-Jie Lu
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
The system only takes a text description of an event as input, then performs evidence localization, event detection and recounting in a large, unlabelled video corpus.  ...  Recounting enables "video skimming", which not only enhances video exploration, but also makes human-in-the-loop possible for improving the detection result.  ...  The For preliminary experiments, we build a concept bank containing a total of 2,048 semantic concepts with varied granularity.  ... 
doi:10.1145/2964284.2971480 dblp:conf/mm/Lu16 fatcat:unzumiekxjcjba3m7l4bk7hmhy

Detection bank

Tim Althoff, Hyun Oh Song, Trevor Darrell
2012 Proceedings of the 20th ACM international conference on Multimedia - MM '12  
In this paper, we propose an image representation, called Detection Bank, based on the detection images from a large number of windowed object detectors where an image is represented by di↵erent statistics  ...  Recognition or retrieval of events and activities can be improved if specific discriminative objects are detected in a video sequence.  ...  INTRODUCTION There has been considerable progress in classifying videos using concept models formed from global feature representations.  ... 
doi:10.1145/2393347.2396384 dblp:conf/mm/AlthoffSD12 fatcat:ydfqq3tkfjdlxlmkxkbrxrpyzu

Design and Assessment of an Intelligent Activity Monitoring Platform

Alberto Avanzi, François Brémond, Christophe Tornieri, Monique Thonnat
2005 EURASIP Journal on Advances in Signal Processing  
of an automatic metro monitoring system built with the platform and briefly the validation results for bank agency monitoring and building access control.  ...  We are interested in designing a reusable and robust activity monitoring platform.  ...  There are two main types of concepts to be represented: physical objects of the observed scene and video events occurring in the scene.  ... 
doi:10.1155/asp.2005.2359 fatcat:kfsvw46v4rcfplz63q3ockytnu

[Invited Paper] A Review of Web Image Mining

Keiji Yanai
2015 ITE Transactions on Media Technology and Applications  
of visual concept database for image/video recognition, (2) Web image application for visual concept analysis and data-driven computer graphics, and (3) real-world sensing through Web images to detect  ...  In this paper, we review works related to big visual data on the Web in the literature of computer vision and multimedia research regarding the following points: (1) Web image acquisition for construction  ...  The objective is the same as 124)129) , although this work more focused on building a concept network representing relations between visual concepts.  ... 
doi:10.3169/mta.3.156 fatcat:gduk25dp7nedvm65xurbwzdu3y

Art crossing Hiroshima Project 2001, spring as an urban development strategy

Yasuyo Kudo
2002 On the W@terfront  
Tatsuo Ebisawa Yoahiharu Maekawa 215 At the former Hiroshima branch building of the Bank of Japan, one of the A-bomb historical memorials, eighteen video works were effectively shown in many rooms, both  ...  Ltd.). 4) Concept and Realization of a Temporary Art Event, "Art Crossing Hiroshima Project 2001, Spring."  ... 
doaj:1bdd244f6834468282eaaabfda4d1047 fatcat:fs77wrrmjzahniywiyfhbfqb7e

EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video [article]

Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, Shih-Fu Chang
2015 arXiv   pre-print
Event-specific concepts are the semantic concepts designed for the events of interest, which can be used as a mid-level representation of complex events in videos.  ...  This motivates us to build a large scale event-specific concept library that covers as many real-world events and their concepts as possible.  ...  CONCLUSION We have introduced EventNet, a large scale structured eventdriven concept library for representing complex event in video.  ... 
arXiv:1506.02328v2 fatcat:doyeetyfqzdzpjsnd55pb6mdge

EventNet

Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, Shih-Fu Chang
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
Event-specific concepts are the semantic concepts specifically designed for the events of interest, which can be used as a mid-level representation of complex events in videos.  ...  This motivates us to build a large scale event-specific concept library that covers as many real-world events and their concepts as possible.  ...  CONCLUSION We have introduced EventNet, a large scale structured eventdriven concept library for representing complex event in video.  ... 
doi:10.1145/2733373.2806221 dblp:conf/mm/YeLXLC15 fatcat:uywnm3yhqra6tk4cpfnwxaeicu
« Previous Showing results 1 — 15 out of 44,728 results