Semantic Video Annotation using Background Knowledge and Similarity-based Video Retrieval.
Published 1 January 2008
Ainhoa Llorente, Srđan Zagorac, Suzanne Little, Rui Hu, Stefan Rüger, Anuj Kumar
Citations8
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The experiments for the High-level Feature Extraction (FE) and Search (SE) tasks and participation in the TRECVID evaluation were a valuable learning experience for the group.
Abstract
Abstract. We describe our experiments for the High-level Feature Extraction (FE) and Search (SE) tasks. We submitted two automatic runs to the FE task, the first one (MMIS alexei) was based on a probabilistic approach while the second (MMIS ainhoa) was an enhanced version that used background knowledge in the form of statistical co-occurrence of annotation keywords. While previous applications of this approach to other datasets have performed quite well, our results in TRECVID 2008 are not so good. In particular, the performance of the second run was limited by the small vocabulary. For the SE task we submitted two runs: a similarity-based media search (MMIS media) and the required text-only search (MMIS text). The similarity search, using media content, had better precision than the text-only search but had difficulties with some types of queries (e.g., motion-based). Overall, participation in the TRECVID evaluation was a valuable learning experience for our group.
Keywords
Computer Science
IEEE Transactions on Systems Man and CyberneticsTextural Features Corresponding to Visual Perception
2,130 Citations1978Hideyuki Tamura, Shunji Mori +1 more
The discrepancies between human vision and computerized techniques that are encountered in this study indicate fundamental problems in digital analysis of textures and could be overcome by analyzing their causes and using more sophisticated techniques.
IEEE Transactions on Circuits and Systems for Video TechnologyColor and texture descriptors
1,650 Citations2001B.S. Manjunath, J.-R. Ohm +2 more
An overview of color and texture descriptors that have been approved for the Final Committee Draft of the MPEG-7 standard is presented, explained in detail by their semantics, extraction and usage.
Lecture notes in computer scienceObject Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
1,608 Citations2002Pınar Duygulu, Kobus Barnard +2 more
This work shows how to cluster words that individually are difficult to predict into clusters that can be predicted well, and cannot predict the distinction between train and locomotive using the current set of features, but can predict the underlying concept.
Multimedia SystemsAutomatic partitioning of full-motion video
1,275 Citations1993HongJiang Zhang, Atreyi Kankanhalli +1 more
A twin-comparison approach has been developed to solve the problem of detecting transitions implemented by special effects, and a motion analysis algorithm is applied to determine whether an actual transition has occurred.
Evaluation campaigns and TRECVid
1,224 Citations2006Alan F. Smeaton, Paul Over +1 more
An introduction to information retrieval (IR) evaluation from both a user and a system perspective is given, high-lighting that system evaluation is by far the most prevalent type of evaluation carried out.
Models for metasearch
681 Citations2001Javed Aslam, Mark Montague
The experimental results show that metasearch algorithms based on the Borda and Bayesian models usually outperform the best input system and are competitive with, and often outperform, existing metAsearch strategies.
ScholarWorks@UMassAmherst (University of Massachusetts Amherst)A Model for Learning the Semantics of Pictures
681 Citations2003Victor Lavrenko, R. Manmatha +1 more
An approach to learning the semantics of images which allows us to automatically annotate an image with keywords and to retrieve images based on text queries using a formalism that models the generation of annotated images.
IEEE MultimediaLarge-Scale Concept Ontology for Multimedia
648 Citations2006Milind Naphade, John R. Smith +6 more
The large-scale concept ontology for multimedia (LSCOM) is the first of its kind designed to simultaneously optimize utility to facilitate end-user access, cover a large semantic space, make automated extraction feasible, and increase observability in diverse broadcast news video data sets.
Estimating average precision with incomplete and imperfect judgments
329 Citations2006Emine Yılmaz, Javed A. Aslam
This work proposes three evaluation measures that are approximations to average precision even when the relevance judgments are incomplete and are more robust to incomplete or imperfect relevance judgments than bpref, and proposes estimates of average precision that are simple and accurate.
Lecture notes in computer scienceAutomated Image Annotation Using Global Features and Robust Nonparametric Density Estimation
138 Citations2005Alexei Yavlinsky, Edward Schofield +1 more
It is shown that under this framework quite simple image properties such as global colour and texture distributions provide a strong basis for reliably annotating images.
Lecture notes in computer scienceAn Inference Network Approach to Image Retrieval
98 Citations2004Donald Metzler, R. Manmatha
A model based on the Inference Network framework from information retrieval that employs a powerful query language that allows structured query operators, term weighting, and the combination of text and images within a query is proposed.
Image Analysis & StereologyMATHEMATICAL MORPHOLOGY IN THE CIELAB SPACE
82 Citations2011Allan Hanbury, Jean Serra
Dissimilarity measures for content-based image retrieval
41 Citations2008Rui Hu, Stefan Rüger +3 more
16 core dissimilarity measures are introduced and evaluated, and a systematic performance comparison on three image collections, Corel, Getty and Trecvid2003, with 7 different feature spaces is carried out.
Audio-visual segmentation for content-based retrieval
35 Citations1998David Pye, Nicholas J. Hollinghurst +2 more
An audio segmentation algorithm that partitions a soundtrack into manageably sized segments for speech recognition and an algorithm for detecting camera shot-break locations in the video are described.
Video Retrieval Using Global Features in Keyframes.
24 Citations2002Marcus Jerome Pickering, Daniel Heesch +3 more
TRECVID 2007 collaborative annotation using active learning
23 Citations2007Stéphane Ayache, Georges Quénot
This paper describes the collaborative annotation system used to annotate the High Level Features (HLF) in the development set of TRECVID 2007 and shows that Active Learning allows simultaneously getting the most useful information form the partial annotation and significantly reducing the annotation eort per participant relatively to previous collaborative annotations.
PainCan a probabilistic image annotation system be improved using a co-occurrence approach?
6 Citations2008Ainhoa Llorente, Stefan Rüger
The Committee for Research and Ethical Issues of the International Association for the Study of Pain (IASP®) is concerned with the ethical aspects of studies producing experimental pain and any suffering it may cause in animals.