Evaluating the implicit feedback models for adaptive video retrieval

  title={Evaluating the implicit feedback models for adaptive video retrieval},
  author={Frank Hopfgartner and Joemon M. Jose},
  booktitle={Multimedia Information Retrieval},
Interactive video retrieval systems are becoming popular. On the one hand, these systems try to reduce the effect of the semantic gap, an issue currently being addressed by the multimedia retrieval community. On the other hand, such systems enhance the quality of information seeking for the user by supporting query formulation and reformulation. Interactive systems are very popular in the textual retrieval domain. However, they are relatively unexplored in the case of multimedia retrieval. The… 

Figures and Tables from this paper

Utilizing Implicit User Feedback to Improve Interactive Video Retrieval

A framework, where the video is first indexed according to temporal, textual, and visual features and then implicit user feedback analysis is realized using a graph-based methodology, which encodes the semantic relations between video segments based on past user interaction and is subsequently used to generate recommendations.

Facet-Based Browsing in Video Retrieval: A Simulation-Based Evaluation

A novel interactive video retrieval approach which uses sub-needs of an information need for querying and organising the search process and demonstrates that the faceted browser can potentially improve the search effectiveness.

Effects of Usage-Based Feedback on Video Retrieval: A Simulation-Based Study

A graph-based model for all types of implicit and explicit feedback, in which the relevant usage information is represented, is proposed, designed to capture the complex interactions of a user with an interactive video retrieval system.

Optimizing visual search with implicit user feedback in interactive video retrieval

A framework is proposed, in which video processing is performed by employing well established techniques, while implicit user feedback analysis is realized with a graph based approach that processes the user actions and navigation patterns during a search session, in order to initiate semantic relations between the video segments.

Studying interaction methodologies in video retrieval

This paper proposes to study the importance of various implicit indicators of relevance and investigates how this implicit feedback can be combined with static user profiles towards an adaptive video retrieval model.

Simulated evaluation of faceted browsing based on feature selection

The experimental results of this study demonstrate that the faceted browser can potentially improve the search effectiveness and present a methodology to reduce the dimensionality of features by selecting the most important ones.

Improving retrieval relevance using users' explicit feedback

CoRRe – an explicit feedback model integrating three popular feedback, namely, Comment-Rating-Referral, is proposed in this study, and is found to have the highest retrieval precisions at all the three levels compared to the other feedback models.

Moving beyond text highlights: inferring users' interests to improve the relevance of retrieval

Users’ post-click behaviour may serve as a significant indicator of their interests, and thus can be used to improve the relevance of the retrieved results, according to a study that examined users’ text highlight frequency, length and users' copy-paste actions.

Personalised video retrieval: application of implicit feedback and semantic user profiles

A semantic user profiling approach for news video retrieval is introduced, which exploits a generic ontology to put news stories into its context and can lead to a better understanding of the personal interests.

A News Video Retrieval Framework for the Study of Implicit Relevance Feedback

  • F. HopfgartnerJ. Jose
  • Computer Science
    Second International Workshop on Semantic Media Adaptation and Personalization (SMAP 2007)
  • 2007
A framework for recording, analysing, indexing and retrieving news videos such as the BBC one o'clock news is proposed, believing that such a framework will be useful to identify implicit indicators of relevance, a nearly untouched area in adaptive multimedia retrieval.



Simulated Testing of an Adaptive Multimedia Information Retrieval System

A novel video retrieval system is introduced and a model of implicit information for interpreting the user's actions with the interface is proposed, which seems to enhance retrieval results.

Addressing the challenge of visual information access from digital image and video libraries

Analysis of TRECVID visual features well suited for particular tasks provides additional insights into the role of automated feature classification for digital image and video libraries.

Dublin City University Video Track Experiments for TREC 2002

Dublin City University participated in the Feature Extraction task and the Search task of the TREC-2002 Video Track and developed an interactive video retrieval system that incorporated the 40 hours of the video search test collection and supported user searching using its own feature extraction data along with the donated feature data and ASR transcript from other Video Track groups.

Implicit interest indicators

It was found that the time spent on a pages, the amount of scrolling on a page and the combination of time and scrolling had a strong correlation with explicit interest, while individual scrolling methods and mouse-clicks were ineffective in predicting explicit interest.

Video Retrieval Using Search and Browsing

Overall search performance falls behind that of last year, a result which the authors would like to attribute to the stronger emphasis on motion in this year’s search task.

An Evaluation of Automatic Query Expansion in an Online Library Catalogue

An automatic query expansion (AQE) facility in an online catalogue was evaluated in an operational library setting and found that contrary to previous results, AQE was beneficial in a substantial number of searches.

Improving retrieval performance by relevance feedback

Prescriptions are given for conducting text retrieval operations iteratively using relevance feedback, and evaluation data are included to demonstrate the effectiveness of the various methods.

Adapting To Evolving Needs: Evaluating A Behaviour-Based Search Interface

An evaluation of a behaviour-based adaptive search interface that predicts the current state of a user’s information need based on their interaction shows that the hypotheses that the adaptive system selects additional query words that closely describe user needs hold.

A Simulated Study of Implicit Feedback Models

A study of implicit feedback models for unobtrusively tracking the information needs of searchers shows that a heuristic-based binary voting model and one based on Jeffrey’s rule of conditioning outperform the other models under investigation.

Imperial College at TRECVID

In the high-level feature detection task, the proven method based on the calculation of distances between colour histograms of frames over a range of timescales was employed and two new methods were tested: naïve model and non-parametric density estimation.