Image annotation refinement using random walk with restarts

Wang, Changhu; Feng, Jing; Zhang, Lei; Zhang, Hong-Jiang

doi:10.1145/1180639.1180774

Cited by 162 publications

(117 citation statements)

References 10 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…In Table 1, our semantically smoothed refinement (SSR) method is compared with a variety of concept detection refinement methods including ontological refinement [19], a Random Walk-based method [14], Tensor-based refinement for wearable sensing [16], training-free refinement (TFR) [18], as well as domain adaptive semantic diffusion (DASD) [4]. We applied the same ontological structure of 85 concepts with subsumption and disjointness concept relationships as used in [18] and applied to ontological refinement.…”

Section: Evaluation and Discussionmentioning

confidence: 99%

Semantically Smoothed Refinement for Everyday Concept Indexing

Wang

Sun

Smeaton

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Instead of occurring independently, semantic concepts pairs tend to co-occur within a single image and it is intuitive that concept detection accuracy for visual concepts can be enhanced if concept correlation can be leveraged in some way. In everyday concept detection for visual lifelogging using wearable cameras to automatically record everyday activities, the captured images usually have a diversity of concepts which challenges the performance of concept detection. In this paper a semantically smoothed refinement algorithm is proposed using concept correlations which exploit topic-related concept relationships, modeled externally in a user experiment rather than extracted from training data. Results for initial concept detection are factorized based on semantic smoothness and adjusted in compliance with the extracted concept correlations. Refinement performance is demonstrated in experiments to show the effectiveness of our algorithm and the extracted correlations.

show abstract

Section: Evaluation and Discussionmentioning

confidence: 99%

Semantically Smoothed Refinement for Everyday Concept Indexing

Wang

Sun

Smeaton

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Detection refinement or adjustment methods [43,44,45,46,47] represent a stream of post-processing method which can enhance detection scores obtained from individual detectors, allowing independent and specialized classification techniques to be leveraged for each concept. In this section, we introduce an approach which can exploit the inter-concept relationships implicity from concept detection results of C N×M in order to provide better quality semantic indexing.…”

Section: Modeling Global and Local Occurrence Patternsmentioning

confidence: 99%

Computer Vision for Lifelogging

Wang

Sun

Smeaton

et al. 2018

Computer Vision for Assistive Healthcare

View full text Add to dashboard Cite

show abstract

“…A common problem with the above methods is scalability to large numbers of concepts, and large-scale categorization techniques have been developed by Wang et al [32], [33] and [31]. These partly leverage auxiliary search engines to retrieve related images from web-scale image sets, utilizing text word search to obtain a ranked list of candidate tags.…”

Section: A Related Workmentioning

confidence: 99%

Evolutionary data purification for social media classification

James

Collomosse

2016

2016 23rd International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Abstract-We present a novel algorithm for the semantic labeling of photographs shared via social media. Such imagery is diverse, exhibiting high intra-class variation that demands large training data volumes to learn representative classifiers. Unfortunately image annotation at scale is noisy resulting in errors in the training corpus that confound classifier accuracy. We show how evolutionary algorithms may be applied to select a 'purified' subset of the training corpus to optimize classifier performance. We demonstrate our approach over a variety of image descriptors (including deeply learned features) and support vector machines.

show abstract

Image annotation refinement using random walk with restarts

Cited by 162 publications

References 10 publications

Semantically Smoothed Refinement for Everyday Concept Indexing

Semantically Smoothed Refinement for Everyday Concept Indexing

Computer Vision for Lifelogging

Evolutionary data purification for social media classification

Contact Info

Product

Resources

About