Content-Based Visual Summarization for Image Collections

  title={Content-Based Visual Summarization for Image Collections},
  author={Xingjia Pan and Fan Tang and Weiming Dong and Chongyang Ma and Yiping Meng and Feiyue Huang and Tong-Yee Lee and Changsheng Xu},
  journal={IEEE Transactions on Visualization and Computer Graphics},
With the surge of images in the information era, people demand an effective and accurate way to access meaningful visual information. Accordingly, effective and accurate communication of information has become indispensable. In this article, we propose a content-based approach that automatically generates a clear and informative visual summarization based on design principles and cognitive psychology to represent image collections. We first introduce a novel method to make representative and… Expand
Image Collection Summarization Method Based on Semantic Hierarchies
Experimental outcomes indicated that the introduced image collection summarization method outperformed the recent techniques for the summarization of image collections. Expand
Creating automatic storytelling videos from still images: a semantically-aware approach
In a widely connected world, communicating through multimedia content has exponentially been gaining popularity. Mostly for common use, technology that enables the production of quality content forExpand
Semantic Storytelling Automation: A Context-Aware and Metadata-Driven Approach
This work proposes an innovative approach that uses context and content information to transform a still photo into an appealing context-aware video clip and assists content creators with a value-added service to automatically build rich contextualized multimedia stories from single photographs. Expand
From a Still Image to a Semantically Aware Video: A Context and Metadata-driven Automatic Media Production Framework
Paula Viana *†, Pedro Carvalho †* {paula.viana,pedro.carvalho} * Polytechnic of Porto Porto, Portugal Maria Teresa Andrade ‡†, Inês N. Teixeira *†‡Expand


Multimodal latent topic analysis for image collection summarization
The proposed MICS (Multimodal Image Collection Summarization), a method that combines textual and visual modalities in a common latent space, which allows to find a subset of images from which the whole collection can be reconstructed, is presented. Expand
Very fast generation of content-preserved photo collage under canvas size constraint
This work addresses the issue of content-preserved collage, which avoids content-harmful processes such as cropping or changes to aspect ratio and orientation, and presents an algorithm that can pack all the input images tightly onto the collage canvas while keeping their visual information unchanged. Expand
Attention-based Multi-Patch Aggregation for Image Aesthetic Assessment
A novel multi-patch aggregation method for image aesthetic assessment using an attention-based mechanism that adaptively adjusts the weight of each patch during the training process to improve learning efficiency and outperforms existing methods by a large margin. Expand
Canonical image selection based on human affects in photographic images
It is proven that the proposed system is superior to the others in selecting the canonical images, when comparing its performance with two baselines in terms of representative and diverse scores. Expand
Composing Semantic Collage for Image Retargeting
Experimental results demonstrate the merits of the proposed algorithm over the state-of-the-art image retargeting methods. Expand
Image collection summarization via dictionary learning for sparse representation
A novel framework is developed to achieve effective summarization of large-scale image collection by treating the problem of automatic image summarization as a problem of dictionary learning for sparse representation, and the results have shown that the dictionarylearning for sparse representations algorithm can obtain more accurate summary as compared with other baseline algorithms. Expand
Semantic Summarization of Egocentric Photo Stream Events
This work addresses the problem of automatically summarizing egocentric photo streams captured through a wearable camera by taking an image retrieval perspective and proposes a new evaluation metric which takes into account the non-uniqueness of the solution. Expand
Generating diverse and representative image search results for landmarks
This work uses a combination of context- and content-based tools to generate representative sets of images for location-driven features and landmarks, a common search task. Expand
Automatic Generation of Visual-Textual Presentation Layout
This article presents a system to automatically generate visual-textual presentation layouts by investigating a set of aesthetic design principles, through which an average user can easily create visually appealing layouts, and demonstrates that the designs achieve the best reading experience compared with the reimplementation of parts of existing state-of-the-art designs. Expand
Picture Collage
This paper forms the picture collage creation problem in a conditional random field model, which integrates image salience, canvas constraint, natural preference, and user interaction, and integrates user interaction in the formulation and optimization. Expand