• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Tools

Sorted by:
Try your query at:
Semantic Scholar Scholar Academic
Google Bing DBLP
Results 1 - 10 of 29
Next 10 →

Weakly Supervised Visual Dictionary Learning by Harnessing Image Attributes

by Yue Gao, Rongrong Ji, Wei Liu, Qionghai Dai, Gang Hua , 2014
"... Bag-of-features (BoFs) representation has been extensively applied to deal with various computer vision applications. To extract discriminative and descriptive BoF, one important step is to learn a good dictionary to minimize the quantization loss between local features and codewords. While most e ..."
Abstract - Add to MetaCart
existing visual dictionary learning approaches are engaged with unsupervised feature quantization, the latest trend has turned to supervised learning by harnessing the semantic labels of images or regions. However, such labels are typically too expensive to acquire, which restricts the scalability

Learning Visual Attributes

by Vittorio Ferrari, Andrew Zisserman
"... We present a probabilistic generative model of visual attributes, together with an efficient learning algorithm. Attributes are visual qualities of objects, such as ‘red’, ‘striped’, or ‘spotted’. The model sees attributes as patterns of image segments, repeatedly sharing some characteristic propert ..."
Abstract - Cited by 126 (2 self) - Add to MetaCart
training images, the model is learnt discriminatively, by optimizing a likelihood ratio. As demonstrated in the experimental evaluation, our model can learn in a weakly supervised setting and encompasses a broad range of attributes. We show that attributes can be learnt starting from a text query to Google

Visual Reranking through Weakly Supervised Multi-Graph Learning

by Cheng Deng, Rongrong Ji, Wei Liu, Dacheng Tao, Xinbo Gao
"... Visual reranking has been widely deployed to refine the quality of conventional content-based image retrieval engines. The current trend lies in employing a crowd of retrieved results stemming from multiple feature modalities to boost the overall performance of visual reranking. However, a major cha ..."
Abstract - Cited by 7 (1 self) - Add to MetaCart
imposed to encode affinities in a single graph and consistency across d-ifferent graphs. Moreover, weakly supervised learning driven by image attributes is performed to denoise the pseudolabeled instances, thereby highlighting the unique strength of individual feature modality. Meanwhile, such learning

Incremental Kernel Learning for Active Image Retrieval without Global Dictionaries

by P. H. Gosselin, F. Precioso A , 2011
"... In content-based image retrieval context, a classic strategy consists in computing off-line a dictionary of visual features. This visual dictionary is then used to provide a new representation of the data which should ease any task of classification or retrieval. This strategy, based on past researc ..."
Abstract - Cited by 2 (1 self) - Add to MetaCart
In content-based image retrieval context, a classic strategy consists in computing off-line a dictionary of visual features. This visual dictionary is then used to provide a new representation of the data which should ease any task of classification or retrieval. This strategy, based on past

DEEP-CARVING: Discovering Visual Attributes by Carving Deep Neural Nets

by Sukrit Shankar, Vikas K. Garg, Roberto Cipolla
"... Most of the approaches for discovering visual attributes in images demand significant supervision, which is cumbersome to obtain. In this paper, we aim to discover visual attributes in a weakly supervised setting that is commonly encountered with contemporary image search engines. For instance, give ..."
Abstract - Add to MetaCart
Most of the approaches for discovering visual attributes in images demand significant supervision, which is cumbersome to obtain. In this paper, we aim to discover visual attributes in a weakly supervised setting that is commonly encountered with contemporary image search engines. For instance

Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts

by unknown authors
"... Current state-of-the-art systems for visual content anal-ysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples. In this paper, we present a general framework for the zero-shot learning problem of performing high-level event de-tection with ..."
Abstract - Add to MetaCart
Current state-of-the-art systems for visual content anal-ysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples. In this paper, we present a general framework for the zero-shot learning problem of performing high-level event de

Learning from Images with Captions Using the Maximum Margin Set Algorithm

by Jie Luo, Francesco Orabona, Barbara Caputo, Vittorio Ferrari, Luo Jie, Francesco Orabona, Barbara Caputo, Vittorio Ferrari , 2011
"... Abstract—A large amount of images with accompanying text captions are available on the Internet. These are valuable for training visual classifiers without any explicit manual intervention. In this paper, we present a general framework to address this problem. Under this new framework, each training ..."
Abstract - Add to MetaCart
formulation, and an efficient algorithm to solve the proposed learning problem. Experiments conducted on artificial datasets and two real-world images and captions datasets support our claims. Index Terms—Weakly supervised learning, candidate labeling sets, images and captions, multi-class and multi

Visualization of Hash-functions

by Diplomarbeit Timo, Kilian Darmstadt, Fachbereich Informatik, Theoretische Informatik Kryptographie, Vorgelegte Diplomarbeit, Timo Kilian Darmstadt
"... den angegebenen Quellen und Hilfsmitteln angefertigt zu haben. Alle Stellen, die aus Quellen entnommen wurden, sind als solche kenntlich gemacht. Diese Arbeit hat in gleicher oder ähnlicher Form noch keiner Prüfungsbehörde vorgelegen. Darmstadt, den 26.06.2012 (T. Kilian) Contents ..."
Abstract - Add to MetaCart
den angegebenen Quellen und Hilfsmitteln angefertigt zu haben. Alle Stellen, die aus Quellen entnommen wurden, sind als solche kenntlich gemacht. Diese Arbeit hat in gleicher oder ähnlicher Form noch keiner Prüfungsbehörde vorgelegen. Darmstadt, den 26.06.2012 (T. Kilian) Contents

under a Creative Commons Attribution Non-Commercial No Derivatives

by Sira Gonzalez, Deparment Of Electrical, Electronic Engineering , 2013
"... the condition that they attribute it, that they do not use it for commercial purposes and that they do not alter, transform or build upon it. For any reuse or redistribution, researchers must make clear to others the licence terms of this work. ..."
Abstract - Add to MetaCart
the condition that they attribute it, that they do not use it for commercial purposes and that they do not alter, transform or build upon it. For any reuse or redistribution, researchers must make clear to others the licence terms of this work.

Accuracy Measurement for Image Retrieval System

by Dr S Thabasu Kannan , P Kumaravel
"... ABSTRACT During the past decades we have been observing a permanent increase in image data, leading to huge repositories. Content-based image retrieval (CBIR) methods have tried to improve the access to image data. To date, numerous feature extraction methods have been proposed to improve the quali ..."
Abstract - Add to MetaCart
is nowadays easy and getting more affordable. As a result, the amount of data in visual form is increasing and there is a strong need for effective ways to manage and process it. We have studied support vector machines to learn the feature space distribution of our structure-based features for several images
Next 10 →
Results 1 - 10 of 29
Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University