Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
29
Weakly Supervised Visual Dictionary Learning by Harnessing Image Attributes
, 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
"... 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
"... 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
, 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
"... 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
"... 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
, 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
"... 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
, 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
"... 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
Results 1 - 10
of
29
