Boosting image retrieval

Tieu, Kinh; Viola, Paul A.

doi:10.1109/cvpr.2000.855824

Cited by 295 publications

(164 citation statements)

References 18 publications

Supporting

Mentioning

164

Contrasting

Order By: Relevance

“…Different approaches for image representation have been proposed including by Feng et al (2004), Takala et al (2005), Tieu and Viola (2004). In the information retrieval community there is wide agreement that a bag-of-words representation is a very useful representation for handling text documents in a wide range of applications.…”

Section: Image Representationmentioning

confidence: 99%

“…Our local descriptor representation is therefore simple, relying on both a basic segmentation approach and simple features. Naturally, alternative representations could also be used with OASIS, (Feng et al, 2004, Grangier et al, 2006, Tieu and Viola, 2004 However, this paper focuses on the learning model, and a benchmark of image representations is beyond the scope of the current paper.…”

Section: Image Representationmentioning

confidence: 99%

See 1 more Smart Citation

Large Scale Online Learning of Image Similarity through Ranking

Chechik

Sharma

Shalit

et al. 2009

Lecture Notes in Computer Science

420

624

View full text Add to dashboard Cite

Learning a measure of similarity between pairs of objects is an important generic problem in machine learning. It is particularly useful in large scale applications like searching for an image that is similar to a given image or finding videos that are relevant to a given video. In these tasks, users look for objects that are not only visually similar but also semantically related to a given object. Unfortunately, the approaches that exist today for learning such semantic similarity do not scale to large datasets. This is both because typically their CPU and storage requirements grow quadratically with the sample size, and because many methods impose complex positivity constraints on the space of learned similarity functions.The current paper presents OASIS, an Online Algorithm for Scalable Image Similarity learning that learns a bilinear similarity measure over sparse representations. OASIS is an online dual approach using the passive-aggressive family of learning algorithms with a large margin criterion and an efficient hinge loss cost. Our experiments show that OASIS is both fast and accurate at a wide range of scales: for a dataset with thousands of images, it achieves better results than existing state-of-the-art methods, while being an order of magnitude faster. For large, web scale, datasets, OASIS can be trained on more than two million images from 150K text queries within 3 days on a single CPU. On this large scale dataset, human evaluations showed that 35% of the ten nearest neighbors of a given test image, as found by OASIS, were semantically relevant to that image. This suggests that query independent similarity could be accurately learned even for large scale datasets that could not be handled before.

show abstract

Section: Image Representationmentioning

confidence: 99%

Section: Image Representationmentioning

confidence: 99%

Large Scale Online Learning of Image Similarity through Ranking

Chechik

Sharma

Shalit

et al. 2009

Lecture Notes in Computer Science

420

624

View full text Add to dashboard Cite

show abstract

“…It was developed by Freund and Schapire [5] and has been used in diverse applications, e.g., as classifiers for image retrieval [6], for ball tracking with soccer-robots [7], and to classify laser scans for learning of places in indoor environments [8,9]. The latter work provides a nice demonstration of the use of machine learning and a set of generic features to transform sensor readings into human concepts.…”

Section: Adaboostmentioning

confidence: 99%

Virtual sensors for human concepts—Building detection by an outdoor mobile robot

Persson

Duckett

Lilienthal

2007

Robotics and Autonomous Systems

View full text Add to dashboard Cite

In human-robot communication it is often important to relate robot sensor readings to concepts used by humans. We suggest to use a virtual sensor (one or several physical sensors with a dedicated signal processing unit for recognition of real world concepts) and a method with which the virtual sensor can be learned from a set of generic features. The virtual sensor robustly establishes the link between sensor data and a particular human concept. In this work, we present a virtual sensor for building detection that uses vision and machine learning to classify image content in a particular direction as buildings or non-buildings. The virtual sensor is trained on a diverse set of image data, using features extracted from grey level images. The features are based on edge orientation, configurations of these edges, and on grey level clustering. To combine these features, the AdaBoost algorithm is applied. Our experiments with an outdoor mobile robot show that the method is able to separate buildings from nature with a high classification rate, and extrapolate well to images collected under different conditions. Finally, the virtual sensor is applied on the mobile robot, combining classifications of sub-images from a panoramic view with spatial information (location and orientation of the robot) in order to communicate the likely locations of buildings to a remote human operator.

show abstract

“…Other ranking algorithms are based on inductive learning [10,11] which typically use a bank of classifiers to represent the set of possible events to test.…”

Section: Ranking Functionsmentioning

confidence: 99%

Latent topics-based relevance feedback for video retrieval

Fernández-Beltrán

Pla

2016

Pattern Recognition

View full text Add to dashboard Cite

This work presents a novel Content-Based Video Retrieval approach in order to cope with the semantic gap challenge by means of latent topics.Firstly, a supervised topic model is proposed to transform the classical retrieval approach into a class discovery problem. Subsequently, a new probabilistic ranking function is deduced from that model to tackle the semantic gap between low-level features and high-level concepts. Finally, a shortterm relevance feedback scheme is defined where queries can be initialised with samples from inside or outside the database. Several retrieval simulations have been carried out using three databases and seven different ranking functions to test the performance of the presented approach. Experiments revealed that the proposed ranking function is able to provide a competitive advantage within the content-based retrieval field.

show abstract

Boosting image retrieval

Abstract: We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. Our approach is predicated on the assumption that each image is generated by a sparse set of visual "causes" and that

Cited by 295 publications

References 18 publications

Large Scale Online Learning of Image Similarity through Ranking

Large Scale Online Learning of Image Similarity through Ranking

Virtual sensors for human concepts—Building detection by an outdoor mobile robot

Latent topics-based relevance feedback for video retrieval

Contact Info

Product

Resources

About