We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this article, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and in the process discuss the spawning of related subfields. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.

Abstract. Bag-of-features representations have recently become popular for content based image classification owing to their simplicity and good performance. They evolved from texton methods in texture analysis. The basic idea is to treat images as loose collections of independent patches, sampling a representative set of patches from the image, evaluating a visual descriptor vector for each patch independently, and using the resulting distribution of samples in descriptor space as a characterization of the image. The four main implementation choices are thus how to sample patches, how to describe them, how to characterize the resulting distributions and how to classify images based on the result. We concentrate on the first issue, showing experimentally that for a representative selection of commonly used test databases and for moderate to large numbers of samples, random sampling gives equal or better classifiers than the sophisticated multiscale interest operators that are in common use. Although interest operators work well for small numbers of samples, the single most important factor governing performance is the number of patches sampled from the test image and ultimately interest operators can not provide enough patches to compete. We also study the influence of other factors including codebook size and creation method, histogram normalization method and minimum scale for feature extraction. 1

We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. The model is scale and translation invariant. In the training phase, image regions that optimize an objective function are automatically located in the training images, without requiring any user annotation such as bounding boxes. The objective function measures visual similarity between training image pairs, using the spatial distribution of both appearance patches and edges. The optimization is initialized using discriminative features. The model enables the detection (localization) of multiple instances of the object class in test images, and can be used as a precursor to training other visual models that require bounding box annotation. The detection performance of the model is assessed on the PASCAL Visual Object Classes Challenge 2006 test set. For a number of object classes the performance far exceeds the current state of the art of fully supervised methods. 1.

Abstract. Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization task. First a binary classifier is trained using a sample of positive and negative examples, and this classifier is subsequently applied to multiple regions within test images. We propose instead to treat object localization in a principled way by posing it as a problem of predicting structured data: we model the problem not as binary classification, but as the prediction of the bounding box of objects located in images. The use of a joint-kernel framework allows us to formulate the training procedure as a generalization of an SVM, which can be solved efficiently. We further improve computational efficiency by using a branch-and-bound strategy for localization during both training and testing. Experimental evaluation on the PASCAL VOC and TU Darmstadt datasets show that the structured training procedure improves performance over binary training as well as the best previously published scores. 1

We present a discriminative shape-based algorithm for object category localization and recognition. Our method learns object models in a weakly-supervised fashion, without requiring the specification of object locations nor pixel masks in the training data. We represent object models as cliques of fully-interconnected parts, exploiting only the pairwise geometric relationships between them. The use of pairwise relationships enables our algorithm to successfully overcome several problems that are common to previously-published methods. Even though our algorithm can easily incorporate local appearance information from richer features, we purposefully do not use them in order to demonstrate that simple geometric relationships can match (or exceed) the performance of state-of-the-art object recognition algorithms.

Integration of goal-driven, top-down attention and image-driven, bottom-up attention is crucial for visual search. Yet, previous research has mostly focused on models that are purely top-down or bottom-up. Here, we propose a new model that combines both. The bottom-up component computes the visual salience of scene locations in different feature maps extracted at multiple spatial scales. The topdown component uses accumulated statistical knowledge of the visual features of the desired search target and background clutter, to optimally tune the bottom-up maps such that target detection speed is maximized. Testing on 750 artificial and natural scenes shows that the model’s predictions are consistent with a large body of available literature on human psychophysics of visual search. These results suggest that our model may provide good approximation of how humans combine bottom-up and top-down cues such as to optimize target detection speed. 1.

Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial binning of the local descriptors to impose spatial information beyond a pure “bag-of-words ” model, and thus may fail to capture the most informative space-time relationships. We propose to learn the shapes of space-time feature neighborhoods that are most discriminative for a given action category. Given a set of training videos, our method first extracts local motion and appearance features, quantizes them to a visual vocabulary, and then forms candidate neighborhoods consisting of the words associated with nearby points and their orientation with respect to the central interest point. Rather than dictate a particular scaling of the spatial and temporal dimensions to determine which points are near, we show how to learn the class-specific distance functions that form the most informative configurations. Descriptors for these variable-sized neighborhoods are then recursively mapped to higher-level vocabularies, producing a hierarchy of space-time configurations at successively broader scales. Our approach yields state-of-theart performance on the UCF Sports and KTH datasets. 1.

We present methods for recognizing object categories which are able to combine various feature types (e.g. image patches and edge boundaries). Our objective is to detect object instances in an image, as opposed to the easier task of image categorization. To this end, we investigate two algorithms for learning and detecting object categories which both benefit from combining features. The first uses a naive combination method for detectors each employing only one type of feature, the second learns the best features (from a pool of patches and boundaries). In experiments we achieve comparable results to the state of the art over a number of datasets, and for some categories we even achieve the lowest errors that have been reported so far. The results also show that certain object categories prefer certain feature types (e.g. boundary fragments for airplanes).

In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-based image classifier in front of a reinforcement learning algorithm. The classifier partitions the visual space according to the presence or absence of few highly informative local descriptors that are incrementally selected in a sequence of attempts to remove perceptual aliasing. We also address the problem of fighting overfitting in such a greedy algorithm. Finally, we show how high-level visual features can be generated when the power of local descriptors is insufficient for completely disambiguating the aliased states. This is done by building a hierarchy of composite features that consist of recursive spatial combinations of visual features. We demonstrate the efficacy of our algorithms by solving three visual navigation tasks and a visual version of the classical “Car on the Hill ” control problem. 1.

Abstract This paper describes a computer vision approach to automated rapid-throughput taxonomic identification of stonefly larvae. The long-term goal of this research is to develop a cost-effective method for environmental monitoring based on automated identification of indicator species. Recognition of stonefly larvae is challenging because they are highly articulated, they exhibit a high degree of intraspecies variation in size and color, and some species are difficult to distinguish visually, despite prominent dorsal patterning. The stoneflies are imaged via an apparatus that manipulates the specimens into the field of view of a microscope so that images are obtained under highly repeatable conditions. The images are then classified through a process that involves (a) identification of regions of interest, (b) representation of