Results 1 - 10
of
317
Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories
- In CVPR
"... This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting “spatial pyrami ..."
Abstract
-
Cited by 1923 (47 self)
- Add to MetaCart
(Show Context)
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting “spatial pyramid ” is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba’s “gist ” and Lowe’s SIFT descriptors. 1.
80 million tiny images: a large dataset for non-parametric object and scene recognition
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
"... ..."
Sun database: Largescale scene recognition from abbey to zoo
- In CVPR
"... Scene categorization is a fundamental problem in com-puter vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object cate-gorization contain hund ..."
Abstract
-
Cited by 306 (37 self)
- Add to MetaCart
Scene categorization is a fundamental problem in com-puter vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databases for object cate-gorization contain hundreds of different classes of objects, the largest available dataset of scene categories contains only 15 classes. In this paper we propose the extensive Scene UNderstanding (SUN) database that contains 899 categories and 130,519 images. We use 397 well-sampled categories to evaluate numerous state-of-the-art algorithms for scene recognition and establish new bounds of perfor-mance. We measure human scene classification perfor-mance on the SUN database and compare this with com-putational methods. Additionally, we study a finer-grained scene representation to detect scenes embedded inside of larger scenes. 1.
Scene completion using millions of photographs
- ACM Transactions on Graphics (SIGGRAPH
, 2007
"... Figure 1: Given an input image with a missing region, we use matching scenes from a large collection of photographs to complete the image. What can you do with a million images? In this paper we present a new image completion algorithm powered by a huge database of photographs gathered from the Web. ..."
Abstract
-
Cited by 251 (12 self)
- Add to MetaCart
Figure 1: Given an input image with a missing region, we use matching scenes from a large collection of photographs to complete the image. What can you do with a million images? In this paper we present a new image completion algorithm powered by a huge database of photographs gathered from the Web. The algorithm patches up holes in images by finding similar image regions in the database that are not only seamless but also semantically valid. Our chief insight is that while the space of images is effectively infinite, the space of semantically differentiable scenes is actually not that large. For many image completion tasks we are able to find similar scenes which contain image fragments that will convincingly complete the image. Our algorithm is entirely data-driven, requiring no annotations or labelling by the user. Unlike existing image completion methods, our algorithm can generate a diverse set of results for each input image and we allow users to select among them. We demonstrate the superiority of our algorithm over existing image completion approaches.
Recovering human body configurations: Combining segmentation and recognition
- In CVPR
, 2004
"... localized joints and limbs. (c) Segmentation mask associated with human figure. The goal of this work is to take an image such as the one in Figure 1(a), detect a human figure, and localize his joints and limbs (b) along with their associated pixel masks (c). In this work we attempt to tackle this p ..."
Abstract
-
Cited by 215 (8 self)
- Add to MetaCart
(Show Context)
localized joints and limbs. (c) Segmentation mask associated with human figure. The goal of this work is to take an image such as the one in Figure 1(a), detect a human figure, and localize his joints and limbs (b) along with their associated pixel masks (c). In this work we attempt to tackle this problem in a general setting. The dataset we use is a collection of sports news photographs of baseball players, varying dramatically in pose and clothing. The approach that we take is to use segmentation to guide our recognition algorithm to salient bits of the image. We use this segmentation approach to build limb and torso detectors, the outputs of which are assembled into human figures. We present quantitative results on torso localization, in addition to shortlisted full body configurations. 1.
Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes
, 2003
"... Standard approaches to object detection focus on local patches of the image, and try to classify them as background or not. We propose to use the scene context (image as a whole) as an extra source of (global) information, to help resolve local ambiguities. We present a conditional random field ..."
Abstract
-
Cited by 175 (13 self)
- Add to MetaCart
(Show Context)
Standard approaches to object detection focus on local patches of the image, and try to classify them as background or not. We propose to use the scene context (image as a whole) as an extra source of (global) information, to help resolve local ambiguities. We present a conditional random field for jointly solving the tasks of object detection and scene classification.
Learning Spatial Context: Using Stuff to Find Things
"... Abstract. The sliding window approach of detecting rigid objects (such as cars) is predicated on the belief that the object can be identified from the appearance in a small region around the object. Other types of objects of amorphous spatial extent (e.g., trees, sky), however, are more naturally cl ..."
Abstract
-
Cited by 131 (1 self)
- Add to MetaCart
(Show Context)
Abstract. The sliding window approach of detecting rigid objects (such as cars) is predicated on the belief that the object can be identified from the appearance in a small region around the object. Other types of objects of amorphous spatial extent (e.g., trees, sky), however, are more naturally classified based on texture or color. In this paper, we seek to combine recognition of these two types of objects into a system that leverages “context ” toward improving detection. In particular, we cluster image regions based on their ability to serve as context for the detection of objects. Rather than providing an explicit training set with region labels, our method automatically groups regions based on both their appearance and their relationships to the detections in the image. We show that our things and stuff (TAS) context model produces meaningful clusters that are readily interpretable, and helps improve our detection ability over state-of-the-art detectors. We also present a method for learning the active set of relationships for a particular dataset. We present results on object detection in images from the PASCAL VOC 2005/2006 datasets and on the task of overhead car detection in satellite images, demonstrating significant improvements over state-of-the-art detectors. 1
Modeling scenes with local descriptors and latent aspects
- In Proc. of IEEE Int. Conf. on Computer Vision
, 2005
"... We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to three open questions:(1) whether the invariant local features are suitable for scene (rather than object) classification ..."
Abstract
-
Cited by 104 (13 self)
- Add to MetaCart
(Show Context)
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to three open questions:(1) whether the invariant local features are suitable for scene (rather than object) classification; (2) whether unsupervised latent space models can be used for feature extraction in the classification task; and (3) whether the latent space formulation can discover visual co-occurrence patterns, motivating novel approaches for image organization and segmentation. Using a 9500-image dataset, our approach is validated on each of these issues. First, we show with extensive experiments on binary and multi-class scene classification tasks, that a bag-of-visterm representation, derived from local invariant descriptors, consistently outperforms state-of-theart approaches. Second, we show that Probabilistic Latent Semantic Analysis (PLSA) generates a compact scene representation, discriminative for accurate classification, and significantly more robust when less training data are available. Third, we have exploited the ability of PLSA to automatically extract visually meaningful aspects, to propose new algorithms for aspect-based image ranking and context-sensitive image segmentation. 1.
Graph Cut based Inference with Co-occurrence Statistics
"... Abstract. Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily ..."
Abstract
-
Cited by 100 (13 self)
- Add to MetaCart
(Show Context)
Abstract. Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily optimised using standard graph cut algorithms at little extra expense compared to a standard pairwise field. This result can be directly used for the problem of class based image segmentation which has seen increasing recent interest within computer vision. Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. There have been several approaches proposed to exploit this property, but all of them suffer from different limitations and typically carry a high computational cost, preventing their application on large images. We find that the new model we propose produces an improvement in the labelling compared to just using a pairwise model. 1
