Recognizing indoor scenes

Quattoni, A.; Torralba, A.

doi:10.1109/cvprw.2009.5206537

Cited by 495 publications

(765 citation statements)

References 14 publications

Supporting

Mentioning

758

Contrasting

Unclassified

Order By: Relevance

“…To test the performance of the EKD approach, we perform image classification experiments on four well-known datasets: Scene-15 [6,7,19], Caltech-101 [20], UIUC-8 [21], and MIT Indoor-67 [22]. Besides, we also construct EHKD to obtain the image-level feature representation and evaluate its performance on the CI-FAR10 dataset [23].…”

Section: Resultsmentioning

confidence: 99%

“…This dataset raises a challenging classification problem, since yet some indoor scenes can be well characterized by global spatial properties, others are only characterized by the object contained in the image. Following the same training/test split strategy as in [22], we randomly select 80 training images and 20 testing images in each category. The comparison results are shown in Table 5.…”

Section: Scene-15mentioning

confidence: 99%

See 1 more Smart Citation

Efficient image representation for object recognition via pivots selection

Bojun¹,

Xie²,

Yi³

et al. 2014

Front. Comput. Sci.

View full text Add to dashboard Cite

Patch-level features are essential for achieving good performance in computer vision tasks. Besides wellknown pre-defined patch-level descriptors such as scaleinvariant feature transform (SIFT) and histogram of oriented gradient (HOG), the kernel descriptor (KD) method [1] offers a new way to "grow-up" features from a match-kernel defined over image patch pairs using kernel principal component analysis (KPCA) and yields impressive results.In this paper, we present efficient kernel descriptor (EKD) and efficient hierarchical kernel descriptor (EHKD), which are built upon incomplete Cholesky decomposition. EKD automatically selects a small number of pivot features for generating patch-level features to achieve better computational efficiency. EHKD recursively applies EKD to form image-level features layer-by-layer. Perhaps due to parsimony, we find surprisingly that the EKD and EHKD approaches achieved competitive results on several public datasets compared with other state-of-the-art methods, at an improved efficiency over KD.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Scene-15mentioning

confidence: 99%

Efficient image representation for object recognition via pivots selection

Bojun¹,

Xie²,

Yi³

et al. 2014

Front. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…4) Only a subset of images in SUN09 have scene annotations, so we conducted the experiment on this subset. 5) Specifically, for the SUN09 dataset, 30% of images were used as training data, and the rest were used as testing data; the MIT Indoor dataset was split as described in [44].…”

Section: Resultsmentioning

confidence: 99%

Probabilistic modeling of scenes using object frames

2014

Sci. China Inf. Sci.

View full text Add to dashboard Cite

In this paper, we propose a probabilistic scene model using object frames, each of which is a group of co-occurring objects with fixed spatial relations. In contrast to standard co-occurrence models, which mostly explore the pairwise co-existence of objects, the proposed model captures the spatial relationship among groups of objects. Such information is closely tied to the semantics of the underlying scenes, which allows us to perform object detection and scene recognition in a unified framework. The proposed probabilistic model has two major components. The first models the dependencies between object frames and objects by adopting the Latent Dirichlet Allocation model for text analysis. The second component characterizes the dependencies between object frames and scenes by establishing a mapping between global image features and object frame distributions. Experimental results show that the induced object frames are both semantically meaningful and spatially consistent. In addition, our model significantly improves the performance of object recognition and scene retrieval.

show abstract

“…However, the authors are confident that context also plays an important role in indoor recognition which was recently shown by e.g. [8,37,27]. A major contribution of this work was the context integration technique based on multi-dimensional KDE modeling.…”

Section: Discussionmentioning

confidence: 95%