Conference Paper

Large-scale Outdoor Scene Classification by Boosting a Set of Highly Discriminative and Low Redundant Graphlets

DOI: 10.1109/ICDMW.2011.108 Conference: Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference on, Vancouver, BC, Canada, December 11, 2011
Source: DBLP

ABSTRACT

Large-scale outdoor scene classification is an important issue in multimedia information retrieval. In this paper, we propose an efficient scene classification model by integrating outdoor scene image's local features into a set of highly discriminative and less redundant graph lets (i.e., small connected sub graph). Firstly, each outdoor scene image is segmented into a number of regions in terms of its color intensity distribution. And a region adjacency graph (RAG) is defined to encode the geometric property and color intensity distribution of outdoor scene image. Then, the frequent sub-structures are mined statistically from the RAGs corresponding to the training outdoor scene images. And a selecting process is carried out to obtain a set of sub-structures from the frequent ones towards being highly discriminative and low redundant. And these selected sub-structures are used as templates to extract the corresponding graph lets. Finally, we integrate these extracted graph lets by a multi-class boosting strategy for outdoor scene classification. The experimental results on the challenging SUN~\cite{sun} data set and the LHI~\cite{lotus} data set validate the effectiveness of our approach.

0 Followers
 · 
2 Reads
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper deals with the role of platinum or titanium–titanium nitride electrodes on variability of resistive switching characteristics and electrical performances of HfO 2 -based memory elements. Capacitor-like Pt/HfO 2 (10 nm)/Pt and Ti/HfO 2 (10 nm)/TiN structures were fabricated on top of a tungsten pillar bottom electrode and integrated in-between two interconnect metal lines. First, quasi-static measurements were performed to ap-prehend the role of electrodes on electroforming, set and reset operations and their corresponding switching pa-rameters. Memory elements with Pt as top and bottom electrodes exhibited a non-polar behavior with sharp decrease of current during reset operation while Ti/HfO 2 /TiN capacitors showed a bipolar switching behavior, with a gradual reset. In a second step, statistical distributions of switching parameters (voltage and resistance) were extracted from data obtained on few hundreds of capacitors. Even if the resistance in low resistive state and reset voltage was found to be comparable for both types of electrodes, the progressive reset operation ob-served on samples with Ti/TiN electrodes led to a lower variability of resistance in high resistive state and con-comitantly of set voltage. In addition Ti–TiN electrodes enabled gaining: (i) lower forming and set voltages with significantly narrower capacitor-to-capacitor distributions; (ii) a better data retention capability (10 years at 65 °C instead of 10 years at 50 °C for Pt electrodes); (iii) satisfactory dynamic performances with lower set and reset voltages for ramp speed ranging from 10 −2 to 10 7 V/s. The significant improvement of switching behavior with Ti–TiN electrodes is mainly attributed to the formation of a native interface layer be-tween HfO 2 oxide and Ti top electrode.
    Full-text · Article · Apr 2013 · Thin Solid Films
  • [Show abstract] [Hide abstract]
    ABSTRACT: Scene understanding is a popular research direction. In this area, many attempts focus on the problem of naming objects in the complex natural scene, and visual semantic integration model (VSIM) is the representative. This model consists of two parts: semantic level and visual level. In the first level, it uses a four-level pachinko allocation model (PAM) to capture the semantics behind images. However, this four-level PAM is inflexible and lacks of considerations of common subtopics that represent the background semantics. To address these problems, we use hierarchical PAM (hPAM) to replace PAM. Since hPAM is flexible, we investigate two variations of hPAM to boost VSIM in this paper. We derive the Gibbs sampler to learn the proposed models. Empirical results validate that our works can obtain better performance than the state-of-the-art algorithms.
    No preview · Article · Jan 2015 · Multimedia Tools and Applications