Bi-Level Semantic Representation Analysis for Multimedia Event Detection

Chang, Xiaojun; Ma, Zhiliang; Yang, Yi; Zeng, Zhiqiang; Hauptmann, Alexander G.

doi:10.1109/tcyb.2016.2539546

Cited by 220 publications

(44 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the traffic sign detection methods are focused on images. Another focus of study can be to analyze traffic videos for traffic sign detection by leveraging the semantic representations [20,21]. Yet another focus could consider mining the correlations between the features of traffic signs by a semi-supervised feature selection framework [22] in traffic videos.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2

et al. 2017

View full text Add to dashboard Cite

Abstract:Traffic sign detection is an important task in traffic sign recognition systems. Chinese traffic signs have their unique features compared with traffic signs of other countries. Convolutional neural networks (CNNs) have achieved a breakthrough in computer vision tasks and made great success in traffic sign classification. In this paper, we present a Chinese traffic sign detection algorithm based on a deep convolutional network. To achieve real-time Chinese traffic sign detection, we propose an end-to-end convolutional network inspired by YOLOv2. In view of the characteristics of traffic signs, we take the multiple 1 × 1 convolutional layers in intermediate layers of the network and decrease the convolutional layers in top layers to reduce the computational complexity. For effectively detecting small traffic signs, we divide the input images into dense grids to obtain finer feature maps. Moreover, we expand the Chinese traffic sign dataset (CTSD) and improve the marker information, which is available online. All experimental results evaluated according to our expanded CTSD and German Traffic Sign Detection Benchmark (GTSDB) indicate that the proposed method is the faster and more robust. The fastest detection speed achieved was 0.017 s per image.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The recall rate was inferior to other methods. [13] 92.15% 89.17% -CNN(Zhu) [13,22] 94% 91% -ConvNet [20] 96.49% 99.89% 0.027…”

Section: Evaluations On Gtsdbmentioning

confidence: 99%

A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2

et al. 2017

View full text Add to dashboard Cite

show abstract

“…We obtained raw Digital Imaging and Communications in Medicine (DICOM) MRI scans from the public ADNI website, where these MRI scans have been reviewed for quality, and automatically corrected for spatial distortion caused by gradient nonlinearity and B1 field inhomogeneity. We then processed all MR images following the same procedures in [38], [39] as detailed below:…”

Section: Materials and Data Preprocessingmentioning

confidence: 99%

Low-Rank Graph-Regularized Structured Sparse Regression for Identifying Genetic Biomarkers

Zhu

Suk

Huang

et al. 2017

IEEE Trans. Big Data

View full text Add to dashboard Cite

In this paper, we propose a novel sparse regression method for Brain-Wide and Genome-Wide association study. Specifically, we impose a low-rank constraint on the weight coefficient matrix and then decompose it into two low-rank matrices, which find relationships in genetic features and in brain imaging features, respectively. We also introduce a sparse acyclic digraph with sparsity-inducing penalty to take further into account the correlations among the genetic variables, by which it can be possible to identify the representative SNPs that are highly associated with the brain imaging features. We optimize our objective function by jointly tackling low-rank regression and variable selection in a framework. In our method, the low-rank constraint allows us to conduct variable selection with the low-rank representations of the data; the learned low-sparsity weight coefficients allow discarding unimportant variables at the end. The experimental results on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset showed that the proposed method could select the important SNPs to more accurately estimate the brain imaging features than the state-of-the-art methods.

show abstract

“…In the past decades, a large number of efforts have been devoted to revealing the inter-modal correspondence via learning a shared embedding space for cross-modal similarity measurement Kang et al (2015a); Wang et al (2015); Jin et al (2015); Menon et al (2015); Irie et al (2015); Chang et al (2017b). For example, Canonical Correlation Analysis (CCA) and its extensions to kernel version Hotelling (1936); Hardoon et al (2004) aim to learn a common representation by mutually maximizing the correlation between their projections onto the shared basis vectors; Latent Dirichlet Allocation (LDA) based methods ; Barnard et al (2003); Wang et al (2009) ;Jia et al (2011); Xiaojun Chang and Hauptmann (2017) establish the shared latent semantic model through the joint distribution of images and the corresponding annotations as well as the conditional relationships between them.…”

Section: Arxiv:170201229v2 [Cslg] 7 Jul 2017mentioning

confidence: 99%

Simple to complex cross-modal learning to rank

Luo

Chang

et al. 2017

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval. Some studies formalize the cross-modal retrieval tasks as a ranking problem and learn a shared multi-modal embedding space to measure the cross-modality similarity. However, previous methods often establish the shared embedding space based on linear mapping functions which might not be sophisticated enough to reveal more complicated inter-modal correspondences. Additionally, current studies assume that the rankings are of equal importance, and thus all rankings are used simultaneously, or a small number of rankings are selected randomly to train the embedding space at each iteration. Such strategies, however, always suffer from outliers as well as reduced generalization capability due to their lack of insightful understanding of procedure of human cognition. In this paper, we involve the self-paced learning theory with diversity into the cross-modal learning to rank and learn an optimal multi-modal embedding space based on non-linear mapping functions. This strategy enhances the model's robustness to outliers and achieves better generalization via training the model gradually from easy rankings by diverse queries to more complex ones. An efficient alternative algorithm is exploited to solve the proposed challenging problem with fast convergence in practice. Extensive experimental results on several benchmark datasets indicate that the proposed method achieves significant improvements over the state-of-the-arts in this literature.

show abstract

Bi-Level Semantic Representation Analysis for Multimedia Event Detection

Cited by 220 publications

References 35 publications

A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2

A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2

Low-Rank Graph-Regularized Structured Sparse Regression for Identifying Genetic Biomarkers

Simple to complex cross-modal learning to rank

Contact Info

Product

Resources

About