Deep convolutional neural networks (CNNs) have shown superior performance on the task of single-label image classification. However, the applicability of CNNs to multi-label images still remains an open problem, mainly because of two reasons. First, each image is usually treated as an inseparable entity and represented as one instance, which mixes the visual information corresponding to different labels. Second, the correlations amongst labels are often overlooked. To address these limitations, we propose a deep multi-modal CNN for multi-instance multi-label image classification, called MMCNN-MIML. By combining CNNs with multi-instance multi-label (MIML) learning, our model represents each image as a bag of instances for image classification and inherits the merits of both CNNs and MIML. In particular, MMCNN-MIML has three main appealing properties: 1) it can automatically generate instance representations for MIML by exploiting the architecture of CNNs; 2) it takes advantage of the label correlations by grouping labels in its later layers; and 3) it incorporates the textual context of label groups to generate multi-modal instances, which are effective in discriminating visually similar objects belonging to different groups. Empirical studies on several benchmark multi-label image data sets show that MMCNN-MIML significantly outperforms the state-of-the-art baselines on multi-label image classification tasks.

No abstract

No abstract

The mitogen activated protein kinases (MAPK) signaling cascade plays an important role in cell life. We proved that small interfering RNAs targeting MAPK1 (siRNA-2) could inhibit HeLa cell growth, but the effects of siRNA-2 on gene expression profile were unclear. Using Affymetrix GeneChip HG-U133A 2.0, we identified the long-term changes for 48 h in gene expression profile in HeLa cell treated by siRNA-2. The results showed that expressions of 181 genes were altered by siRNA-2 and were divided into two groups: (i) one group showed downregulation by siRNA-2, including the proliferation associated genes, small G protein, cytoskeleton associated protein and extracellular matrix associated protein; and (ii) the other group showed upregulation by siRNA-2, including interferon response genes, OAS family, TRIM family and apoptosis associated genes. The results of Real-time quantitative PCR for MAPK1, NUP188, P38, STAT1, STAT2, MPL and OAS1 were consistent with that of gene chip. Two networks were found to react substantially to the downregulation of MAPK1 by siRNA-2. One of the networks regulates cell growth through cell-cycle control, apoptosis and cytoskeleton. The other network is related to interferon-like response. Our findings suggest that siRNA-mediated downregulation of MAPK1 could be an attractive strategy for cancer therapy.

Image annotation plays a significant role in large scale image understanding, indexing and retrieval. The Probability Topic Models (PTMs) attempt to address this issue by learning latent representations of input samples, and have been shown to be effective by existing studies. Though useful, PTM has some limitations in interpreting the latent representations of images and texts, which if addressed would broaden its applicability. In this paper, we introduce sparsity to PTM to improve the interpretability of the inferred latent representations. Extending the Sparse Topical Coding that originally designed for unimodal documents learning, we propose a non-probabilistic formulation of PTM for automatic image annotation, namely Sparse Multi-Modal Topical Coding. Beyond controlling the sparsity, our model can capture more compact correlations between words and image regions. Empirical results on some benchmark datasets show that our model achieves better