No abstract

Detecting objects becomes difficult when we need to deal with large shape deformation, occlusion and low resolution. We propose a novel approach to i) handle large deformations and partial occlusions in animals (as examples of highly deformable objects), ii) describe them in terms of body parts, and iii) detect them when their body parts are hard to detect (e.g., animals depicted at low resolution). We represent the holistic object and body parts separately and use a fully connected model to arrange templates for the holistic object and body parts. Our model automatically decouples the holistic object or body parts from the model when they are hard to detect. This enables us to represent a large number of holistic object and body part combinations to better deal with different "detectability" patterns caused by deformations, occlusion and/or low resolution.We apply our method to the six animal categories in the PASCAL VOC dataset and show that our method significantly improves state-of-the-art (by 4.1% AP) and provides a richer representation for objects. During training we use annotations for body parts (e.g., head, torso, etc), making use of a new dataset of fully annotated object parts for PAS-CAL VOC 2010, which provides a mask for each part.

Integrating multiple different yet complementary feature representations has been proved to be an effective way for boosting tracking performance. This paper investigates how to perform robust object tracking in challenging scenarios by adaptively incorporating information from grayscale and thermal videos, and proposes a novel collaborative algorithm for online tracking. In particular, an adaptive fusion scheme is proposed based on collaborative sparse representation in Bayesian filtering framework. We jointly optimize sparse codes and the reliable weights of different modalities in an online way. In addition, this paper contributes a comprehensive video benchmark, which includes 50 grayscale-thermal sequences and their ground truth annotations for tracking purpose. The videos are with high diversity and the annotations were finished by one single person to guarantee consistency. Extensive experiments against other state-of-the-art trackers with both grayscale and grayscale-thermal inputs demonstrate the effectiveness of the proposed tracking approach. Through analyzing quantitative results, we also provide basic insights and potential future research directions in grayscale-thermal tracking.

Colorectal neoplasia differentially expressed (CRNDE) is the most upregulated long noncoding RNA (lncRNA) in glioma. Herein, the function and potential molecular mechanisms of CRNDE and miR-384 were illustrated in glioma cells. CRNDE overexpression facilitated cell proliferation, migration, and invasion, while inhibited glioma cells apoptosis. Quantitative real-time polymerase chain reaction (PCR) demonstrated that miR-384 was downregulated in human glioma tissues and glioma cell lines. Moreover, restoration of miR-384 exerted tumor-suppressive functions. In addition, the expression of miR-384 was negatively correlated with CRNDE expression. A binding region between CRNDE and miR-384 was confirmed using luciferase assays. Moreover, CRNDE promoted cell malignant behavior by decreasing miR-384 expression. At the molecular level, treatment by CRNDE knockdown or miR-384 overexpression resulted in a decrease of piwi-like RNA-mediated gene silencing 4 (PIWIL4) protein. Besides, PIWIL4 was identified as a target of miR-384 and plays an oncogenic role in glioma. Similarly, downstream proteins of PIWIL4 such as STAT3, cyclin D1, VEGFA, SLUG, MMP-9, caspase 3, Bcl-2, and bcl-xL were modulated when treated with miR-384 and PIWIL4. Remarkably, CRNDE knockdown combined with miR-384 overexpression led to tumor regression in vivo. Overall, these results depicted a novel pathway mediated by CRNDE in glioma, which may be a potential application for glioma therapy.