Xiaolong Wang

Learn More
Computer vision has a great potential to help our daily lives by searching for lost keys, watering flowers or reminding us to take a pill. To succeed with such tasks, computer vision methods need to be trained from real and diverse examples of our daily dynamic scenes. While most of such scenes are not particularly exciting, they typically do not appear on(More)
What defines an action like "kicking ball"? We argue that the true meaning of an action lies in the change or transformation an action brings to the environment. In this paper, we propose a novel representation for actions by modeling an action as a transformation which changes the state of the environment before the action happens (precondition) to the(More)
In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture? We propose to build upon the decades of hard work in 3D scene understanding to design a new CNN architecture(More)
This paper proposes a reconfigurable model to recognize and detect multiclass (or multiview) objects with large variation in appearance. Compared with well acknowledged hierarchical models, we study two advanced capabilities in hierarchy for object modeling: (i)``switch'' variables(i.e. or-nodes) for specifying alternative compositions, and (ii) making(More)
Current generative frameworks use end-to-end learning and generate images by sampling from uniform noise distribution. However, these approaches ignore the most basic principle of image formation: images are product of: (a) Structure: the underlying 3D model; (b) Style: the texture mapped onto structure. In this paper, we factorize the image generation(More)
This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree. This model extends the traditional hierarchical tree structures by introducing the “switch” variables (i.e. the or-nodes) that explicitly(More)
The theory of targeting cancer stem-like cells (CSCs) provides novel strategy for cancer treatment. In the present study, we examined the inhibitory effect of Huaier aqueous extract on eradicating breast cancer stem cells and explored the underlying mechanisms. Our data demonstrated that various concentrations of Huaier extract significantly decreased the(More)
Chemoresistance is a challenge for clinician in management of tongue cancer. Therefore, it is necessary to explore alternative therapeutic methods to overcome drug resistance. miRNAs are endogenous −22nt RNAs that play important regulatory roles by targeting mRNAs. miR-21, an essential oncogenic molecule, is associated with chemosensitivity of several human(More)
Insulin-like growth factor (IGF) signaling is involved in oral squamous cell carcinoma (OSCC), but IGF-1 receptor (IGF-1R)-mediated intricate regulatory networks among molecular interactions and signalling path ways in OSCC remain unclear. Here, we found that overexpression of IGF-1R and insulin receptor substrate-2 (IRS-2) was negatively associated with(More)
Tumor suppressor p53 plays a central role in tumor suppression. To ensure its proper function, the levels and activity of p53 are under a tight regulation in cells. MicroRNAs are short non-coding RNAs that play an important role in regulation of gene expression. Recently, microRNA-339-5p has been reported to be frequently down-regulated in colorectal(More)