Learn More
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate(More)
Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of(More)
Recent gait recognition systems often suffer from the challenges including viewing angle variation and large intra-class variations. In order to address these challenges, this paper presents a robust View Transformation Model for gait recognition. Based on the gait energy image, the proposed method establishes a robust view transformation model via robust(More)
Pedestrian tracking in multi-camera is an important task in intelligent visual surveillance system, but it suffers from the problem of large appearance variations of the same person under different cameras. Inspired by the success of existing view transformation model in multi-view gait recognition, we present a novel view transformation model based(More)
The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e.g. 'I see a shiny red chair'). In this paper, we formulate the problem of joint visual attribute and object class image segmentation as a dense multi-labelling problem, where each pixel in an image(More)
AIMS High shear stress (HSS) can have significant impact on angiogenesis and atherosclerosis in collateral arteries near the bifurcation and curvature regions. Here, we investigate the spatiotemporal pattern of HSS-induced intracellular calcium alteration. METHODS AND RESULTS Genetically encoded biosensors based on fluorescence resonance energy transfer(More)
Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns(More)
The cytosolic protein α-catenin is a postulated force transducer at cadherin complexes. The demonstration of force activation, identification of consequent downstream events in live cells, and development of tools to study these dynamic processes in living cells are central to elucidating the role of α-catenin in cellular mechanics and tissue function. Here(More)
We address the problem of semantic segmentation using deep learning. Most segmentation systems include a Conditional Random Field (CRF) to produce a structured output that is consistent with the image's visual features. Recent deep learning approaches have incorporated CRFs into Convolutional Neural Networks (CNNs), with some even training the CRF(More)
Cumulative foot pressure images represent the 2D ground reaction force during one gait cycle. Biomedical and forensic studies show that humans can be distinguished by unique limb movement patterns and ground reaction force. Considering continuous gait pose images and corresponding cumulative foot pressure images, this paper presents a cascade fusion scheme(More)