Tinghuai Wang

Nokia CTO Labs

This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate filters while suppressing contributions of less relevant ones. In the meanwhile, we further propose to enforce...

Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part regions in unconstrained environments. Specifically we propose a convolutional neural network (CNN) architectu...

This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate filters while suppressing contributions of less relevant ones. In the meanwhile, we further propose to enforce...

We propose a novel approach for modeling semantic contextual relationships in videos. This graph-based model enables the learning and propagation of higher-level spatial-temporal contexts to facilitate the semantic labeling of local regions. We introduce an exemplar-based nonparametric view of contextual cues, where the inherent relationships impli...

We address semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling. Tracklet characterizes varying spatial-temporal relations of video object which, however, quite often suffers from sporadic local outliers. In order to acquire high-qu...

We present a set of images for helping NPR practitioners evaluate their image-based portrait stylisation algorithms. Using a standard set both facilitates comparisons with other methods and helps ensure that presented results are representative. We give two levels of difficulty, each consisting of 20 images selected systematically so as to provide...

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labelled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing th...

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively exploiting the representation power of CNN with limited training data remains a challenge. Simply borrowing the...

The proliferation of video data makes it imperative to develop automatic approaches that semantically analyze and summarize the ever-growing massive visual data. As opposed to existing approaches built on still images, we propose an algorithm that detects recurring primary object and learns cohort object proposals over space-time in video. Our core...

Interactive image segmentation is growingly useful for selecting objects of interest in images, facilitating spatially localized media manipulation especially on touch screen devices. We present a robust and efficient approach for segmenting image with less and intuitive user interaction. Our approach combines geodesic distance information with the...

We describe a novel framework for segmenting a time- and view-coherent foreground matte sequence from synchronised multiple view video. We construct a Markov Random Field (MRF) comprising links between super pixels corresponded across views, and links between super pixels and their constituent pixels. Texture, colour and disparity cues are incorpor...

We propose an unsupervised video object segmentation algorithm that detects recurring objects and learns cohort object proposals over space-time. Our core contribution is a graph transduction process that learns object proposals densely over space-time, exploiting both appearance models learned from rudimentary detections of sparse object-like regi...

We describe a new system for searching video databases using free-hand sketched queries. Our query sketches depict both object appearance and motion, and are annotated with keywords that indicate the semantic category of each object. We parse space-time volumes from video to form graph representation, which we match to sketches under a Markov Rando...

We present TouchCut; a robust and efficient algorithm for segmenting image and video sequences with minimal user interaction. Our algorithm requires only a single finger touch to identify the object of interest in the image or first frame of video. Our approach is based on a level set framework, with an appearance model fusing edge, region texture...

We present a novel algorithm for stylizing photographs into portrait paintings comprised of curved brush strokes. Rather than drawing upon a prescribed set of heuristics to place strokes, our system learns a flexible model of artistic style by analyzing training data from a human artist. Given a training pair - A source image and painting of that i...

This paper surveys the field of non-photorealistic rendering (NPR), focusing on techniques for transforming 2D input (images and video) into artistically stylized renderings. We first present a taxonomy of the 2D NPR algorithms developed over the past two decades, structured according to the design characteristics and behavior of each technique. We...

We present a robust algorithm for temporally coherent video segmentation. Our approach is driven by multi-label graph cut applied to successive frames, fusing information from the current frame with an appearance model and labeling priors propagated forwarded from past frames. We propagate using a novel motion diffusion model, producing a per-pixel...

In this paper, we propose an object segmentation algorithm driven by minimal user interactions. Compared to previous user-guided systems, our system can cut out the desired object in a given image with only a single finger touch minimizing user effort. The proposed model harnesses both edge and region based local information in an adaptive manner a...

This paper presents a system for retrieving photographs using free-hand sketched queries. Regions are extracted from each image by gathering nodes of a hierarchical image segmentation into a bag-of-regions (BoR) representation. The BoR represents object shape at multiple scales, encoding shape even in the presence of adjacent clutter. We extract a...

The falling cost of digital cameras and camcorders has encouraged the creation of massive collections of personal digital media. However, once captured, this media is infrequently accessed and often lies dormant on users' PCs. We present a system to breathe life into home digital media collections, drawing upon artistic stylization to create a ''Di...

We present a new algorithm for segmenting video frames into temporally stable colored regions, applying our technique to create artistic stylizations (e.g. cartoons and paintings) from real video sequences. Our approach is based on a multi-label graph cut applied to successive frames, in which the color data term and label priors are incrementally...

Falling hardware costs have prompted an explosion in casual video capture by domestic users. Yet, this video is infrequently accessed post-capture and often lies dormant on users' PCs. We present a system to breathe life into home video repositories, drawing upon artistic stylization to create a "Digital Ambient Display" that automatically selects,...

Digital video has become affordable and attractive to home users, but skill and manual labour are still required to transform amateur footage into aesthetically pleasing movies. We present a novel algorithm for transforming raw home video footage into concise, temporally salient clips. We interpret the sequence of editing operations applied to foot...

The effect of the primary user traffic on the performance of spectrum sensing is investigated. The investigation considers both local and collaborative spectrum sensing. Numerical results show that the performance of spectrum sensing can be significantly degraded if the primary user channel state changes frequently, and that collaborative spectrum...

A wireless mesh network (WMN) serves to extend the coverage of access points (APs) by means of relay nodes (RNs) that forward data between mobile nodes (MNs) and an AP. This concept reduces deployment costs by exchanging the wires between APs by a wireless backbone. Unfortunately, this also reduces capacity, owing to multiple transmissions of the s...

The relay technique is an effective way to enlarge the cell coverage and enhance the spectral efficiency in wireless network. In this paper, we propose a novel cooperative transmission protocol based on the channel coding, named the adaptive cooperative coding (ACC), which is im-plemented by transmitting the rate-compatible punctured convolutional...