Tinghuai Wang
I am a research manager in Huawei Helsinki Research Center, where I have been leading the research in machine learning and computer vision. My recent research interests focus on multimodal foundation models and reinforcement learning.
I received my PhD from the University of Surrey and MSc from KTH and RWTH Aachen in machine learning and computer vision. I have more than 10 years experience in research and innovation roles at various industry research labs (Huawei Helsinki Research Center, Nokia, HP Labs, Sony Research Labs). I have published 40 peer-reviewed international journals and conference publications, including top venues ICML, AAAI, IJCAI, ICCV, BMVC, TVCG, TGRS, TMM, CVIU. My publications have won two IEEE best paper awards (MESH 2009, ICME 2015). I also (co-)invented 84 granted/pending patents filed in US and EU, with more than two dozens of technology transfers to influential products. I have been serving as programme committee member for top AI venues such as AAAI, IJCAI, and area chair of ICIP 2018, CVMP 2013-2016 and SIGRAPH/NPAR 2012-2016. I was awarded as distinguished PC member of IJCAI 2018.
Email  / 
Google Scholar  / 
Google Patents / 
Github
|
|
Research
I'm generally interested in computer vision/graphics, machine learning, and reinforcement learning.
Representative papers and patents are listed as follows. Full list of publications can be found in my Google Scholar page.
|
|
Probabilistic Subgoal Representations for Hierarchical Reinforcement Learning
Vivienne Huiling Wang*,
Tinghuai Wang*,
Wenyan Yang,
Joni-Kristian Kämäräinen,
Joni Pajarinen
The Forty-first International Conference on Machine Learning (ICML), 2024
We propose a new Gaussian processes (GPs) based method for learning probabilistic subgoal representations in Hierarchical Reinforcement Learning (HRL).
|
|
State-Conditioned Adversarial Subgoal Generation
Vivienne Huiling Wang,
Joni Pajarinen,
Tinghuai Wang,
Joni-Kristian Kämäräinen
Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023
pdf
We propose a novel adversarially guided subgoal generation framework for goal-conditioned HRL to mitigate the issue of non-stationarity in off-policy training.
|
|
“Smartphone PDR/GNSS Integration via Factor Graph Optimization
for Pedestrian Navigation”
Changhui Jiang, Yuwei Chen, hen Chen, Jianxin Jia, Haibin Sun, Tinghuai Wang, Juha Hyyppä
IEEE Transactions on Instrumentation and Measurement, 2022
pdf
We propose two novel factor graph optimization (FGO)-based models to improve smartphone positioning accuracy by integrating pedestrian dead reckoning (PDR) with GNSS data. The first model combines position data from both PDR and GNSS, while the second tackles heading angle errors and smartphone misalignment by integrating PDR step length with GNSS.
|
|
“Tradeoffs in the Spatial and Spectral Resolution of Airborne Hyperspectral Imaging Systems: A Crop Identification Case Study”
Jianxin Jia, Jinsong Chen, Xiaorou Zheng, Yueming Wang, Shanxin Guo, Haibin Sun, Changhui Jiang, Mika Karjalainen, Kirsi Karila, Zhiyong Duan, Tinghuai Wang, Chong Xu, Juha Hyyppä, Yuwei Chen
IEEE Transactions on Instrumentation and Measurement, 2022
pdf
We investigate the tradeoffs between signal-to-noise ratio (SNR), spatial resolution, and spectral resolution in hyperspectral imaging for crop identification, addressing gaps in existing research. Results show that overall accuracy decreases with lower SNR and coarser spectral resolution but improves with lower spatial resolution. This study bridges the gap between hyperspectral sensor design and practical crop identification.
|
|
Hyperspectral Image Classification via Pyramid Graph Reasoning
Tinghuai Wang,
Guangming Wang,
Kuan Eeik Tan,
Donghui Tan
ISVC, 2020
pdf
We design an architecture to encode the multiple spectral contextual information in the form of spectral pyramid of multiple embedding spaces. In each spectral embedding space, we propose graph attention mechanism to explicitly perform interpretable reasoning in the spatial domain based on the connection in spectral feature space.
|
|
Simultaneously Learning Architectures and Features of Deep Neural Networks
Tinghuai Wang,
Lixin Fan,
Huiling Wang
ICANN, 2019
pdf
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 the diversities between filters and this diversity-based regularization term improves the trade-off between model sizes and accuracies. Nokia proposal to ISO/IEC DIS 15938-17
Information technology — Multimedia content description interface — Part 17: Compression of neural networks for multimedia content description and analysis
|
|
Cross-Granularity Attention Network for Semantic Segmentation
Lingyu Zhu*,
Tinghuai Wang*,
Emre Aksu,
Joni-Kristian Kämäräinen
ICCV, 2019
pdf
We propose a categorical attention mechanism to propagate consistent category-oriented information across multi-granularity contextual interpretations to close the semantic gap residing in CNN feature hierarchy; a cross-granularity contour enhancement mechanism is also proposed to propagate rich boundary cues from early layers to deep layers. These novel mechanisms boost the essentials in segmentation, i.e., region-wise semantic coherence and accurate object contour localization.
|
|
Portrait Instance Segmentation for Mobile Devices
Lingyu Zhu*,
Tinghuai Wang*,
Emre Aksu,
Joni-Kristian Kämäräinen
ICME, 2019
pdf
We propose a novel and efficient non-parametric affinity model to achieve efficient instance segmentation on mobile devices. We also present a portrait image dataset with instance level annotations dedicated to evaluating portrait instance segmentation algorithms.
|
|
Semantic segmentation based on a hierarchy of neural networks
Tinghuai Wang
US10872275B2, 2019
pdf
Method for Nokia 8 Portrait Segmentation.
|
|
Cross-Granularity Graph Inference for Semantic Video Object Segmentation
Huiling Wang,
Tinghuai Wang,
Ke Chen,
Joni-Kristian Kämäräinen
IJCAI, 2017
pdf
/
video
We address semantic video object segmentation
via a novel cross-granularity hierarchical graphical
model to integrate tracklet and object proposal reasoning with superpixel labeling.
|
|
Benchmarking Non-Photorealistic Rendering of Portraits
Paul L. Rosin, David Mould, Itamar Berger, John P. Collomosse, Yu-Kun Lai, Chuan Li, Hua Li, Ariel Shamir, Michael Wand, Tinghuai Wang, Holger Winnemöller
NPAR, 2017
pdf
We present a set of images for helping NPR practitioners evaluate their image-based portrait stylisation algorithms.
|
|
Method, an apparatus and a computer program product for object detection
Tinghuai Wang,
US10778988B2, 2017
pdf
Video object detection method for Nokia OZO camera.
|
|
Primary Object Discovery and Segmentation in Videos via Graph-Based Transductive Inference
Huiling Wang,
Tinghuai Wang
CVIU, 2016
pdf
We present a novel algorithm that detects recurring primary object and learns cohort object proposals over space-time in video. Our core contribution is a graph transduction process that exploits both appearance cues learned from rudimentary detections of object-like regions, and the intrinsic structures within video data.
|
|
Boosting Objectness: Semi-Supervised Learning for Object Detection and Segmentation in Multi-View Images
Huiling Wang,
Tinghuai Wang
ICASSP, 2016
pdf
/
video #1
/
video #1
This paper presents a method to detect and segment recurring object from multi-view images. By harnessing a top-down explicit notion of object, our method overcomes the limitations of previous bottom-up methods that often mis-segment an object and de- livers high quality segmentation.
|
|
Methods and apparatuses for determining positions of multi-directional image capture apparatuses
Tinghuai Wang, Yu You, Lixin Fan, Kimmo Roimela
GB2557212A, 2016
pdf
Method for Nokia OZO camera positioning.
|
|
Rendering of user-defined message having 3D motion information
Yu You,
Lixin Fan,
Tinghuai Wang
US10701433B2, 2016
pdf
Method for Nokia OZO VR content rendering.
|
|
Apparatus for sharing objects of interest and associated methods
Tinghuai Wang,
Lixin Fan,
Yu You
US10701433B2, 2016
pdf
Method for Nokia OZO VR content view synthesis.
|
|
A Weakly Supervised Geodesic Level Set Framework for Interactive Image Segmentation
Tinghuai Wang,
Huiling Wang,
Lixin Fan
Neurocomputing, 2015
pdf
We combine geodesic distance information with the flexibility of level set methods in energy minimization, leveraging the complementary strengths of each to promote accurate boundary placement and strong region connectivity while requiring less user interaction.
|
|
Robust Interactive Image Segmentation with Weak Supervision for Mobile Touch Screen Devices
Tinghuai Wang,
Huiling Wang,
Lixin Fan
ICME, 2015
pdf
/
video
We present a a robust and efficient approach for segmenting images with less and intuitive user interaction, particularly targeted for mobile touch screen devices.
|
|
TouchCut: Fast Image and Video Segmentation using Single-Touch Interaction
Tinghuai Wang,
Bo Han,
John Collomosse
CVIU, 2014
pdf
/
video
We present TouchCut; a robust and efficient algorithm for segmenting image and video sequences with minimal user interaction i.e., only a single finger touch to identify the object of interest in the image or first frame of video. This approach to visual object cut-out provides a practical solution for image and video segmentation on compact touch screen devices, facilitating spatially localized media manipulation.
|
|
Wide Baseline Multi-View Video Matting using a Hybrid Markov Random Field
Tinghuai Wang,
John Collomosse,
Adrian Hilton
ICPR, 2014
pdf
We present a novel multi-view video matting
method suitable for incorporation into a 4DPC pipeline. The
key contributions of this method are 1) the propagation of
appearance and spatial information across views using superpixel matching and a novel MRF that solves the mattes
simultaneously across all views, 2) the temporal propagation
of appearance and spatial information forward in time.
|
|
Apparatus, a method and a computer program for image processing
Tinghuai Wang,
US9495755B2, 2013
pdf
Interactive segmentation method for Nokia Lumia Phone.
|
|
State of the'Art': A Taxonomy of Artistic Stylization Techniques for Images and Video
Jan Eric Kyprianidis,
John Collomosse,
Tinghuai Wang,
Tobias Isenberg
TVCG, 2013
pdf
We survey the field of non-photorealistic rendering (NPR), focusing on techniques for transforming 2D input
(images and video) into artistically stylized renderings.
|
|
Learnable Stroke Models for Example-based Portrait Painting
Tinghuai Wang,,
John Collomosse,
Andrew Hunter,
Darryl Greig
BMVC, 2013
pdf
/
poster
We present the first machine learning model which is capable of learning artistic style for portraits by analyzing training
data from a human artist. Given a training pair — a source image and painting of that image — a non-parametric model of style is learned by observing the geometry and tone of brush strokes local to image features.
|
|
Markov Random Fields for Sketch based Video Retrieval
Rui Hu,
Stuart James,
Tinghuai Wang,
John Collomosse
ICMR, 2013
pdf
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
Random Field (MRF) optimization.
|
|
Progressive Motion Diffusion of Labeling Priors for Coherent Video Segmentation
Tinghuai Wang,
John Collomosse
TMM, 2012
pdf
/
video
We present a novel algorithm for video segmentation and our core contribution is a multi-frame probabilistic motion diffusion model to incorporate labelling priors from previous frames to influence the segmentation in new frame.
|
|
Stylized Ambient Displays of Digital Media Collections
Tinghuai Wang, John Collomosse, David Slatter, Phil Cheatle, Darryl Greig
Computer and Graphics, 2011
pdf
/
poster
We present a system to breathe life into home digital media collections, drawing upon artistic stylization to create a ‘‘Digital Ambient Display’’ that automatically selects, stylizes and transitions between digital contents in a semantically meaningful sequence.
|
|
A Bag-of-Regions Approach to Sketch-based Image Retrieval
Rui Hu, Tinghuai Wang, John Collomosse
ICIP, 2011
pdf
We present a sketch based image retrieval
system built on a bag of regions which encodes the complete information of salient shapes at various level of details
in the form of enclosed contours of regions presenting a coherent visual appearance.
|
|
An Evolutionary Approach to Automatic Video Editing
Tinghuai Wang, Andrew Mansfield, John Collomosse, Rui Hu
CVMP, 2009
pdf
We interpret the sequence of editting operations
applied to footage as a ‘program’ comprising cutting,
panning and zooming constructs. We develop a Genetic
Programming (GP) framework for representing and evolving
such programs. Under this framework, the search for an
aesthetically pleasing video edit becomes a search for the
optimal genetic program. Our aesthetic criterion promotes
the inclusion of people in shots, whilst penalising rapid shot
changes or shot changes in the presence of camera motion.
|
|