A high-quality video denoising algorithm based on reliable motion estimation
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
TagSense: a smartphone-based approach to automatic image tagging
MobiSys '11 Proceedings of the 9th international conference on Mobile systems, applications, and services
Detecting customers' buying events on a real-life database
CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part I
Cortical surface strain estimation using stereovision
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Video motion estimation with temporal coherence
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
Modeling and segmentation of floating foreground and background in videos
Pattern Recognition
Face morphing using 3D-aware appearance optimization
Proceedings of Graphics Interface 2012
Robust patch-based hdr reconstruction of dynamic scenes
ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2012
Video object segmentation with shortest path
Proceedings of the 20th ACM international conference on Multimedia
Proceedings of the 20th ACM international conference on Multimedia
Background subtraction using low rank and group sparsity constraints
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
3D reconstruction of dynamic scenes with multiple handheld cameras
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Learning to segment a video to clips based on scene and camera motion
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Non-causal temporal prior for video deblocking
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Depth extraction from video using non-parametric sampling
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
A complete confidence framework for optical flow
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
SCoBeP: Dense image registration using sparse coding and belief propagation
Journal of Visual Communication and Image Representation
Pattern Recognition Letters
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Non-rigid target tracking based on 'flow-cut' in pair-wise frames with online hough forests
Proceedings of the 21st ACM international conference on Multimedia
Patch-based high dynamic range video
ACM Transactions on Graphics (TOG)
Image and Vision Computing
When is a confidence measure good enough?
ICVS'13 Proceedings of the 9th international conference on Computer Vision Systems
Shopping behavior recognition using a language modeling analogy
Pattern Recognition Letters
Neurocomputing
Automatic cinemagraph portraits
EGSR '13 Proceedings of the Eurographics Symposium on Rendering
Hi-index | 0.00 |
The focus of motion analysis has been on estimating a flow vector for every pixel by matching intensities. In my thesis, I will explore motion representations beyond the pixel level and new applications to which these representations lead. I first focus on analyzing motion from video sequences. Traditional motion analysis suffers from the inappropriate modeling of the grouping relationship of pixels and from a lack of ground-truth data. Using layers as the interface for humans to interact with videos, we build a human-assisted motion annotation system to obtain ground-truth motion, missing in the literature, for natural video sequences. Furthermore, we show that with the layer representation, we can detect and magnify small motions to make them visible to human eyes. Then we move to a contour presentation to analyze the motion for textureless objects under occlusion. We demonstrate that simultaneous boundary grouping and motion analysis can solve challenging data, where the traditional pixel-wise motion analysis fails. In the second part of my thesis, I will show the benefits of matching local image structures instead of intensity values. We propose SIFT flow that establishes dense, semantically meaningful correspondence between two images across scenes by matching pixel-wise SIFT features. Using SIFT flow, we develop a new framework for image parsing by transferring the metadata information, such as annotation, motion and depth, from the images in a large database to an unknown query image. We demonstrate this framework using new applications such as predicting motion from a single image and motion synthesis via object transfer. Based on SIFT flow, we introduce a nonparametric scene parsing system using label transfer, with very promising experimental results suggesting that our system outperforms state-of-the-art techniques based on training classifiers. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)