About AMP Lab
Publications People Links
Personal Homepage: http://dliu.cmu.googlepages.com
Lab: Porter Hall B6
Phone: 412-268-1171 (Office)
Porter Hall B23, CMU ECE
- Currently working on
Object Detection/Recognition [Download papers (CVPR_BP) (ICASSP) (ICIP)]
My text detection
system received the most accurate results in a recent VACE evaluation.
My recent interest is on
Markov Random Field (MRF), probabilistic Latent Semantic Analysis (PLSA) and
Presentation slides on PLSA
Presentation slides on Semantic-Shift
Video demos accompanying
the Semantic-Shift presentation slides [ 1 ] [ 2 ]
- Shape Matching based on Shape Context and ICP
The shape context method
can be integrated into the iterative closest point (ICP) method as an auxiliary
feature vector, enriching the representation of an image point from spatial
information only, to spatial and shape information. This yields a
registration method more robust than the original ICP method. The method
is general for 2D shapes. It does not calculate derivatives, hence being
able to handle shapes with junctions and discontinuities.
translation error 6.3 pixels
rotation error 7.5 degrees
with soft shape context
translation error 1.6 pixels
rotation error 1.8 degrees
translation error 8.2 pixels
rotation error 6.1 degrees
soft shape context
translation error 0.2 pixels
rotation error 5.7 degrees
- Probabilistic Relevance Feedback for Image Retrieval
More can be found at the probabilistic
relevance feedback link.
Top of this page
- Content-based Image Retrieval
details on the project please see the trademark retrieval
project and the probabilistic
relevance feedback project.
- Object Detection and Recognition
discovery website is up.
Top of this page
Liu and T. Chen, "DISCOV:
A Framework for Discovering Objects in Video", IEEE
Transactions on Multimedia, 2008.
Huang, D. Liu and Li-Chen
Tracking in Cluttered Environment Using the Visual Probabilistic Data
Association Filter", IEEE Transactions on Robotics, 2006.
Liu and T. Chen, "Unsupervised
Image Categorization and Object Localization using Topic Models and
Correspondences between Images",
IEEE International Conference on Computer Vision, 2007.
Liu and T. Chen, "A
Topic-Motion Model for Unsupervised Video Object Discovery (Poster)",
IEEE Conference on Computer Vision and Pattern Recognition, 2007.
Liu and T. Chen, "Background
Cutout with Automatic Object Discovery (Poster)",
IEEE International Conference on Image Processing, 2007.
Liu and T. Chen, "Semantic-Shift
for Unsupervised Object Detection",
slides), Workshop on Beyond Patches, in conjunction with CVPR,
Liu, D. Chen, and T. Chen, "Latent
Layout Analysis for Discovering Objects in Images", IEEE
International Conference on Pattern Recognition,
D. Liu, D. Chen, and T. Chen, "Unsupervised
Image Layout Extraction", IEEE International Conference on
Image Processing, 2006.
D. Liu and T. Chen, "Content-Free
Image Retrieval using Bayesian Product Rule", IEEE International
Conference on Multimedia & Expo, 2006.
D. Liu and T. Chen, "Object
Detection in Video with Graphical Models", IEEE
International Conference on Acoustics, Speech, and
Signal Processing, 2006.
D. Liu, Simon Lucey,
Datong Chen and T. Chen, "Addressing
the Tunnel Vision Problem in Object Detection", AMP Tech Report, 2005.
D. Liu and T. Chen, "Probabilistic
relevance feedback for image retrieval with binary feature vectors",
IEEE Conference on Acoustics, Speech, and Signal
D. Liu and Tsuhan Chen, "Soft
shape context for iterative closest point registration", IEEE
International Conference on Image Processing, 2004.
D. Liu, L.C. Fu, S.H. Hsu, T.K. Kuo, "Analysis
on an On-Line Iterative Correction Control Law for Visual Tracking",
Asian Control Conference, 2002.
D. Liu, L.C. Fu, "Target
Tracking in an Environment of Nearly Stationary and Biased Clutter",
IEEE International Conference on Intelligent Robots and Systems, 2001.
Liu, L.C. Fu, T.K. Kuo, J.W. Yeh, "PDA
Filter Based on the Winner-Update Strategy for Visual Tracking",
Chinese Automatic Control Conference 2001 (Best
W.G. Yau, L.C. Fu, D. Liu, "Design
and Implementation of a Visual Servoing System for Realistic Air Target
Tracking", IEEE International Conference on Robotics &
W.G. Yau, Li-Chen Fu,
D. Liu, "Robust
Real-time 3D Trajectory Tracking Algorithms for Visual Tracking Using Weak
Perspective Projection", American Control Conference, 2001.
Top of this page