欢迎光临 赵明 的个人主页!
![]() |
愿神祝福你! 神爱世人,甚至将他的独生子赐给他们,叫一切信他的,不至灭亡, 反得永生 。(约 3:16) 叫人活着的乃是灵,肉体是无益的 。(约 6:63) 若有人在基督里,他就是新造的人 。旧事已过,都变成新的了 。(林后 5:17) |
我现在在位于美国加州硅谷的Google公司工作. 消息更新 Two papers are accepted by CVPR 2010 (details coming soon)
[教育][工作][研究][论文][家人][老师][朋友][兴趣] Sep.1999-Jul.2004 博士, 浙江大学 Ph.D., Zhejiang University,
P.R.China. 专业: 计算机视觉与模式识别 Specialty:
Computer Vision and Pattern Recognition. 导师: 陈纯教授 Supervisor: Prof. Chun Chen Sep.1995-Jul.1999 本科,
兰州大学 B.S., Lanzhou University,
P.R.China Sep.1989-Jul.1995 中学, 彭州中学 Pengzhou High School
2007年2月 Google Inc. at Mountain View 2004年8月 到 2007年2月 新加坡国立大学博士后
Postdoc (Research Fellow) at ·
TRECVID
2005 (Jul. 2005 -- Sep. 2005) ·
3D
Face Reconstruction and Animation (May. 2005 -- Now) ·
Photo
Album Annotation (Feb. 2005 -- Now) ·
TRECVID
2004 (Aug. 2004 -- Sep. 2004) ·
PersonX
Detection in News Video (Aug. 2004 -- Feb. 2005) ·
Face
Alignment for Face Recognition (Aug. 2003 ~ Jul. 2004) ·
Face
Alignment and Iris Localization (Dec. 2002 ~ Jul. 2003) ·
Face
Alignment for 3D Facial Reconstruction (Sep. 2002 ~ Nov. 2002) ·
Computer
Aided Medical Imaging Diagnosis. (Dec. 2001 ~ Apr. 2002) ·
Content-Based
Video Retrieval and Browsing (Aug. 2001 ~ Jul. 2002) ·
Video
Object Segmentation (Sep. 1999 ~ Jul. 2001) Last updated on Feb 25, 2010 PDT.
Google Landmark: Tour the World
Face Recogntion on Web Videos and Personal Photo Ablums
Concept Detection/Visual Object Recognition
教育
博士论文: 二维视觉对象分割 Thesis: 2D Visual Object Segmentation
专业: 计算机科学 Specialty: Computer
Science
工作经历
研究经历
TRECVID is TREC Video Retrieval Evaluation. It is sponsored by the National
Institute of Standards and Technology (NIST). TRECVID is the most challenging evaluation
for video retrieval in the world. Most famous research groups in video
retrieval participated, such as IBM, CMU, Columbia University.There are four
tasks this year: Shot boundary detection, Low-level feature extraction (camera
motion), High-level feature extraction, Search and Exploring BBC rushes. We
gained the first position in the search task.
3D face reconstruction from image(s) has a wide range of applications, such as
face animation and recognition. The slow speed of the 3D morphable model is due
to the texture mapping. To improve the speed, we only use the shape matching to
recover the 3D shape and use texture mapping to get the texture. However, only
with the shape information, one image is not enough for accurate 3D face
reconstruction. So we propose to use multiple images with the morphable shape
model. First, with the feature points given on the multiple images, the 3D
coordinates of the feature points are estimate by the pose estimation. Then,
frontal and profile 2D morphable shape models are built to estimate the 3D
morphable shape model. These two steps works iteratively to improve the result.
At last, the texture is extracted from multiple images with the pose estimation
from the estimated 3D face.
Home photos are becoming more common place and large quantity of home photos
are available on the Internet. There is a need of efficient techniques to
manage this large collection of photos, some with text annotations but many
without. Basically, we need to identify the following essential attributes in
home photos like the place, time, people. With these attributes, a series of
questions can be asked about photos by time, place, people, and their
combinations.
TRECVID is TREC Video Retrieval Evaluation. It is sponsored by the National
Institute of Standards and Technology (NIST). TRECVID is the most challenging
evaluation for video retrieval in the world. Most famous research groups in
video retrieval participated, such as IBM, CMU, Columbia University.There are
four tasks this year: Shot boundary detection, Story segmentation,Feature
extraction and Search. We gained the first position in the search task.
With the development of computer technology, more and more digital videos are
available, which demands more efficient access to video content. Video
retrieval thus becomes a hot research topic in multimedia. To achieve the goal
of video retrieval, it's important to find objects of interest to users in
video. For news video, which is a significant source of video, persons are the
most important objects. Thus finding a specific person, called finding "Person-X",
is essential to understand and retrieve news video. The goal of finding
Person-X is to find the shots where Person-X visually appears.
I aimed to use face alignment to improve the performance of face
recognition. Although face alignment is very important for high performance
face recognition, existing face recognition systems often use simple alignment
strategies or assume that alignment is done beforehand. I planed to first
improve face alignment algorithms and then combine face alignment with face
recognition.
This was the work performed when I was a visiting student in Visual Computing
Group of Microsoft Research Asia. Research was focused on iris localization for
iris recognition and face alignment for face recognition under the supervision
of Stan Z.Li.
The task for face alignment is to accurately locate facial features such as the
eyes, nose, mouth and outline. Accurate extraction of facial features offers
advantages for many applications and is crucial for highly accurate face
recognition and synthesis. We used face alignment for "Real-Time
Realistic-Looking 3D Facial Reconstruction and Interaction by Voice-Driven
Expression Animation", supported by National Natural Science Foundation of
China (60203013).
I cooperated with other medical students to develop a system to help medial
imaging diagnosis for the "Science Research Challenge Cup" of
Zhejiang University. This system won the third prize.
The goal is to help people to rapidly get desired videos and efficiently grasp
the idea of their contents. We developed a system of video analysis,
segmentation, abstraction, classification, indexing, retrieval and browsing. As
for home video abstraction, we proposed an audio and video combined algorithm
which is especially suitable for home videos.
The goal is to segment semantic video objects from videos. We developed two
techniques: statistical inference based automatic video object segmentation and
hierarchy optical flow based semi-automatic video object segmentation.
论文