|
Showing 1 - 9 of
9 matches in All Departments
Deep learning has achieved impressive results in image
classification, computer vision and natural language processing. To
achieve better performance, deeper and wider networks have been
designed, which increase the demand for computational resources.
The number of floating-point operations (FLOPs) has increased
dramatically with larger networks, and this has become an obstacle
for convolutional neural networks (CNNs) being developed for mobile
and embedded devices. In this context, our book will focus on CNN
compression and acceleration, which are important for the research
community. We will describe numerous methods, including parameter
quantization, network pruning, low-rank decomposition and knowledge
distillation. More recently, to reduce the burden of handcrafted
architecture design, neural architecture search (NAS) has been used
to automatically build neural networks by searching over a vast
architecture space. Our book will also introduce NAS due to its
superiority and state-of-the-art performance in various
applications, such as image classification and object detection. We
also describe extensive applications of compressed deep models on
image classification, speech recognition, object detection and
tracking. These topics can help researchers better understand the
usefulness and the potential of network compression on practical
applications. Moreover, interested readers should have basic
knowledge about machine learning and deep learning to better
understand the methods described in this book. Key Features: Review
recent advances in CNN compression and acceleration Elaborate
recent advances on binary neural network (BNN) technologies
Introduce applications of Binary Neural Network in image
classification, speech recognition, object detection etc. Baochang
Zhang is a full Professor with Institute of Artificial
Intelligence, Beihang University, Beijing, China. He was selected
by the Program for New Century Excellent Talents in University of
Ministry of Education of China, also selected as Academic Advisor
of Deep Learning Lab of Baidu Inc., and a distinguished researcher
of Beihang Hangzhou Institute in Zhejiang Province. His research
interests include explainable deep learning, computer vision and
patter recognition. His HGPP and LDP methods were state-of-the-art
feature descriptors, with 1234 and 768 Google Scholar citations,
respectively. Both are "Test-of-Time" works. Our 1-bit methods
achieved the best performance on ImageNet. His group also won the
ECCV 2020 tiny object detection, COCO object detection, and ICPR
2020 Pollen recognition challenges. Sheng Xu received the B.E.
degree in Automotive Engineering from Beihang University, Beijing,
China. He is currently a Ph.D. with the school of Automation
Science and Electrical Engineering, Beihang University, Beijing,
China, specializing in computer vision, model quantization, and
compression. He has made significant contributions to the field and
has published about a dozen papers as the first author in top-tier
conferences and journals such as CVPR, ECCV, NeurIPS, AAAI, BMVC,
IJCV, and ACM TOMM. Notably, he has 4 papers selected as oral or
highlighted presentations by these prestigious conferences.
Furthermore, Sheng Xu actively participates in the academic
community as a reviewer for various international journals and
conferences, including CVPR, ICCV, ECCV, NeurIPS, ICML, and IEEE
TCSVT. His expertise has also led to his group's victory in the
ECCV 2020 tiny object detection challenge. Mingbao Lin finished his
M.S.-Ph.D. study and obtained the Ph.D. degree in intelligence
science and technology from Xiamen University, Xiamen, China, in
2022. Earlier, he received the B.S. degree from Fuzhou University,
Fuzhou, China, in 2016. He is currently a senior researcher with
the Tencent Youtu Lab, Shanghai, China. His publications on
top-tier conferences/journals include IEEE TPAMI, IJCV, IEEE TIP,
IEEE TNNLS, CVPR, NeurIPS, AAAI, IJCAI, ACM MM and so on. His
current research interest is to develop efficient vision model, as
well as information retrieval. Tiancheng Wang received the B.E.
degree in Automation from Beihang University, Beijing, China. He is
currently pursuing the Ph.D. degree with the school of Institute of
Artificial Intelligence, Beihang University, Beijing, China. During
undergraduate, he has been awarded the title of Merit Student for
several consecutive years, and has received various scholarships
including academic excellence scholarship and academic competitions
scholarship, etc. He was involved in several AI projects, including
behavior detection and intention understanding research and
unmanned air-based vision platform, etc. Now, his current research
interests include deep learning and network compression, his goal
is to explore the highly energy-saving model and drive the
deployment of neural networks in embedded devices. Dr. David
Doermann is a Professor of Empire Innovation at the University at
Buffalo (UB) and the Director of the University at Buffalo
Artificial Intelligence Institute. Prior to coming to UB, he was a
program manager at the Defense Advanced Research Projects Agency
(DARPA), where he developed, selected and oversaw approximately
$150 million in research and transition funding in the areas of
computer vision, human language technologies and voice analytics.
He coordinated performers on all of the projects, orchestrating
consensus, evaluating cross team management and overseeing fluid
program objectives.
Deep learning has achieved impressive results in image
classification, computer vision and natural language processing. To
achieve better performance, deeper and wider networks have been
designed, which increase the demand for computational resources.
The number of floating-point operations (FLOPs) has increased
dramatically with larger networks, and this has become an obstacle
for convolutional neural networks (CNNs) being developed for mobile
and embedded devices. In this context, our book will focus on CNN
compression and acceleration, which are important for the research
community. We will describe numerous methods, including parameter
quantization, network pruning, low-rank decomposition and knowledge
distillation. More recently, to reduce the burden of handcrafted
architecture design, neural architecture search (NAS) has been used
to automatically build neural networks by searching over a vast
architecture space. Our book will also introduce NAS due to its
superiority and state-of-the-art performance in various
applications, such as image classification and object detection. We
also describe extensive applications of compressed deep models on
image classification, speech recognition, object detection and
tracking. These topics can help researchers better understand the
usefulness and the potential of network compression on practical
applications. Moreover, interested readers should have basic
knowledge about machine learning and deep learning to better
understand the methods described in this book.
In the past five years, the field of electrostatic discharge (ESD)
control has under gone some notable changes. Industry standards
have multiplied, though not all of these, in our view, are
realistic and meaningful. Increasing importance has been ascribed
to the Charged Device Model (CDM) versus the Human Body Model (HBM)
as a cause of device damage and, presumably, premature (latent)
failure. Packaging materials have significantly evolved. Air
ionization techniques have improved, and usage has grown. Finally,
and importantly, the government has ceased imposing MIL-STD-1686 on
all new contracts, leaving companies on their own to formulate an
ESD-control policy and write implementing documents. All these
changes are dealt with in five new chapters and ten new reprinted
papers added to this revised edition of ESD from A to Z. Also, the
original chapters have been augmented with new material such as
more troubleshooting examples in Chapter 8 and a 20-question
multiple-choice test for certifying operators in Chapter 9. More
than ever, the book seeks to provide advice, guidance, and
practical ex amples, not just a jumble of facts and
generalizations. For instance, the added tailored versions of the
model specifications for ESD-safe handling and packaging are
actually in use at medium-sized corporations and could serve as
patterns for many readers.
Traditionally, scientific fields have defined boundaries, and
scientists work on research problems within those boundaries.
However, from time to time those boundaries get shifted or blurred
to evolve new fields. For instance, the original goal of computer
vision was to understand a single image of a scene, by identifying
objects, their structure, and spatial arrangements. This has been
referred to as image understanding. Recently, computer vision has
gradually been making the transition away from understanding single
images to analyzing image sequences, or video Video understanding
deals with understanding of video understanding. sequences, e.g.,
recognition of gestures, activities, facial expressions, etc. The
main shift in the classic paradigm has been from the recognition of
static objects in the scene to motion-based recognition of actions
and events. Video understanding has overlapping research problems
with other fields, therefore blurring the fixed boundaries.
Computer graphics, image processing, and video databases have obvi
ous overlap with computer vision. The main goal of computer
graphics is to generate and animate realistic looking images, and
videos. Re searchers in computer graphics are increasingly
employing techniques from computer vision to generate the synthetic
imagery. A good exam pIe of this is image-based rendering and
modeling techniques, in which geometry, appearance, and lighting is
derived from real images using computer vision techniques. Here the
shift is from synthesis to analy sis followed by synthesis. Image
processing has always overlapped with computer vision because they
both inherently work directly with images."
|
Arabic and Chinese Handwriting Recognition - Summit, SACH 2006, College Park, MD, USA, September 27-28, 2006, Selected Papers (Paperback, 2008 ed.)
David Doermann, Stefan Jaeger
|
R1,557
Discovery Miles 15 570
|
Ships in 10 - 15 working days
|
In the fall of 2006, the University of Maryland, along with various
government and industrial sponsors, invited leading researchers
from all over the world to a two-day Summit on Arabic and Chinese
Handwriting Recognition (SACH 2006). The event acted as a
complement to the biennial Symposium on Document Image
Understanding Technology (SDIUT), providing a focused glimpse into
the state of the art in Arabic and Chinese handwriting recognition.
It offered a forum for interaction with prominent researchers at
the forefront of the scientific community and provided an
opportunity for participants to help explore possible directions of
the field. This book is a result of the expansion, peer review, and
revision of selected papers presented at this meeting. Handwriting
recognition remains the Holy Grail of document analysis, and Arabic
and Chinese scripts embrace many of the most significant
challenges. We are pleased to have 16 scientific papers covering
the original topics of handwritten Arabic and Chinese, as well as 2
papers covering other handwritten scripts. We asked each author to
not only describe the techniques used in addressing the problem,
but to attempt to identify the key research challenges and problems
that the community faces. The result is an impressive collection of
manuscripts that provide various detailed views of the state of
research. In this book, six articles deal directly with Arabic
handwriting. * Cheriet provides an overview of the problems of
Arabic recognition and how systems can use natural language
processing techniques to correct errors in lexicon-based systems.
Traditionally, scientific fields have defined boundaries, and
scientists work on research problems within those boundaries.
However, from time to time those boundaries get shifted or blurred
to evolve new fields. For instance, the original goal of computer
vision was to understand a single image of a scene, by identifying
objects, their structure, and spatial arrangements. This has been
referred to as image understanding. Recently, computer vision has
gradually been making the transition away from understanding single
images to analyzing image sequences, or video Video understanding
deals with understanding of video understanding. sequences, e.g.,
recognition of gestures, activities, facial expressions, etc. The
main shift in the classic paradigm has been from the recognition of
static objects in the scene to motion-based recognition of actions
and events. Video understanding has overlapping research problems
with other fields, therefore blurring the fixed boundaries.
Computer graphics, image processing, and video databases have obvi
ous overlap with computer vision. The main goal of computer
graphics is to generate and animate realistic looking images, and
videos. Re searchers in computer graphics are increasingly
employing techniques from computer vision to generate the synthetic
imagery. A good exam pIe of this is image-based rendering and
modeling techniques, in which geometry, appearance, and lighting is
derived from real images using computer vision techniques. Here the
shift is from synthesis to analy sis followed by synthesis. Image
processing has always overlapped with computer vision because they
both inherently work directly with images."
In the past five years, the field of electrostatic discharge (ESD)
control has under gone some notable changes. Industry standards
have multiplied, though not all of these, in our view, are
realistic and meaningful. Increasing importance has been ascribed
to the Charged Device Model (CDM) versus the Human Body Model (HBM)
as a cause of device damage and, presumably, premature (latent)
failure. Packaging materials have significantly evolved. Air
ionization techniques have improved, and usage has grown. Finally,
and importantly, the government has ceased imposing MIL-STD-1686 on
all new contracts, leaving companies on their own to formulate an
ESD-control policy and write implementing documents. All these
changes are dealt with in five new chapters and ten new reprinted
papers added to this revised edition of ESD from A to Z. Also, the
original chapters have been augmented with new material such as
more troubleshooting examples in Chapter 8 and a 20-question
multiple-choice test for certifying operators in Chapter 9. More
than ever, the book seeks to provide advice, guidance, and
practical ex amples, not just a jumble of facts and
generalizations. For instance, the added tailored versions of the
model specifications for ESD-safe handling and packaging are
actually in use at medium-sized corporations and could serve as
patterns for many readers."
Throughout history, handwriting has been the primary means of
recording information that is persevered across both time and
space. With the coming of the electronic document era, we are
challenged with making an enormous amount of handwritten documents
available for electronic access. Though many handwritten documents
contain only handwriting, now, more are mixed with printed text,
noise, and background patterns. Handwriting in a printed document
often indicates corrections, additions, or other supplemental
information that should be treated differently from the main
content. The mixture of handwriting with other components presents
a great challenge for making an original document electronically
accessible. In this book, we propose a novel approach to separating
a handwritten document into different layers, such as handwriting,
machine printed text, noise, and background patterns. The
identified handwriting may be further analyzed. For example, we
propose a novel point-pattern based handwriting matching technique
and apply it for handwriting synthesis and retrieval.
The "Handbook of Document Image Processing and Recognition" is a
comprehensive resource on the latest methods and techniques in
document image processing and recognition. Each chapter provides a
clear overview of the topic followed by the state of the art of
techniques used including elements of comparison between them along
with supporting references to archival publications, for those
interested in delving deeper into topics addressed. Rather than
favor a particular approach, the text enables the reader to make an
informed decision for their specific problems."
|
You may like...
Catan
(16)
R1,150
R887
Discovery Miles 8 870
|