Gyuyeong KIM
Hyun KWON Jun LEE
Fan LI Enze YANG Chao LI Shuoyan LIU Haodong WANG
Guangjin Ouyang Yong Guo Yu Lu Fang He
Yuyao LIU Qingyong LI Shi BAO Wen WANG
Cong PANG Ye NI Jia Ming CHENG Lin ZHOU Li ZHAO
Nikolay FEDOROV Yuta YAMASAKI Masateru TSUNODA Akito MONDEN Amjed TAHIR Kwabena Ebo BENNIN Koji TODA Keitaro NAKASAI
Yukasa MURAKAMI Yuta YAMASAKI Masateru TSUNODA Akito MONDEN Amjed TAHIR Kwabena Ebo BENNIN Koji TODA Keitaro NAKASAI
Kazuya KAKIZAKI Kazuto FUKUCHI Jun SAKUMA
Yitong WANG Htoo Htoo Sandi KYAW Kunihiro FUJIYOSHI Keiichi KANEKO
Waqas NAWAZ Muhammad UZAIR Kifayat ULLAH KHAN Iram FATIMA
Haeyoung Lee
Ji XI Pengxu JIANG Yue XIE Wei JIANG Hao DING
Weiwei JING Zhonghua LI
Sena LEE Chaeyoung KIM Hoorin PARK
Akira ITO Yoshiaki TAKAHASHI
Rindo NAKANISHI Yoshiaki TAKATA Hiroyuki SEKI
Chuzo IWAMOTO Ryo TAKAISHI
Chih-Ping Wang Duen-Ren Liu
Yuya TAKADA Rikuto MOCHIDA Miya NAKAJIMA Syun-suke KADOYA Daisuke SANO Tsuyoshi KATO
Yi Huo Yun Ge
Rikuto MOCHIDA Miya NAKAJIMA Haruki ONO Takahiro ANDO Tsuyoshi KATO
Koichi FUJII Tomomi MATSUI
Yaotong SONG Zhipeng LIU Zhiming ZHANG Jun TANG Zhenyu LEI Shangce GAO
Souhei TAKAGI Takuya KOJIMA Hideharu AMANO Morihiro KUGA Masahiro IIDA
Jun ZHOU Masaaki KONDO
Tetsuya MANABE Wataru UNUMA
Kazuyuki AMANO
Takumi SHIOTA Tonan KAMATA Ryuhei UEHARA
Hitoshi MURAKAMI Yutaro YAMAGUCHI
Jingjing Liu Chuanyang Liu Yiquan Wu Zuo Sun
Zhenglong YANG Weihao DENG Guozhong WANG Tao FAN Yixi LUO
Yoshiaki TAKATA Akira ONISHI Ryoma SENDA Hiroyuki SEKI
Dinesh DAULTANI Masayuki TANAKA Masatoshi OKUTOMI Kazuki ENDO
Yuan LI Tingting HU Ryuji FUCHIKAMI Takeshi IKENAGA
Takahito YOSHIDA Takaharu YAGUCHI Takashi MATSUBARA
Congcong FANG Yun JIN Guanlin CHEN Yunfan ZHANG Shidang LI Yong MA Yue XIE
Zhigang WU Yaohui ZHU
Nat PAVASANT Takashi MORITA Masayuki NUMAO Ken-ichi FUKUI
Keitaro NAKASAI Shin KOMEDA Masateru TSUNODA Masayuki KASHIMA
Naoya NEZU Hiroshi YAMADA
Nan Wu Xiaocong Lai Mei Chen Ying Pan
Qinghua WU Weitong LI
Kento KIMURA Tomohiro HARAMIISHI Kazuyuki AMANO Shin-ichi NAKANO
Ryotaro MITSUBOSHI Kohei HATANO Eiji TAKIMOTO
Genta INOUE Daiki OKONOGI Satoru JIMBO Thiem Van CHU Masato MOTOMURA Kazushi KAWAMURA
Hikaru USAMI Yusuke KAMEDA
Lihan TONG Weijia LI Qingxia YANG Liyuan CHEN Peng CHEN
Yinan YANG
Myung-Hyun KIM Seungkwang LEE
Shuoyan LIU Chao LI Yuxin LIU Yanqiu WANG
Takumi INABA Takatsugu ONO Koji INOUE Satoshi KAWAKAMI
Zheqing ZHANG Hao ZHOU Chuan LI Weiwei JIANG
Liu ZHANG Zilong WANG Yindong CHEN
Wenxia Bao An Lin Hua Huang Xianjun Yang Hemu Chen
Fengshan ZHAO Qin LIU Takeshi IKENAGA
Haruhiko KAIYA Shinpei OGATA Shinpei HAYASHI
Jiakai LI Jianyong DUAN Hao WANG Li HE Qing ZHANG
Yuxin HUANG Yuanlin YANG Enchang ZHU Yin LIANG Yantuan XIAN
Naohito MATSUMOTO Kazuhiro KURITA Masashi KIYOMI
Na XING Lu LI Ye ZHANG Shiyi YANG
Zhe Wang Zhe-Ming Lu Hao Luo Yang-Ming Zheng
Rina TAGAMI Hiroki KOBAYASHI Shuichi AKIZUKI Manabu HASHIMOTO
Tomohiro KOBAYASHI Tomomi MATSUI
Shin-ichi NAKANO
Hongzhi XU Binlian ZHANG
Weizhi WANG Lei XIA Zhuo ZHANG Xiankai MENG
Yuka KO Katsuhito SUDOH Sakriani SAKTI Satoshi NAKAMURA
Ming PAN
The direct implementation of the conventional vector quantization codec requires unfeasibly large-sized codebooks as the block length increases. This paper discusses a systematic approach for constructing vector quantization codec with large block length which can be compared with that of the transform coding techniques. Here we propose a class of Recursive Vector Quantizer (RVQ) which recursively encodes a given large-dimensional input vector into a series of indices of reproduction vectors derived from a small-sized and small-dimensional codebook. This codebook is referred to as a wavelet codebook. Note that a single codebook will be used repeatedly in every stage of the hierarchical quadtree decomposition of input vectors. For this construction of the RVQ system, the mean value of each input vector is extracted and then encoded separately. The side information, which represents how the wavelet vectors are combined for reproducing the replica of the input vector, can be efficiently encoded by using the binary tree code. We also give a design example of a 64-dimensional RVQ using a four-dimensional tree search vector quantizer as a wavelet quantizer. The results of computer simulation show effectiveness of the RVQ for video signals. For example, the signal-to-noise ratio of 37.6 dB is obtained at the rate of 1.27 bits per pixel for the image data
This paper newly proposes HOMomorphic Transformer (HOMT) in order to formalize relations among strictness-related analyses (SRAs) on first-order functional programs. A HOMT is defined to be a composition of special instances of abstract interpretation, and has enough ability to treat known SRAs including head/tail/total strictness detection on nonflat domains. A set of HOMTs, furthermore, is an algebraic space such that some composition of HOMTs can be reduced to a simpler HOMT. This structure gives a transformational mechanism between various SRAs, and further clarifies the equivalence and the hierarchy among them. First, we show a construction of a HOMT as a composition of Unit-HOMTs (U-HOMTs) which are specified by quadruplet representations. Second, algebraic relations among HOMTs are shown as reduction rules among specific pairs of quadruplet representations. Thus, hierarchy among HOMTs can be clarified by finding some adequate quadruplet representation which bridges a HOMT to the other. Third, various SRAs are formalized as HOMTs in either forward or back-ward manners. They are also shown to be safe under unified discussions. Finally, their equivalence and hierarchy are examined in terms of an algebraic structure of HOMTs.
Yuichi OHTA Masaki WATANABE Yasushi SUMI
In order to realize a robust computer vision system which can cope with a variety of scenes, we propose a new scheme to integrate multiple vision algorithms in a cooperative framework. The key concepts of the scheme can be summarized as follows: (1) A vision algorithm is implemented as an independent specialist. (2) There are multiple specialists in the system. (3) All specialists work in parallel. (4) Each specialist tries to solve the vision problem in its own way. (5) A specialist may communicate with another specialist when it needs a help. The scheme clearly has a nature of task parallelism and is suitable to be built on a parallel computer. In order to demonstrate the feasibility of the proposed scheme, we are developing two computer vision systems in two different approaches which are both based on the same concept. They are called a cooperative approach and a concurrent top-down approach. Roughly speaking, the former is an integration of multiple algorithms in a bottom-up framework while the latter is in a top-down framework. Preliminary results obtained by the systems are also presented.
Distributed match-making is a paradigm that deals with the match-making property of distributed issues such as name service, mutual exclusion, and replicated data management. In order to realize distributed match-making, two kinds of subsets with certain properties must be constructed for each process. We call a set of the subsets defined for all processes an
Dusan JOKANOVIC Norio SHIRATORI Shoichi NOGUCHI
This paper considers processor utilization in faulty hypercube multiprocessor. The utilization is proportional to the continuity of processor allocation model based on Gray code. Busy and faulty processors make this model fragmented. That prevents assigning of larger tasks onto hypercube and decreases processor utilization. A set of procedures is derived which reassigns active tasks so that a new task configuration along with faulty processors makes as little damage as possible to the continuity of allocation model. First, a hypercube fragmentation measure is defined and a task reassigning technique presented. Then, procedures are given which determine: (1) active tasks to be reassigned, (2) their new optimal locations and (3) the shortest reassigning paths. At last, it is proved that while increasing processor utilization, presented scheme minimizes task reconfiguration overhead.
Tomio KUROKAWA Takanari MIZUKOSHI
Logarithmic arithmetic (LA) is a very fast computational method for real numbers. And its precision is better than a floating point arithmetic of equivalent word length and range. This paper shows a method to use LA in computer graphics--picture generation of almost any kind. Various experiments are done--from curve drawing to 3D image generation. The results are all excellent for quality and speed.