检索结果-内蒙古大学图书馆

Dense Regression Network for Video Grounding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zeng, Runhao Xu, Haoming Huang, Wenbing Chen, Peihao Tan, Mingkui Gan, Chuang School of Software Engineering South China University of Technology China MIT-IBM Watson AI Lab Peng Cheng Laboratory Shenzhen China Department of Computer Science and Technology Tsinghua University

We address the problem of video grounding from natural language queries. The key challenge in this task is that one training video might only contain a few annotated starting/ending frames that can be used as positive examples for model training. Most conventional approaches directly train a binary classifier using such imbalance data, thus achieving inferior results. The key idea of this paper is to use the distances between the frame within the ground truth and the starting (ending) frame as dense supervisions to improve the video grounding accuracy. Specifically, we design a novel dense regression network (DRN) to regress the distances from each frame to the starting (ending) frame of the video segment described by the query. We also propose a simple but effective IoU regression head module to explicitly consider the localization quality of the grounding results (i.e., the IoU between the predicted location and the ground truth). Experimental results show that our approach significantly outperforms state-of-the-arts on three datasets (i.e., Charades-STA, ActivityNet-Captions, and TACoS). Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

Final Report of the NTCIR-14 FinNum Task: Challenges and Current Status of Fine-Grained Numeral Understanding in Financial Social Media Data 14th

学校读者我要写书评

暂无评论

Final Report of the NTCIR-14 FinNum Task: Challenges and Cur...

14th International Conference on NII Testbeds and Community for Information Access Research, NTCIR 2019

作者： Chen, Chung-Chi Huang, Hen-Hsen Takamura, Hiroya Chen, Hsin-Hsi Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Computer Science National Chengchi University Taipei Taiwan Artificial Intelligence Research Center National Institute of Advanced Industrial Science and Technology Tokyo Japan MOST Joint Research Center for AI Technology and All Vista Healthcare Taipei Taiwan

ISBN: (纸本)9783030368043

NTCIR-14 FinNum task aims to disambiguate the meanings of the numerals in financial social media data from both coarse-grained taxonomy and fine-grained taxonomy. This task attracted 13 teams from 15 institutions in 6 different countries to register, received 16 submissions from 9 participants, and finally accepted 6 papers from participants. In this paper, we provide the analysis of the proposed dataset in depth, and discuss the challenges of fine-grained numeral understanding in financial social media data. © 2019, Springer Nature Switzerland AG.

关键词： Taxonomies

Zero-shot text-to-SQL learning with auxiliary task

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chang, Shuaichen Liu, Pengfei Tang, Yun Huang, Jing He, Xiaodong Zhou, Bowen Department of Computer Science and Engineering Ohio State University School of Computer Science Fudan University *** AI Research

Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realistic unseen data, which naturally raises a question: does this impressive performance signify a perfect generalization model, or are there still some limitations? In this paper, we first diagnose the bottleneck of text-to-SQL task by providing a new testbed, in which we observe that existing models present poor generalization ability on rarely-seen data. The above analysis encourages us to design a simple but effective auxiliary task, which serves as a supportive model as well as a regularization term to the generation task to increase the models generalization. Experimentally, We evaluate our models on a large text-to-SQL dataset WikiSQL. Compared to a strong baseline coarse-to-fine model, our models improve over the baseline by more than 3% absolute in accuracy on the whole dataset. More interestingly, on a zero-shot subset test of WikiSQL, our models achieve 5% absolute accuracy gain over the baseline, clearly demonstrating its superior generalizability. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Yawei Zhang, Kai Timofte, Radu Van Gool, Luc Kong, Fangyuan Li, Mingxi Liu, Songwei Du, Zongcai Liu, Ding Zhou, Chenhui Chen, Jingyi Han, Qingrui Li, Zheyuan Liu, Yingqi Chen, Xiangyu Cai, Haoming Qiao, Yu Dong, Chao Sun, Long Pan, Jinshan Zhu, Yi Zong, Zhikai Liu, Xiaoxiao Hui, Zheng Yang, Tao Ren, Peiran Xie, Xuansong Hua, Xian-Sheng Wang, Yanbo Ji, Xiaozhong Lin, Chuming Luo, Donghao Tai, Ying Wang, Chengjie Zhang, Zhizhong Xie, Yuan Cheng, Shen Luo, Ziwei Yu, Lei Wen, Zhihong Wu, Qi Li, Youwei Fan, Haoqiang Sun, Jian Liu, Shuaicheng Huang, Yuanfei Jin, Meiguang Huang, Hua Liu, Jing Zhang, Xinjian Wang, Yan Long, Lingshun Li, Gen Zhang, Yuanfan Cao, Zuowei Sun, Lei Alexander, Panaetov Wang, Yucong Cai, Minjie Wang, Li Tian, Lu Wang, Zheyuan Ma, Hongbing Liu, Jie Chen, Chao Cai, Yidong Tang, Jie Wu, Gangshan Wang, Weiran Huang, Shirui Lu, Honglei Liu, Huan Wang, Keyan Chen, Jun Chen, Shi Miao, Yuchun Huang, Zimo Zhang, Lefei Ayazoglu, Mustafa Xiong, Wei Xiong, Chengyi Wang, Fei Li, Hao Wen, Ruimian Yang, Zhijing Zou, Wenbin Zheng, Weixin Ye, Tian Zhang, Yuncheng Kong, Xiangzhen Arora, Aditya Zamir, Syed Waqas Khan, Salman Hayat, Munawar Khan, Fahad Shahbaz Gao, Dandan Zhou, Dengwen Ning, Qian Tang, Jingzhu Huang, Han Wang, Yufei Peng, Zhangheng Li, Haobo Guan, Wenxue Gong, Shenghua Li, Xin Liu, Jun Wang, Wanjun Zeng, Kun Lin, Hanjiang Chen, Xinyu Fang, Jinsheng Zhang, Shuhao Zhang, Yuhao Sinha, Abhishek Kumar Moorthi, S. Manthira Dhar, Debajyoti Yang, Hao-Hsiang Huang, Zhi-Kai Chen, Wei-Ting Chang, Hua-En Kuo, Sy-Yen Tan, Wei Chen, Hao Xu, Qian Narang, Pratik Singh, Usneek Sameen, Syed Khaitan, Harsh Yinghua, Liu Tianlin, Zhang Xiaoming, Zhang Meng, Dingxuan Tian, Chunwei Morshed, Mashrur M. Ahsan, Ahmad Omar Computer Vision Lab ETH Zurich Switzerland University of Würzburg Germany ByteDance Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University China ByteDance Inc China NetEase Inc. China Shenzhen Institutes of Advanced Technology CAS China University of Macau China Shanghai AI Lab Shanghai China Nanjing University of Science and Technology China Amazon Web Services United States China Alibaba DAMO Academy EFC Yuhang District Zhejiang Hangzhou China East China Normal University China Youtu Lab Tencent China Megvii Technology China University of Electronic Science and Technology of China China School of Artificial Intelligence Beijing Normal University China Alibaba Group China Bilibili AI China Nankai-Baidu Joint Lab Nankai University Tianjin China Platform Technologies Tencent Online Video China Higher School of Economics Russia Huawei Moscow Research Center Russia Hunan University China Xidian University China Xilinx Technology Beijing Limited China College of Information Science and Engineering Xinjiang University Urumqi China Department of Electronic Engineering Tsinghua University Beijing China Nanjing University China McMaster University Canada School of Telecommunication Engineering Xidian University Xi’an China School of Computer Science Wuhan University Wuhan China School of Mathematical Science University of Electronic Science and Technology of China Chengdu China School of Computer Science The University of Sydney Sydney Australia Aselsan Research Ankara Turkey School of Electronic and Information Engineering South-Central University for Nationalities Wuhan China Guangdong University of Technology China Fujian Normal University Fuzhou University Jimei University China Design Group China Abu Dhabi United Arab Emirates Monash University Melbourne Australia Mohamed bin Zayed University of AI United Arab Emirates North China Electric Power University Changping District Beijing China The School of Art

This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images. The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29.00dB on DIV2K validation set. IMDN is set as the baseline for efficiency measurement. The challenge had 3 tracks including the main track (runtime), sub-track one (model complexity), and sub-track two (overall performance). In the main track, the practical runtime performance of the submissions was evaluated. The rank of the teams were determined directly by the absolute value of the average runtime on the validation set and test set. In sub-track one, the number of parameters and FLOPs were considered. And the individual rankings of the two metrics were summed up to determine a final ranking in this track. In sub-track two, all of the five metrics mentioned in the description of the challenge including runtime, parameter count, FLOPs, activations, and memory consumption were considered. Similar to sub-track one, the rankings of five metrics were summed up to determine a final ranking. The challenge had 303 registered participants, and 43 teams made valid submissions. They gauge the state-of-the-art in efficient single image super-resolution. © 2022, CC BY.

关键词： Chemical activation

Supervised Representation Hash Codes Learning 23rd

学校读者我要写书评

暂无评论

Supervised Representation Hash Codes Learning

23rd International computer Symposium, ICS 2018

作者： Yang, Huei-Fang Tu, Cheng-Hao Chen, Chu-Song Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Institute of Information Science Academia Sinica Taipei Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare Taipei Taiwan

ISBN: (纸本)9789811391897

Learning-based hashing has been widely employed for large-scale similarity retrieval due to its efficient computation and compressed storage. In this paper, we propose ResHash, a deep representation hash code learning approach to learning compact and discriminative binary codes. In ResHash, we assume that each semantic label has its own representation codeword and these codewords guide hash coding. The codewords are attractors that attract semantically similar images and are also repulsors that repel semantically dissimilar ones. Furthermore, ResHash jointly learns compact binary codes and discover representation codewords from data by a simple margin ranking loss, making it easily realizable and avoiding the need to hand-craft the codewords beforehand. Experimental results on standard benchmark datasets show the effectiveness of ResHash. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Binary codes

Disentanglement of intrinsic and extrinsic side-jump scattering induced spin Hall effect in N-implanted Pt

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shashank, Utkarsh Nakamura, Yoji Kusaba, Yu Tomoda, Takafumi Nongjai, Razia Kandasami, Asokan Medwal, Rohit Rawat, Rajdeep Singh Asada, Hironori Gupta, Surbhi Fukuma, Yasuhiro Department of Physics and Information Technology Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka820-8502 Japan Materials Science Division Inter University Accelerator Centre Aruna Asaf Ali Marg New Delhi110067 India Uttarakhand Dehradun248007 India Department of Physics Indian Institute of Technology Kanpur Kanpur208016 India Natural Sciences and Science Education National Institute of Education Nanyang Technological University 637616 Singapore Graduate School of Sciences and Technology for Innovation Yamaguchi University 2-16-1 Tokiwadai Ube755-8611 Japan Research Center for Neuromorphic AI hardware Kyushu Institute of Technology Kitakyushu808-0196 Japan

The rapidly evolving utilization of spin Hall effect (SHE) arising from spin-orbit coupling in 5d transition metals and alloys have made giant strides in the development of designing low-power, robust and non-volatile magnetic memory. Recent studies, on incorporating non-metallic lighter elements such as oxygen, nitrogen and sulfur into 5d transition metals, have shown an enhancement in damping-like torque efficiency θDL due to the modified SHE, but the mechanism behind this enhancement is not clear. In this paper, we study θDL at different temperatures (100-293 K) to disentangle the intrinsic and extrinsic side-jump scattering induced spin Hall effect in N-implanted Pt. We observe a crossover of intrinsic to extrinsic side-jump mechanism as the implantation dose increases from 2×1016 ions/cm2 to 1×1017 ions/cm2. A sudden decrease in the intrinsic spin Hall conductivity is counterbalanced by the increase in the side-jump induced SHE efficiency. These results conclude that studying θDL as a function of implantation dose, and also as a function of temperature, is important to understand the physical mechanism contributing to SHE, which has so far been unexplored in incorporating non-metallic element in 5d transition metals. Copyright © 2022, The Authors. All rights reserved.

关键词： Spin Hall effect

FlowDesign: Improved design of antibody CDRs through flow matching and better prior distributions

学校读者我要写书评

暂无评论

Cell systems 2025年第6期16卷 101270页

作者： Jun Wu Xiangzhe Kong Ningguan Sun Jing Wei Sisi Shan Fuli Feng Feng Wu Jian Peng Linqi Zhang Yang Liu Jianzhu Ma University of Science and Technology of China Hefei China. Department of Computer Science and Technology Tsinghua University Beijing China Institute for AI Industry Research Tsinghua University Beijing China. Helixon US Inc. Champaign Illinois USA. Comprehensive AIDS Research Center Center for Infection Biology Pandemic Research Alliance School of Basic Medical Sciences Tsinghua Medicine Tsinghua University Beijing China. Institute for AI Industry Research Tsinghua University Beijing China. Electronic address: liuyang2011@***. Institute for AI Industry Research Tsinghua University Beijing China Department of Electronic Engineering Tsinghua University Beijing China. Electronic address: majianzhu@***.

Designing antibodies with desired binding specificity and affinity is essential for pharmaceutical research. While diffusion-based models have advanced the co-design of the complementarity-determining region (CDR) sequences and structures, challenges remain, including non-informative priors, incompatibility with discrete amino acid types, and impractical computational costs in large-scale sampling. To address these, we propose FlowDesign, a sequence-structure co-design approach via flow matching, offering (1) flexible prior selection, (2) direct matching of discrete distributions, and (3) enhanced efficiency for large-scale sampling. By leveraging various priors, data-driven structural models proved the most informative. FlowDesign outperformed baselines in amino acid recovery (AAR), root-mean-square deviation (RMSD), and Rosetta energy. We also applied FlowDesign to design antibodies targeting the HIV-1 receptor CD4. FlowDesign yielded antibodies with improved binding affinity and neutralizing potency compared with the antibody ibalizumab across multiple HIV mutants, validated by biolayer interferometry (BLI) and pseudovirus neutralization. This highlights FlowDesign's potential in antibody and protein design. A record of this paper's transparent peer review process is included in the supplemental information.

关键词： HIV antibody antibody design flow matching structure-based drug design

BitterEN: A novel ensemble model for the identification of bitter peptide

学校读者我要写书评

暂无评论

computers in biology and medicine 2025年 195卷

作者： Md Fahim Sultan Tasmin Karim Md Shazzad Hossain Shaon Md Mamun Ali Sobhy M Ibrahim Mst Shapna Akter Kawsar Ahmed Francis M Bui Mohammad Ali Moni Department of Computer Science and Engineering Oakland University Rochester MI 48309 USA. Electronic address: fahim15-3416@diu.edu.bd. Department of Computer Science and Engineering Oakland University Rochester MI 48309 USA. Electronic address: tasmin15-2920@diu.edu.bd. Department of Computer Science and Engineering Oakland University Rochester MI 48309 USA. Electronic address: shazzad15-3404@diu.edu.bd. Division of Biomedical Engineering University of Saskatchewan 57 Campus Drive Saskatoon SK S7N 5A9 Canada Department of Software Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh. Electronic address: m.ali@usask.ca. Department of Biochemistry College of Science King Saud University P.O. Box: 2455 Riyadh 11451 Saudi Arabia. Electronic address: syakout@ksu.edu.sa. Department of Computer Science and Engineering Oakland University Rochester MI 48309 USA. Electronic address: akter@oakland.edu. Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon SK S7N 5A9 Canada Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh. Electronic address: k.ahmed.bd@***. Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon SK S7N 5A9 Canada. Electronic address: francis.bui@usask.ca. AI & Digital Health Technology Artificial Intelligence & Cyber Future Institute Charles Sturt University Bathurst NSW 2795 Australia AI & Digital Health Technology Rural Health Research Institute Charles Sturt University Orange NSW 2800 Australia. Electronic address: mmoni@csu.edu.au.

Bitter peptides are short amino acid chains that produce a bitter taste. These peptides are made primarily in food processing through the chemical reduction of peptides. The bitterness arises from the specific sequence of amino acids in peptides, which interact with the bitter taste receptors on the human tongue. These peptides influence nutrition and health, offering insights into protein digestion and bioactive advantages. Hence, correctly identifying bitter peptides is pivotal for revealing the biochemical properties of efficient medication. The computational approach is most suitable for identifying bitterness, where most studies obtained insufficient outcomes. Therefore, the current study developed an ensemble-based framework called "BitterEN", where we integrate the Gradient Boosting (GB) and Multi-layer Perception (mlP) methods. Our proposed method improved more than 3 % of accuracy compare to all of the state-of-the-arts methods, where the proposed approach achieved 0.995 accuracy in merged feature extractions with the Random Forest (RF) feature selection method. We used 50 iterations over the performance evaluation phases to enable a more exact generalization of model performance. In addition, we provided a convenient GitHub-based version of our bitter peptide identification. It highlights the practical applicability of these findings. We are optimistic that the proposed approach might benefit many fields, including healthcare development and nutritional science.

关键词： Bitter peptides Ensemble learning Feature extractions Healthcare Nutritional science

Flow++: Improving flow-based generative models with variational dequantization and architecture design

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ho, Jonathan Chen, Xi Srinivas, Aravind Duan, Yan Abbeel, Pieter UC Berkeley Department of Electrical Engineering and Computer Science Covariant.ai

Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to stateof- the-art autoregressive models. In this paper, we investigate and improve upon three limiting design choices employed by flow-based models in prior work: the use of uniform noise for dequantization, the use of inexpressive affine flows, and the use of purely convolutional conditioning networks in coupling layers. Based on our findings, we propose Flow++, a new flow-based model that is now the state-of-the-art non-autoregressive model for unconditional density estimation on standard image benchmarks. Our work has begun to close the significant performance gap that has so far existed between autoregressive models and flow-based models. Our implementation is available at: https://***/ aravindsrinivas/flowpp. Copyright © 2019, The Authors. All rights reserved.

关键词： Computational efficiency