咨询与建议

限定检索结果

文献类型

  • 73 篇 期刊文献
  • 48 篇 会议

馆藏范围

  • 121 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 115 篇 工学
    • 82 篇 计算机科学与技术...
    • 49 篇 电气工程
    • 14 篇 信息与通信工程
    • 13 篇 测绘科学与技术
    • 12 篇 软件工程
    • 11 篇 控制科学与工程
    • 11 篇 生物医学工程(可授...
    • 6 篇 环境科学与工程(可...
    • 5 篇 仪器科学与技术
    • 5 篇 电子科学与技术(可...
    • 3 篇 机械工程
    • 2 篇 交通运输工程
    • 2 篇 生物工程
    • 1 篇 动力工程及工程热...
    • 1 篇 土木工程
    • 1 篇 石油与天然气工程
    • 1 篇 农业工程
    • 1 篇 网络空间安全
  • 38 篇 医学
    • 24 篇 临床医学
    • 10 篇 特种医学
    • 7 篇 基础医学(可授医学...
  • 32 篇 理学
    • 11 篇 地球物理学
    • 10 篇 物理学
    • 6 篇 生物学
    • 5 篇 地理学
    • 2 篇 数学
    • 2 篇 化学
  • 7 篇 管理学
    • 6 篇 管理科学与工程(可...
  • 3 篇 农学
    • 2 篇 作物学
  • 1 篇 教育学
    • 1 篇 体育学

主题

  • 121 篇 masked autoencod...
  • 34 篇 self-supervised ...
  • 12 篇 transformer
  • 10 篇 deep learning
  • 10 篇 feature extracti...
  • 9 篇 vision transform...
  • 9 篇 task analysis
  • 9 篇 training
  • 7 篇 transformers
  • 6 篇 contrastive lear...
  • 6 篇 image reconstruc...
  • 5 篇 anomaly detectio...
  • 5 篇 decoding
  • 5 篇 data models
  • 4 篇 graph neural net...
  • 4 篇 computational mo...
  • 4 篇 multimodal
  • 4 篇 point cloud comp...
  • 4 篇 unsupervised lea...
  • 3 篇 three-dimensiona...

机构

  • 2 篇 univ sci & techn...
  • 2 篇 chinese acad sci...
  • 2 篇 univ sci & techn...
  • 2 篇 xidian univ sch ...
  • 2 篇 microsoft res as...
  • 2 篇 south china univ...
  • 2 篇 univ hong kong p...
  • 2 篇 singapore inst t...
  • 2 篇 xidian univ sch ...
  • 2 篇 univ chinese aca...
  • 2 篇 univ massachuset...
  • 1 篇 southeast univ l...
  • 1 篇 xiamen univ sch ...
  • 1 篇 univ sci & techn...
  • 1 篇 henan polytech u...
  • 1 篇 university of sc...
  • 1 篇 north china univ...
  • 1 篇 bournemouth univ...
  • 1 篇 univ hong kong d...
  • 1 篇 univ chinese aca...

作者

  • 3 篇 liu wei
  • 2 篇 chen dongdong
  • 2 篇 song yan
  • 2 篇 zhang xixi
  • 2 篇 huang chao
  • 2 篇 chen dong
  • 2 篇 sadok samir
  • 2 篇 wang min
  • 2 篇 fang wei
  • 2 篇 ye yaowen
  • 2 篇 tao jianhua
  • 2 篇 xu yongshun
  • 2 篇 xia lianghao
  • 2 篇 mcloughlin ian
  • 2 篇 han shuo
  • 2 篇 xu ke
  • 2 篇 sun licai
  • 2 篇 li houqiang
  • 2 篇 rudolph yannick
  • 2 篇 leglaive simon

语言

  • 119 篇 英文
  • 1 篇 德文
  • 1 篇 法文
  • 1 篇 中文
检索条件"主题词=Masked autoencoder"
121 条 记 录,以下是31-40 订阅
DB-PMAE: Dual-Branch Prototypical masked autoencoder with locality for domain robust speaker verification  25
DB-PMAE: Dual-Branch Prototypical Masked AutoEncoder with lo...
收藏 引用
25th Interspeech Conference
作者: Xie, Wei-lin Xi, Yu-Xuan Song, Yan Zhang, Jian-tao Song, Hao-yu McLoughlin, Ian Univ Sci & Technol China Natl Engn Res Ctr Speech & Language Informat Proc Hefei Peoples R China Australian Natl Univ Canberra ACT Australia Singapore Inst Technol ICT Cluster Singapore Singapore
Existing speaker verification (SV) systems mainly consist of a frontend deep embedding network pretrained for speaker identification (SID) followed by a backend network finetuned to provide a similarity measure. Despi... 详细信息
来源: 评论
A VECTOR QUANTIZED masked autoencoder FOR SPEECH EMOTION RECOGNITION
A VECTOR QUANTIZED MASKED AUTOENCODER FOR SPEECH EMOTION REC...
收藏 引用
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Sadok, Samir Leglaive, Simon Seguier, Renaud CentraleSupelec IETR UMR CNRS 6164 Gif Sur Yvette France
Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the ... 详细信息
来源: 评论
Graph masked autoencoder for Sequential Recommendation  23
Graph Masked Autoencoder for Sequential Recommendation
收藏 引用
46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
作者: Ye, Yaowen Xia, Lianghao Huang, Chao Univ Hong Kong Hong Kong Peoples R China
While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer fro... 详细信息
来源: 评论
DHMAE: A Disentangled Hypergraph masked autoencoder for Group Recommendation  47
DHMAE: A Disentangled Hypergraph Masked Autoencoder for Grou...
收藏 引用
47th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
作者: Zhao, Yingqi Zhang, Haiwei Bai, Qijie Nie, Changli Yuan, Xiaojie Nankai Univ TJ Key Lab NDST Coll CS Tianjin Peoples R China
Group recommendation aims to suggest items to a group of users that are suitable for the group. Although some existing powerful deep learning models have achieved improved performance, various aspects remain unexplore... 详细信息
来源: 评论
Flow-MAE: Leveraging masked autoencoder for Accurate, Efficient and Robust Malicious Traffic Classification  23
Flow-MAE: Leveraging Masked AutoEncoder for Accurate, Effici...
收藏 引用
26th International Symposium on Research in Attacks, Intrusions and Defenses (RAID)
作者: Hang, Zijun Lu, Yuliang Wang, Yongjie Xie, Yi Natl Univ Def Technol Hefei Peoples R China
Malicious traffic classification is crucial for Intrusion Detection Systems (IDS). However, traditional Machine Learning approaches necessitate expert knowledge and a significant amount of well-labeled data. Although ... 详细信息
来源: 评论
AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual masked autoencoder  35
AV-MaskEnhancer: Enhancing Video Representations through Aud...
收藏 引用
35th IEEE International Conference on Tools with Artificial Intelligence (ICTAI)
作者: Diao, Xingjian Cheng, Ming Cheng, Shitong Dartmouth Coll Dept Comp Sci Hanover NH 03755 USA
Learning high-quality video representation has shown significant applications in computer vision and remains challenging. Previous work based on mask autoencoders such as ImageMAE [10] and VideoMAE [23] has proven the... 详细信息
来源: 评论
DP-MAE: A DUAL-PATH masked autoencoder BASED SELF-SUPERVISED LEARNING METHOD FOR ANOMALOUS SOUND DETECTION  49
DP-MAE: A DUAL-PATH MASKED AUTOENCODER BASED SELF-SUPERVISED...
收藏 引用
49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Liu, Zhuo-Li Song, Yan Zeng, Xiao-Min Dai, Li-Rong McLoughlin, Ian Univ Sci & Technol China Natl Engn Res Ctr Speech & Language Informat Proc Hefei Peoples R China Singapore Inst Technol ICT Cluster Singapore Singapore
In this paper, we present a novel general-purpose audio representation learning method named Dual-Path masked autoencoder (DP-MAE) for anomalous sound detection (ASD) task. Existing methods mainly focus on frame-level... 详细信息
来源: 评论
Image Anomaly Detection and Localization Using masked autoencoder  29th
Image Anomaly Detection and Localization Using Masked Autoen...
收藏 引用
29th International Conference on Neural Information Processing
作者: Yu, Xiaohuo Guo, Jiahao Wang, Lu Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China
Generally speaking, abnormal images are distinguished from normal images in terms of content or semantics. Image anomaly detection is the task of identifying anomalous images that deviate from normal images. Reconstru... 详细信息
来源: 评论
NeuralMAE: Data-Efficient Neural Architecture Predictor with masked autoencoder  6th
NeuralMAE: Data-Efficient Neural Architecture Predictor with...
收藏 引用
6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)
作者: Liang, Qiaochu Gong, Lei Wang, Chao Zhou, Xuehai Li, Xi Univ Sci & Technol China Sch Comp Sci & Technol Hefei Peoples R China
Predictor-based Neural Architecture Search (NAS) offers a promising solution for enhancing the efficiency of traditional NAS methods. However, it is non-trivial to train the predictor with limited architecture evaluat... 详细信息
来源: 评论
ROBUST FACE RECOGNITION BASED ON AN ANGLE-AWARE LOSS AND masked autoencoder PRE-TRAINING  49
ROBUST FACE RECOGNITION BASED ON AN ANGLE-AWARE LOSS AND MAS...
收藏 引用
49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Choi, Jaehyeop Kim, Youngbaek Lee, Younghyun NCSOFT Corp Vision AI Lab NC Res Seongnam South Korea
Despite the advances in deep learning techniques, accurate identification using face recognition (FR) systems remains challenging owing to changes in face angles, bad lighting, and occlusions. To address these problem... 详细信息
来源: 评论