陳偉銘
Overview
Works: | 0 works in 9 publications in 2 languages |
---|
Titles
單目人臉多視角生成應用在裸視3D立體電視之實現 = = Multi-view generation via monocular face in 3D stereoscopic TV base on PSM-Net /
by:
陳偉銘; Chen, Wei-Ming; 林洛渝
(Language materials, printed)
基於不良天氣下,人工智慧目標檢測增強資料集訓練,準確率之優化探討與比較 = = Toward adverse weather conditions, AI object detection enhanced data training, discussion and comparison of optimization of accuracy rate /
by:
蘇柏綸; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
居家運動輔助系統設計 = = A design of home motion assistance system /
by:
江欣鴻; 趙涵捷; 陳偉銘; Chao, Han-Chieh; Chen, Wei-Ming
(Language materials, printed)
深度學習應用於向量量化影像壓縮之研究 = = Deep learning based vector quantization for image compression /
by:
張泓亮; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
一種基於ST-GCN的序列化骨架姿勢預測方法 = = A sequential skeleton pose prediction method based on ST-GCN /
by:
徐維彬; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
BERT靈性分類 : = BERT對靈性進行分析 = BERT spiritual classification : BERT analyzes spirituality /
by:
王翊萱; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
離散小波卷積進行多層深度圖像隱寫 : = 用於推薦行銷之研究 = Wavelet CNN for multi-level deep steganography : applicate on referral marketing /
by:
白謹朋; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
人工智慧物件偵測 : = 應用於街景定位及方向判斷功能 = Artificial intelligence object detection : applied to street view positioning and direction judgment functions /
by:
潘宜婷; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
基於人工智慧物件辨識之即時定位系統 = = Real-time positioning system based on artificial intelligence object recognition /
by:
莊御翔; 陳偉銘; Chen, Wei-Ming
(Language materials, printed)
Subjects
向量量化
深度學習
Motion capture
Natural Language Processing
2D to 3D
Artificial intelligence
Depth estimation
推薦行銷
object detection
準確率
Graph Neural Network
Spiritual analysis
自然語言處理
2D轉3D
深度圖預處理
deep learning
模擬雨
augmentation dataset
目標檢測
Image Compression
Augmented reality
Face detection
stereo matching
Indoor positioning
影像壓縮
Vector Quantization
圖神經網路
Graph Convolutional Neural Network
擴增實境
動作捕捉
臉部偵測
混合式 P2P
靈性分析
Bidirectional Encoder Representations from Transformers(BERT)
referral marketing
street view dataset
accuracy
編碼簿
人體姿勢預測
姿態辨識
multi-view face image
室內定位
深度估計
image steganography
feature extraction
deep learnning
Human posture prediction
立體匹配
pre-processing of the depth map
人工智慧
Object detection
特徵擷取
增強資料集
圖卷積神經網路
Hybrid P2P
BERT
人臉多角度視圖
物件偵測
圖像隱寫
simulated synthetic rain
Codebook
Deep Learning
Pose estimation
街景資料集