Deep Learning in Object Recognition, Detection, and Segmentation

As a major breakthrough in artificial intelligence, deep learning has achieved impressive success on solving grand challenges in many fields including speech recognition, natural language processing, computer vision, image and video processing, and multimedia. This monograph provides a historical overview of deep learning and focuses on its applications in object recognition, detection, and segmentation, which are key challenges of computer vision and have numerous applications to images and videos. Specifically the topics covered under object recognition include image classification on ImageNet, face recognition, and video classification. In detection, the monograph covers general object detection on ImageNet, pedestrian detection, face landmark detection (face alignment), and human landmark detection (pose estimation). Finally within segmentation, it covers the most recent progress on scene labeling, semantic segmentation, face parsing, human parsing, and saliency detection. Concrete examples of these applications explain the key points that make deep learning outperform conventional computer vision systems. Deep Learning in Object Recognition, Detection, and Segmentation provides a comprehensive introductory overview of a topic that is having major impact on many areas of research in signal processing, computer vision, and machine learning. This is a must-read for students and researchers new to these fields.

作為人工智慧的一個重大突破，深度學習在解決許多領域的重大挑戰上取得了令人印象深刻的成功，包括語音識別、自然語言處理、計算機視覺、圖像和視頻處理以及多媒體。本專著提供了深度學習的歷史概述，並重點介紹了其在物體識別、檢測和分割方面的應用，這些是計算機視覺的關鍵挑戰，並且在圖像和視頻中有眾多應用。具體而言，物體識別方面涵蓋了在ImageNet上的圖像分類、人臉識別和視頻分類。在檢測方面，本專著涵蓋了在ImageNet上的一般物體檢測、行人檢測、人臉特徵點檢測（人臉對齊）和人體特徵點檢測（姿態估計）。最後，在分割方面，它涵蓋了場景標籤、語義分割、人臉解析、人體解析和显著性檢測方面的最新進展。這些應用的具體示例解釋了深度學習超越傳統計算機視覺系統的關鍵點。《深度學習在物體識別、檢測和分割中的應用》提供了對一個對信號處理、計算機視覺和機器學習等研究領域產生重大影響的主題的全面介紹概述。這是必讀的對於這些領域的新生學生和研究人員。