연구동향 분석
박사

2D 이미지에서 3D 조형물 인식을 위한 딥러닝 네트워크 구조설계

김예진 2020년

논문상세정보
    • 저자 김예진
    • 기타서명 Deep Learning Network Architecture Design for 3D Sculpture Identification
    • 형태사항 26 cm: 95 p.:: 삽화;
    • 일반주기 지도교수:김종원, 상명대학교 논문은 저작권에 의해 보호받습니다, 참고문헌: p.146-152
    • 학위논문사항 저작권보호학과,, 2020. 2, 상명대학교 일반대학원:, 학위논문(박사)-
    • DDC 23, 006.3
    • 발행지 서울:
    • 언어 eng
    • 출판년 2020
    • 발행사항 상명대학교 일반대학원,
    • 주제어 딥 러닝
    유사주제 논문( 2,050)
인용/피인용
' 2D 이미지에서 3D 조형물 인식을 위한 딥러닝 네트워크 구조설계' 의 주제별 논문영향력
논문영향력 선정 방법
논문영향력 요약
주제
  • 특정한 컴퓨터방법
  • 딥 러닝
동일주제 총논문수 논문피인용 총횟수 주제별 논문영향력의 평균
2,052 0

0.0%

' 2D 이미지에서 3D 조형물 인식을 위한 딥러닝 네트워크 구조설계' 의 참고문헌

  • ¡°Overfeat : Integrated recognition , localization , and detection usingConvolutional networks
    [2013]
  • [99] Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., & L ing, H. (2019, July). M2det: A single-shot object detector based on multi-level feature pyramid network. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, pp. 9259-926 6).
  • [44] Bay, H., Tuytelaars, T., & Van Gool, L. (2006, May). Surf: Spee ded up robust features. In European conference on computer vi sion (pp. 404-417). Springer, Berlin, Heidelberg.
  • [29] https://en.wikipedia.org/wiki/Sculpture
  • [21] https://www.zdnet.co.kr/view/?no=20170807140504&re=R_20190306 123420
  • [20] http://www.aitimes.kr/news/articleView.html?idxno=12087
  • [16] Bay, H., Tuytelaars, T., & Van Gool, L. (2006, May). Surf: Spee ded up robust features. In European conference on computer vi sion (pp. 404-417). Springer, Berlin, Heidelberg.
  • [124] https://en.wikipedia.org/wiki/Precision_and_recall
  • [123] Newell, A., Yang, K., & Deng, J. (2016, October). Stacked hour glass networks for human pose estimation. In European confer ence on computer vision (pp. 483-499). Springer, Cham.
  • Zoom out-and-i n network with recursive training for object proposal
    [2017]
  • You only look once : Unified , real-time object detection . In Proceedin gs of the IEEE conference on computer vision and pattern reco gnition
    pp . 779-788 [2016]
  • Yolov3 : An incremental improvement
    [2018]
  • YOLO9000 : better , faster , stronger
    pp . 7263-7271 [2017]
  • Training regio n-based object detectors with online hard example mining
    pp . 761-769 [2016]
  • Tracking feature extraction techniques with improved SIFT for video identification
    76 ( 4 ) , 5927-5936 [2017]
  • Towards Adversarially Robust O bject Detection
    [2019]
  • Structure infere nce net : Object detection using scene-level context and instanc e-level relationships
    pp . 6985-6994 ) [2018]
  • Ssd : Single shot multibox det ector . In EuropeanConference onComputer vision
    pp . 21-37 [2016]
  • Spatial pyramid pooling in deepConvolutional networks for visual recognition
    37 ( 9 ) , 1904-1916 [2015]
  • Spatial memory forContext reaso ning in object detection
    pp . 4086-4096 [2017]
  • Softer-nms : Rethinking bounding box regression for accurate object detectio n. arXiv
    [2018]
  • Soft-N MS -Improving Object Detection With One Line ofCode
    pp . 5561-5569 ) [2017]
  • Soft sampling for robust object detection
    [2018]
  • Singleshot refinement neural network for object detection
    pp . 4203-4212 [2018]
  • SemanticContours from inverse detectors . In 2 011 InternationalConference onComputer Vision
    pp . 991-998
  • ScratchDet : Training Single-Shot Object Detectors fr om Scratch
    pp . 2268-2277 [2019]
  • Scale-transf errable object detection
    pp . 528-537 [2018]
  • Scale invariant feature transform
    [2012]
  • Scalable object detection using deep neural networks
    pp . 2147-2154 [2014]
  • SNIPER : Efficient multiscale training
    pp . 9310-9320 [2018]
  • Ron : ReverseConnection with objectness prior networks for obj ect detection
    pp . 5936-5944 [2017]
  • Robust Wide-baseline Stereo from Maximally Stable Extremal Regions
    22 ( 10 ) , 761-767 [2004]
  • Rich feature hierarchies for accurate object detection and semantic segmentation
    pp . 580-587 [2014]
  • Relation Networks for Object Detection
    pp . 3588-359 7 [2018]
  • Region-b ased saliency detection and its application in object recognition . I EEE Transactions onCircuits and Systems for Video Technology
    24 ( 5 ) , 769-779 [2013]
  • Recurrent scale approximation for object detection inCnn
    pp . 571-579 [2017]
  • Receptive field block net for accur ate and fast object detection
    pp . 385-400 [2018]
  • Reasoning -RCNN : Unifying Adaptive Global Reasoning Into Large-Scale Object Detection
    pp . 6419-6428 [2019]
  • R-fcn : Object detection via region-based fullyConvolutional networks
    pp . 379-387 [2016]
  • Pv anet : Deep but lightweight neural networks for real-time object detection .
    [2016]
  • Pelee : A real-time ob ject detection system on mobile devices
    pp . 1963-1972 [2018]
  • Parallel feature pyramid network for object detection
    pp . 234-250
  • On optimization methods for deep learning .
    pp . 265-272 ) . Omnipress [2011]
  • Object retrieval with large vocabularies and fast spatial matching
    [2007]
  • Object detection via a multi-region and semantic segmentation-aware cnn model
    pp . 1134-1142 ) . [2015]
  • Object Detection based on Region Decomposi tion and Assembly .
    [2019]
  • Objec t detection networks on convolutional feature maps
    39 ( 7 ) , 1476- 1481 [2016]
  • Name that scul pture
    [2012]
  • Multi-sc ale location-aware kernel representation for object detection
    pp . 1248-1257 [2018]
  • Multi-adversarial Faster-RCNN for Unrestricted Object Detection
    [2019]
  • Metaa nchor : Learning to detect objects with customized anchors
    pp . 320-330 [2018]
  • Megdet : A large mini-batch object detector
    pp . 6181-6189 [2018]
  • MaxpoolNMS : Getting Rid of NMS Bott lenecks in Two-Stage Object Detectors .
    pp . 9356-9364 [2019]
  • Mask ´ r-cnn
    pp . 2961-2969 [2017]
  • Light-head r-cnn : In defense of two-stage object detector
    [2017]
  • Learning me thods for generic object recognition with invariance to pose and lighting .
    2 ) ( pp . 97-104 ) . [2004]
  • Learning and-or templates for object recognition and detection
    35 ( 9 ) , 2189-2205 [2013]
  • Is Object Localization for Free ? – Weakly-Supervised Learning With Convolutional Neural Networks
    pp . 685-694 [2015]
  • Integrating machine learnin g and workflow management to support acquisition and adaptati on of workflow models
    9 ( 2 ) , 67-92 . [2000]
  • Inside-Outside Net : Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
    pp . 2874-28 83 [2016]
  • Improving object loca lization with fitness nms and bounded iou loss
    pp . 6877-6885 [2018]
  • Improving Object Detection from Scratch via Gated Feature Reuse
    [2019]
  • Imp roving object detection with deep convolutional networks via ba yesian optimization and structured prediction
    pp . 249-258 [2015]
  • ImagenetClassification with deepConvolutional neural networks
    pp . 1097-1105 [2012]
  • ImageNet Large Scale Visual Recognition Challenge
    115 ( 3 ) , 211 -252 [2015]
  • Hypernet : Towar ds accurate region proposal generation and joint object detectio n. In Proceedings of the IEEE conference on computer vision a nd pattern recognition
    pp . 845-853 ) [2016]
  • Hybrid knowledge routed modules for large-scale object detection
    pp . 1552-1563 [2018]
  • Histograms of oriented grad ients for human detection . ] with an SVM machine learning mode l [ SomanMachine lear ning with SVM and other kernel methods
    [2005]
  • Histograms of Oriented Gradients for Human Detection
    [2005]
  • Handwriting Arabic character recognition Le Net using neural network
    6 ( 3 ) , 304-3 09 . [2009]
  • Going Deeper with Convolutions
    pp . 1-9 [2015]
  • Generalized intersection over union : A metri c and a loss for bounding box regression
    pp . 658-666 [2019]
  • Gaussian YO LOv3 : An Accurate and Fast Object Detector using Localization Uncertainty for Autonomous Driving .
    [2019]
  • G-cnn : an iterative grid based object detector
    pp . 2369-23 77 [2016]
  • Fully Convolutional Networks for Semantic Segmentation
    pp . 343 1-3440 [2015]
  • Focal loss for dense object detection
    pp . 2980-2988 ) [2017]
  • Features from accelerated segment test ( fast )
    [2009]
  • Feature pyramid networks for object detection
    pp . 2117-2125 [2017]
  • Faster r-cnn : Towards real-time object detection with region proposal networks
    pp . 91-18 99 ) . [2015]
  • Fast R-CNN
    pp . 1440-1448 [2015]
  • Facial feature detection using Haar classifiers
    21 ( 4 ) , 127-133 . [2006]
  • F orest species recognition using deep convolutional neural networ ks
    [2014]
  • Dssd : Deconvolutional single shot detector
    [2017]
  • Dsod : Learning deeply supervised object detectors from scrat ch
    pp . 1919-1927 ) .
  • Domain adaptive f aster r-cnn for object detection in the wild
    pp . 3339-3348 [2018]
  • Distinctive image features from scale-invariant keypoints
    60 ( 2 ) , 9 1-110 . [2004]
  • Denet : Scalable realtime object detection with directed sparse sampling
    pp . 428-436 ) [2017]
  • Delving deep into rectifiers : Surpassing human-level performance on imagenet classification
    pp . 1026-1034 ) . [2015]
  • Deforma ble part models are convolutional neural networks
    pp . 437-446 [2015]
  • Deepproposal : Hunting objects by cascading deep co nvolutional layers
    pp . 2578-2586 ) [2015]
  • Deepid-net : Deformable deep convolutional neural networks for object detection
    pp . 2 403-2412 [2015]
  • Deepbox : Learning o bjectness with convolutional networks
    pp . 2479-2487 [2015]
  • Deep Residual Learning for Image Recognition
    pp . 770-778 [2016]
  • Deep Learning for Generic Object Detection : A Survey
    [2018]
  • D. H. P. ( 2018 , S eptember ) . Shapeshifter : Robust physical adversarial attack on f aster r-cnn object detector . In Joint European Conference on M achine Learning and Knowledge Discovery in Databases
    pp . 52- 68
  • D. ( 2 019 ) . Libra r-cnn : Towards balanced learning for object detecti on
    pp . 821-830
  • Crafting gbd-net for object detection
    40 ( 9 ) , 21 09-2123 [2017]
  • Craft objects from images
    pp . 6043-6051 [2016]
  • Couplenet : Coupling global structure with local parts for object detection
    pp . 4126-4134 ) [2017]
  • Cornernet : Detecting objects as pai red keypoints
    pp . 734-750 [2018]
  • Contextual priming and feedback for faster r-cnn . In European Conference on Com puter Vision
    pp . 330-348 [2016]
  • Class s egmentation and object localization with superpixel neighborhood s. In 2009
    [2009]
  • Cascade r-cnn : Delving into high quality object detection
    pp . 6154-6162 [2018]
  • Cas cade RetinaNet : Maintaining Consistency for Single-Stage Objec t Detection
    [2019]
  • Cap2Det : Learning to Amplify Weak Caption Supervision for Object Detection
    [2019]
  • CAMOU : Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild .
    [2018]
  • Bottom-up object detection by grouping extreme and center points
    pp . 850-859 [2019]
  • Blob analysis of the head and hands : A m ethod for deception detection . In Proceedings of the 38th Annua l Hawaii International Conference on System Sciences
    pp . 20c-2 0c [2005]
  • Beyond Skip Connections : Top-Down Modulation for Object Detection
    [2016]
  • Be yond sliding windows : Object localization by efficient subwindow search
    [2008]
  • Attentionnet : Aggregating weak directions for accurate objec t detection
    pp . 2659-2667 ) .
  • An analysis of the Viola-Jones face detecti on algorithm
    4 , 128-148 [2014]
  • An Analysis of Scale Invariance in Object Detection - SNIP
    pp . 3578-3587 [2018]
  • Adaptive object detecti on using adjacency and zoom prediction
    [2016]
  • Adaptive NMS : Refining Pedestrian Detection in a Crowd
    pp . 64 59-6468 [2019]
  • A unified multi-scale deep convolutional neural network for fast object detection
    [2016]
  • A survey on object detection in opt ical remote sensing images
    117 , 11-28 [2016]
  • A survey of image classification met hods and techniques for improving classification performance
    28 ( 5 ) , 823-870 [2007]
  • A multipath network for object detection
    [2016]
  • .STDnet : AConvNet for Small Target Detection . BOSQUET , MUCIENTES , BREA : STDNET FOR SMALL TARGET DETECTION
    [2018]