메뉴 건너뛰기




Volumn 38, Issue 1, 2016, Pages 74-87

Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding

Author keywords

Human Machine Hybrid; Object Detection; Scene Recognition; Scene Understanding; Semantic Segmentation

Indexed keywords

IMAGE SEGMENTATION; OBJECT RECOGNITION; SEMANTICS;

EID: 84961639809     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2015.2437377     Document Type: Article
Times cited : (23)

References (44)
  • 4
    • 80052895150 scopus 로고    scopus 로고
    • Articulated pose estimation using flexible mixtures of parts
    • Y. Yang and D. Ramanan, "Articulated pose estimation using flexible mixtures of parts," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 1385-1392.
    • (2011) Proc. IEEE Conf. Comput. Vis. Pattern Recog , pp. 1385-1392
    • Yang, Y.1    Ramanan, D.2
  • 5
    • 65249140851 scopus 로고    scopus 로고
    • How many pixels make an image?
    • A. Torralba, "How many pixels make an image?" Vis. Neurosci., vol. 26, no. 1, pp. 123-131, 2009.
    • (2009) Vis. Neurosci. , vol.26 , Issue.1 , pp. 123-131
    • Torralba, A.1
  • 7
    • 84866687133 scopus 로고    scopus 로고
    • Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation
    • J. Yao, S. Fidler, and R. Urtasun, "Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, pp. 702-709.
    • (2012) Proc. IEEE Conf. Comput. Vis. Pattern Recog , pp. 702-709
    • Yao, J.1    Fidler, S.2    Urtasun, R.3
  • 8
    • 84858763935 scopus 로고    scopus 로고
    • Cascaded classification models: Combining models for holistic scene understanding
    • G. Heitz, S. Gould, A. Saxena, and D. Koller, "Cascaded classification models: Combining models for holistic scene understanding," in Proc. Adv. Neural Inf. Process. Syst., 2008, pp. 641-648.
    • (2008) Proc. Adv. Neural Inf. Process. Syst , pp. 641-648
    • Heitz, G.1    Gould, S.2    Saxena, A.3    Koller, D.4
  • 9
    • 85162313618 scopus 로고    scopus 로고
    • Towards holistic scene understanding: Feedback enabled cascaded classification models
    • C. Li, A. Kowdle, A. Saxena, and T. Chen, "Towards holistic scene understanding: Feedback enabled cascaded classification models," in Proc. Adv. Neural Inf. Process. Syst., 2010, pp. 1351-1359.
    • (2010) Proc. Adv. Neural Inf. Process. Syst , pp. 1351-1359
    • Li, C.1    Kowdle, A.2    Saxena, A.3    Chen, T.4
  • 11
    • 5044232205 scopus 로고
    • Recovering intrinsic scene characteristics from images
    • Stanford Research Institute, Menlo Park, CA US
    • H. G. Barrow and J. M. Tenenbaum, "Recovering intrinsic scene characteristics from images," Stanford Research Institute, Menlo Park, CA US, Tech. Rep. AI-TN-157, 1978.
    • (1978) Tech. Rep. AI-TN-157
    • Barrow, H.G.1    Tenenbaum, J.M.2
  • 18
    • 33745848658 scopus 로고    scopus 로고
    • A hierarchical field framework for unified context-based classification
    • S. Kumar and M. Hebert, "A hierarchical field framework for unified context-based classification," in Proc. 10th IEEE Int. Conf. Comput. Vis., 2005, pp. 1284-1291.
    • (2005) Proc. 10th IEEE Int. Conf. Comput. Vis , pp. 1284-1291
    • Kumar, S.1    Hebert, M.2
  • 20
    • 57149143156 scopus 로고    scopus 로고
    • A dynamic conditional random field model for joint labeling of object and scene classes
    • C. Wojek and B. Schiele, "A dynamic conditional random field model for joint labeling of object and scene classes," in Proc. Eur. Conf. Comput. Vis., 2008, vol. 4, pp. 733-747.
    • (2008) Proc. Eur. Conf. Comput. Vis , vol.4 , pp. 733-747
    • Wojek, C.1    Schiele, B.2
  • 22
    • 0029655798 scopus 로고    scopus 로고
    • Localizing contours defined by more than one attribute
    • J. Rivest and P. Cabanagh, "Localizing contours defined by more than one attribute," Vis. Res., vol. 36, no. 1, pp. 53-66, 1996.
    • (1996) Vis. Res. , vol.36 , Issue.1 , pp. 53-66
    • Rivest, J.1    Cabanagh, P.2
  • 24
    • 0037047130 scopus 로고    scopus 로고
    • Rapid natural scene categorization in the near absence of attention
    • L. Fei-Fei, R. VanRullen, C. Koch, and P. Perona, "Rapid natural scene categorization in the near absence of attention," Proc. Nat. Acad. Sci. USA, vol. 99, no. 14, pp. 9596-9601, 2002.
    • (2002) Proc. Nat. Acad. Sci. USA , vol.99 , Issue.14 , pp. 9596-9601
    • Fei-Fei, L.1    VanRullen, R.2    Koch, C.3    Perona, P.4
  • 25
    • 84887323591 scopus 로고
    • Identification of spatially quantized tachistoscopic images of faces: How many pixels does it take to carry identity?
    • T. Bachmann, "Identification of spatially quantized tachistoscopic images of faces: How many pixels does it take to carry identity?" Europ. J. Cogn. Psych., vol. 3, no. 1, pp. 87-103, 1991.
    • (1991) Europ. J. Cogn. Psych. , vol.3 , Issue.1 , pp. 87-103
    • Bachmann, T.1
  • 26
    • 0034269180 scopus 로고    scopus 로고
    • Diagnostic colors mediate scene recognition
    • A. Oliva and P. G. Schyns, "Diagnostic colors mediate scene recognition," Cognitive Psychol., vol. 41, no. 2, pp. 176-210, 2000.
    • (2000) Cognitive Psychol. , vol.41 , Issue.2 , pp. 176-210
    • Oliva, A.1    Schyns, P.G.2
  • 27
  • 29
    • 84856671912 scopus 로고    scopus 로고
    • Recognizing jumbled images: The role of local and global information in image classification
    • D. Parikh, "Recognizing jumbled images: The role of local and global information in image classification," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 519-526.
    • (2011) Proc. IEEE Conf. Comput. Vis. Pattern Recog , pp. 519-526
    • Parikh, D.1
  • 34
    • 85162009902 scopus 로고    scopus 로고
    • A primal-dual message-passing algorithm for approximated large scale structured prediction
    • T. Hazan and R. Urtasun, "A primal-dual message-passing algorithm for approximated large scale structured prediction," in Proc. Adv. Neural Inf. Process. Syst., 2010, pp. 838-846.
    • (2010) Proc. Adv. Neural Inf. Process. Syst , pp. 838-846
    • Hazan, T.1    Urtasun, R.2
  • 35
    • 58149151266 scopus 로고    scopus 로고
    • Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling appearance, shape and context
    • J. Shotton, J. Winn, C. Rother, and A. Criminisi, "Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling appearance, shape and context," Int. J. Comput. Vis., vol. 81, no. 1, pp. 2-23, 2007.
    • (2007) Int. J. Comput. Vis. , vol.81 , Issue.1 , pp. 2-23
    • Shotton, J.1    Winn, J.2    Rother, C.3    Criminisi, A.4
  • 36
    • 84898492432 scopus 로고    scopus 로고
    • Improving spatial support for objects via multiple segmentations
    • T. Malisiewicz and A. A. Efros, "Improving spatial support for objects via multiple segmentations," in Proc. Brit. Mach. Vis. Conf., 2007, pp. 55.1-55.10.
    • (2007) Proc. Brit. Mach. Vis. Conf , pp. 551-5510
    • Malisiewicz, T.1    Efros, A.A.2
  • 40
    • 84933530882 scopus 로고
    • Approximating discrete probability distributions with dependence trees
    • May
    • C. K. Chow and C. N. Liu, "Approximating discrete probability distributions with dependence trees," IEEE Trans. Inf. Theory, vol. IT-14, no. 3, p. 462-467, May 1968.
    • (1968) IEEE Trans. Inf. Theory , vol.IT-14 , Issue.3 , pp. 462-467
    • Chow, C.K.1    Liu, C.N.2
  • 43
  • 44
    • 84903211110 scopus 로고    scopus 로고
    • Relating things and stuff via object property interactions
    • Jul
    • M. Sun, B. soo Kim, P. Kohli, and S. Savarese, "Relating things and stuff via object property interactions," IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 7, pp. 1370-1383, Jul. 2014.
    • (2014) IEEE Trans. Pattern Anal. Mach. Intell , vol.37 , Issue.7 , pp. 1370-1383
    • Sun, M.1    Soo Kim, B.2    Kohli, P.3    Savarese, S.4


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.