Search

The objective of this document is to provide a non-technical introduction to the field of Artificial Intelligence. It is intended for anyone outside of the data science community curi-ous about the subject, such as researchers from other areas looking for new instruments, legal professionals confronted with automated decision making algorithms or legal tech tools, en-trepreneurs interested in expanding their products into new areas, etc. No prior knowledge of the domain is required for this introduction. External resources with technical details and additional examples are provided in the footnotes for the interested reader. In the following sections, we introduce the fundamental concepts in the field, aim to clarify some commonly used terms and explain some limitations of modern AI techniques. First, we distinguish two types of AI: the symbolic approach, consisting of systems encoding rules and explicit knowledge, and the machine learning approach, which uses statistical methods and models to automatically infer relations between data and tasks to solve. In the subsequent section, we distinguish two complexity levels of these tasks. Finally, we introduce the subfield of “Explainable Artificial Intelligence” and distinguish three classes of explanations.

The social design approach presented in this chapter was developed to ensure that the new smart living lab building includes not only sus- tainable environmental and economic aspects, but also social aspects. By better understand- ing the preferences and attitudes of its future occupants and the three founding institutions, the team will be able to successfully incorpo- rate the former in the design process.

The Audio/Visual Emotion Challenge and Workshop (AVEC 2016) "Depression, Mood and Emotion" will be the sixth competition event aimed at comparison of multimedia processing and machine learning methods for automatic audio, visual and physiological depression and emotion analysis, with all participants competing under strictly the same conditions. The goal of the Challenge is to provide a common benchmark test set for multi-modal information processing and to bring together the depression and emotion recognition communities, as well as the audio, video and physiological processing communities, to compare the relative merits of the various approaches to depression and emotion recognition under well-defined and strictly comparable conditions and establish to what extent fusion of the approaches is possible and beneficial. This paper presents the challenge guidelines, the common data used, and the performance of the baseline system on the two tasks.

This article examines the influence of mood feedback on different outcomes of teamwork in two different collaborative work environments. Employing a 2 x 2 between-subjects design, mood feedback (present vs. not present) and communication mode (face-to-face vs. video conferencing) were manipulated experimentally. We used a newly developed collaborative communication environment, called EmotiBoard, which is a large vertical interactive screen, with which team members can interact in a face-to-face discussion or as a spatially distributed team. To support teamwork, this tool provides visual feedback of each team member’s emotional state. Thirty-five teams comprising 3 persons each (with a confederate in each team) completed three different tasks, measuring mood, performance, subjective workload, and team satisfaction. Results indicated that the evaluation of the other team members’ emotional state was more accurate when the mood feedback was presented. In addition, mood feedback influenced team performance positively in the video conference condition and negatively in the face-to-face condition. Furthermore, participants in the video conference condition were more satisfied after task completion than participants in the face-to-face condition. Findings indicate that the mood feedback toolis helpful for teams to gain a more accurate understanding of team members’ emotional states in different work situations.

International audience; Fusion engines are fundamental components of multimodal interactive systems, to interpret input streams whose meaning can vary according to the context, task, user and time. Other surveys have considered multimodal interactive systems; we focus more closely on the design, specification, construction and evaluation of fusion engines. We first introduce some terminology and set out the major challenges that fusion engines propose to solve. A history of past work in the field of fusion engines is then presented using the BRETAM model. These approaches to fusion are then classified. The classification considers the types of application, the fusion principles and the temporal aspects. Finally, the challenges for future work in the field of fusion engines are set out. These include software frameworks, quantitative evaluation, machine learning and adaptation.

This paper proposes a method, combining color and layout features, for identifying documents captured from lowresolution handheld devices. On one hand, the document image color density surface is estimated and represented with an equivalent ellipse and on the other hand, the document shallow layout structure is computed and hierarchically represented. The combined color and layout features are arranged in a symbolic file, which is unique for each document and is called the document-s visual signature. Our identification method first uses the color information in the signatures in order to focus the search space on documents having a similar color distribution, and finally selects the document having the most similar layout structure in the remaining search space. Finally, our experiment considers slide documents, which are often captured using handheld devices., {"references":["S. Mukhopadhyay, and B. Smith, \"Passive capture and structuring of\nlectures,\" in Proc. of ACM Multimedia, 1999, pp. 477-487.","B. Erol, and J. Hull, \"Linking presentation documents using image\nanalysis,\" in Asilomar Conf. on Signals, Systems, and Computers, Nov.\n9-12 2003, Pacific Grove, CA.","D. Franklin, S. Bradshaw, and K. J. Hammond, \"Jabberwocky: you don-t\nhave to be a rocket scientist to change slides for hydrogen combustion\nlecture,\" Intelligent User Interface, 2000, pp. 98-105.","D. Lee, B. Erol, J. Graham, J. J. Hull, and N. Murata, \"Portable meeting\nrecorder,\" In ACM Multimedia Conference, 2000, pp. 493-502.","G. D. Abowd, \"Classroom 2000: An experiment with the\ninstrumentation of a living educational environment,\" IBM Systems\nJournal, Special issue on Pervasive Computing, vol. 38, No. 4, pp. 508-\n530, 1999.","P. Chiu, A. Kapuskar, and L. Wilcox, \"Meeting capture in a media\nenriched conference room,\" in 2nd International Workshop on\nCooperative Buildings, 1999, pp.79-88.","D. Lalanne, R. Ingold, D. von Rotz, A. Behera, D. Mekhaldi and A.\nPopescu-Belis, ÔÇÿÔÇÿUsing static documents as structured and thematic\ninterfaces to multimedia meeting archives,\" in 1st Intl. Workshop on\nMachine Learning for Multimodal Interaction (MLMI), 2004, Martigny,\nSwitzerland, LNCS, vol. 3361, pp. 87-100.","P. Chiu, J. Foote, A. Girgensohn, and J. Boreczky, \"Automatically\nlinking multimedia meeting documents by image matching,\" in Proc. of\nACM Hypertext -00, 2000, pp. 244-245.","N. Ozawa, H. Takebe, Y. Katsuyama, S. Naoi, and H. Yakota, \"Slide\nidentification for lecture movies by matching characters and images,\" in\nProc. SPIE-Document Recognition and Retrieval XI, 2004, vol. 5296,\npp. 74-81.\n[10] J. Hu, R. Kashi, and G. Wilfong, \"Document classification using layout\nanalysis\", in Proc. International Workshop on Database and Expert\nSystems Applications, 1999, pp. 556-560.\n[11] C. Shin and D. Doermann, \"Classification of document page images\nbased on visual similarity of layout structures,\" in Proc. SPIE -\nDocument Recognition and Retrieval VII, 2000, pp. 182-190.\n[12] A. Dengel, and F. Dubiel, \"Clustering and classification of document\nstructure - a machine learning approach,\" in Proc. Second International\nConf. on Document Analysis and Recognition, 1993, pp. 587-591.\n[13] E. Appiani, and A.M. Colla, \"Automatic analysis and indexing of\nvariable-layout documents,\" in Proc. RIAO2000, Paris, France, April 12-\n14, 2000, pp. 980-987.\n[14] K. Y. Wong, R. G. Casey, and F. M. Wahl, \"Document analysis system,\"\nIBM Journal of Research and Development, vol.26, pp. 647-656, 1982.\n[15] G. Nagy, and S. Seth, \"Hierarchical representation of optically scanned\ndocuments,\" in Proceedings of International Conference on Pattern\nRecognition, 1984, Vol. 1, pp. 347-349.\n[16] H. S. Baird, S. E. Jones, and S. J. Fortune, \"Image segmentation by\nshape-directed covers,\" in Proceedings of International Conference on\nPattern Recognition, June 1990, pp. 820-825.\n[17] L. O. Gorman, \"The document spectrum for page layout analysis,\" IEEE\nTrans. on PAMI, vol. 15, pp. 1162-1173, 1993.\n[18] K. Kise, A. Sato, and M. Iwata, \"Segmentation of page images using the\narea voronoi diagram,\" Computer Vision and Image Understanding, vol.\n70, pp. 370-382, 1998.\n[19] F. Wahl, K. Wong, and R. Casey, \"Block segmentation and text\nextraction in mixed text/image documents,\" Graphical Models and\nImage Processing, vol. 20, pp. 375-390, 1982.\n[20] T. Pavlidis and J. Zhou, \"Page segmentation and classification,\" CVGIP\nvol. 54, pp. 484-496, 1992.\n[21] T. Weldon and W. Higgins, \"An algorithm for designing multiple gabor\nfilters for segmenting multi-textured images,\" in IEEE International\nConference on Image Processing, Chicago, October, 1998, pp. 4-7.\n[22] A.K. Jain, and S.K. Bhattacharjee, \"Address block location on envelopes\nusing gabor filters,\" Pattern Recognition, vol. 25, no.12, pp. 1459-1477,\n1992.\n[23] A. K. Jain, and Y. Zhong, \"Page segmentation using texture analysis,\"\nPattern Recognition, 1996, vol. 29, pp. 743-770.\n[24] X.Wan, and C.C.J. Kuo, \"Color distribution analysis and quantization\nfor image retrieval,\" in Proceedings of SPIE, vol. 2670, February 1996.\n[25] M. Stricker, M. Orengo, \"Similarity of color images,\" in SPIE\nConference on Storage and Retrieval for Image and Video Databases\nIII, February 1995, vol. 2420, pp. 381-392.\n[26] P. Aigrain, H. Zhang, and D. Petkovic, \"Content-based representation\nand retrieval of visual media: a state-of-the-art review,\" Multimedia\nTools and Applications, 1996, no. 3, pp. 179-202.\n[27] B.S. Manjunath, W.Y. Ma, \"Texture features for browsing and retrieval\nof image data,\" IEEE Transactions on Pattern Analysis and Machine\nIntelligence, vol. 18, no. 8, pp. 837-842, 1996.\n[28] B.S. Manjunath, J.R Ohm, V.V. Vasudevan, and A. Yamada, \"Color and\ntexture descriptors,\" IEEE Trans. on Circuits and Systems for Video\nTechnology, vol. 11, no. 6, pp. 703-715, 2001.\n[29] A.K. Jain and A. Vailaya, \"Image retrieval using color and shape,\"\nPattern Recognition, vol. 29, no. 8, pp. 1233-1244, 1996.\n[30] J.E. Gary, and R. Mehrotra, \"Similar shape retrieval using a structural\nfeature index,\" Information Systems, 18, 7, pp. 525-537, October 1990.\n[31] M. Petkovic', \"Content-based video retrieval,\" in 7th International\nConference on Extending Database Technology, March 27-31, 2000,\nKonstanz, Germany, pp 74-77.\n[32] M. Swain and D. Ballard, ÔÇÿÔÇÿColor indexing--, Intl. Journal of Computer\nVision, vol. 7, no. 1, pp. 11-32, 1991.\n[33] D. W. Scott, Multivariate Density Estimation. New York: John Wiley,\n1992.\n[34] B. W. Silverman, Density Estimation for Statistic and Data Analysis.\nNew York: Chapman and Hall, 1986.\n[35] E. Parzen, \"On estimation of a probability density function and mode,\"\nAnn. Math. Stat., vol. 33, pp. 1065-1076, 1962.\n[36] M. J. Jones and J. M. Rehag, \"Statistical color models with application\nto skin detection,-- Intl. Journal of Computer Vision, vol. 46, no. 1, pp.\n81-96, 2002.\n[37] R. Cattoni, T. Coianiz, S. Messelodi, and C. M. Modena, \"Geometric\nlayout analysis techniques for document image understanding a review,\"\nTechnical Report, ITC-IRST, Trento, Italy 1998.\n[38] A. Behera, D. Lalanne and R. Ingold, \"Visual signature based\nidentification of low-resolution document images,\" ACM Symposium on\nDocument Engineering, Milwaukee, Wisconsin, 2004, pp. 178-187."]}

This paper proposes a method, combining color and layout features, for identifying documents captured from low-resolution handheld devices. On one hand, the document image color density surface is estimated and represented with an equivalent ellipse and on the other hand, the document shallow layout structure is computed and hierarchically represented. Our identification method first uses the color information in the documents in order to focus the search space on documents having a similar color distribution, and finally selects the document having the most similar layout structure in the remaining of the search space.