Seminar "Selected Topics in Human Language Technology and Pattern Recognition"

Registration for the seminar

Prerequisites for participation in the seminar

• Bachelor students: Einführung in das wissenschaftliche Arbeiten (Proseminar)
• Master students: Bachelor degree
• Diploma students: Vordiplom
  
• Attendance of at least one of the lectures Pattern Recognition and Neural Networks, Introduction to Statistical Classification, Automatic Speech Recognition, or Statistical Methods in Natural Language Processing, or evidence of equivalent knowledge.
• For successful participants of the above lectures, the possibility of a seminar talk is guaranteed.
  

Seminar format and important dates

• Proposals: initial proposals (report's content page) will be accepted up until the start of the term (April 1, 2013) by the individual supervisor. Email submission will be sufficient. At this time participants must arrange an appointment with the individual supervisor. Revised proposals will be accepted up until two weeks after the start of the term (April 14, 2013).
• Article: must be submitted by June 7, 2013 and at least 1 month prior to the trial presentation date to the individual supervisor in electronic form (PDF).
  
• Presentation slides: must be submitted at least 1 week prior to the trial presentation date to the individual supervisor in electronic form (PDF).
• Trial presentations: at least 2 weeks prior to the actual presentation date. Please refer to your individual supervisor to schedule your trial presentation.
• Seminar presentations: the exact dates and schedule for the presentation block (expected to be around end of July/beginning of August 2013) will be arranged and announced for the individual topics.
• Final (possibly corrected) articles and presentation slides: must be submitted within 4 weeks after the presentation date at the latest to the individual supervisor in electronic form (PDF).
• Compulsory attendance: in order to receive a certificate participants must attend all presentation sessions.
• Ethical Guidelines:The Computer Science Department of RWTH Aachen University has adopted ethical guidelines for the authoring of academic work such as seminar reports. Each student has to comply with these guidelines. In this regard, you, as a seminar attendant, have to sign a declaration of compliance, in which you assert that your work complies with the guidelines, that all references used are properly cited, and that the report was done autonomously by yourself. We ask you do download the guidelines and submit the declaration together with your seminar report and talk to your individual supervisor. You also find a German version of the guidelines and a German version of the declaration you may use as well.

Note: failure to meet deadlines, absence without permission from compulsory sessions (presentations and preliminary meeting as announced by email to each participating student), or dropping out of the seminar after more than 3 weeks after the kick-off meeting (i.e. by March 11, 2013) results in the grade 5.0/not appeared.

Topics, relevant references and participants

• Automatic Speech Recognition;
• Machine Translation;
• Pattern Recognition.

1. Open-vocabulary Handwriting (and Speech) Recognition (Matysiak; Supervisor: Michal Kozielski)
   References:
   
   • Vertanen, K.: Combining open vocabulary recognition and word confusion networks. Acoustics, Speech and Signal Processing, 2008. (ICASSP 2008), pp.4325-4328.
   • Issam Bazzi, Richard M. Schwartz, John Makhoul: An Omnifont Open-Vocabulary OCR System for English and Arabic. IEEE Trans. Pattern Anal. Mach. Intell. 21(6): 495-504 (1999)
   • M. A. Basha Shaik, A. El-Desoky Mousa, R. Schlüter, and H. Ney: Hybrid Language Models Using Mixed Types of Sub-lexical Units for Open Vocabulary German LVCSR. In Interspeech, pages 1441-1444, Florence, Italy, August 2011.
2. Feature Extraction for Off-line Handwriting Recognition (Ketabdar; Supervisor: Michal Kozielski)
   References:
   
   • John T. Favata, Geetha Srikantan: A multiple feature/resolution approach to handprinted digit and character recognition. International Journal of Imaging Systems and Technology. Volume 7, Issue 4, pages 304-311, Winter 1996
   • Marti, U.-V. and Bunke, H.:Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition systems, Published in Book Hidden Markov models, pages 65--90, 2002
   • José A. Rodriguez, Florent Perronnin: Local gradient histogram features for word spotting in unconstrained handwritten documents; ICFHR 2008 (International Conference on Frontiers in Handwriting Recognition), Montréal, Canada, 19-21 August, 2008
3. The Vanishing Gradient Problem in Recurrent Neural Networks (Hauptmann; Supervisor: Patrick Dötsch)
   References:
   
   • Bengio, Y.; Simard, P.; Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. Neural Networks, IEEE Transactions on , vol.5, no.2, pp.157-166, Mar 1994
   • Sepp Hochreiter , Yoshua Bengio , Paolo Frasconi , Jürgen Schmidhuber: Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies. In book A field guide to dynamical recurrent neural networks, pages 237-243, 2001.
   • Sepp Hochreiter, Jürgen Schmidhuber: Long Short-Term Memory. In journal Neural Computations, volume 9, number 8, 1997, pages 1735-1780.
4. Connectionist Temporal Classification (Voigtländer; Supervisor: Patrick Dötsch)
   References:
   
   • Alex Graves, Santiago Fernández, Faustino Gomez, Jürgen Schmidhuber: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks; In ICML '06, pages 369-376, 2006.
   • Graves, A.; Liwicki, M.; Fernandez, S.; Bertolami, R.; Bunke, H.; Schmidhuber, J.: A Novel Connectionist System for Unconstrained Handwriting Recognition. Pattern Analysis and Machine Intelligence, vol. 31, no. 5, pages 855-868, May 2009.
   • Alex Graves: Supervised Sequence Labelling with Recurrent Neural Networks; Studies in Computational Intelligence, volume 385, pages 1-131, 2012.
5. Self-Taught Learning for Handwriting Recognition (Kim; Supervisor: Mehdi Hamdani)
   References:
   
   • Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, Andrew Y. Ng: Self-taught learning: transfer learning from unlabeled data; ICML 2007, pages 759-766.
   • Bastien et al.: Deep Self-Taught Learning for Handwritten Character Recognition, in CoRR, 2010.
   • Bengio: Deep Learning of Representations for Unsupervised and Transfer Learning; JMLR W&CP 27:17-36, 2012.
6. Signer Adaptive Techniques for Sign Language Recognition (Habalov; Supervisor: Yannick Gweth)
   References:
   
   • Gweth, Yannick and Plahl, Christian and Ney, Hermann: Enhanced Continuous Sign Language Recognition using PCA and Neural Network Features; CVPR 2012 Workshop on Gesture Recognition, 2012
   • von Agris, U. and Knorr, M. and Kraiss, K.-F.: The Significance of Facial Features for Automatic Sign Language Recognition; in FG 2008
   • Wade Shen; Reynolds, D.; , "Improved GMM-based language recognition using constrained MLLR transforms," Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on , vol., no., pp.4149-4152, March 31 2008-April 4 2008
7. Tracking with Body Pose Estimation in Sign Language (NN; Supervisor: Christian Oberdörfer)
   References:
   
   • Buehler et al.: Upper Body Detection and Tracking in Extended Signing Sequences, in IJCV 2011.
   • Pfister et al.: Automatic and Efficient Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcast, in BMVC 2012.
   • Yang et al.: Articulated Pose Estimation with flexible Mixtures-of-Parts, in CVPR 2011.
8. Spotting Signs in Context (NN; Supervisor: Jens Forster)
   References:
   
   • Yang, Sclaroff, Lee: Sign Language Spotting with a Threshold Model Based on Conditional Random Fields; in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no 7, 2009, pages 1264-1277
   • Cooper and Bowden: Learning Signs from Subtitles: A Weakly Supervised Approach to Sign Language Recognition; in CVPR 2009, pages 2568-2574
   • Buehler, Everingham, Zisserman: Employing signed TV broadcasts for automated learning of British Sign Language; Workshop on the Representation and Processing of Sign Languages 2010, LREC 2010 Malta
9. Handling Epenthesis in Sign Language Recognition (Thill; Supervisor: Jens Forster)
   References:
   
   • Yang, Sarkar, Loeding: Handling Movement Epenthesis and Sign Ambiguities in Continuous Sign Language Recognition using Nested Dynamic Programming; IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 3, 2010, pages 462-477
   • Fang, Gao, Zhao: Large-Vocabulary Continuous Sign Language Recognition Based on Transition-Movement Models; IEEE Transactions on Systems, Man, And Cypernetics - Part A: Systems and Humans, vol. 37, no. 1, 2007
   • Kelly, McDonald, Markham: Recognizing Spatiotemporal Gestures and Movement Epenthesis in Sign Language; in International Machine Vision and Image Processing Conference 2009, pages 145-150
10. Keypoint-based Object Matching (Takahashi; Supervisor: Harald Hanselmann)
    References:
    
    • Li, H. and Huang, J. and Zhang, S. and Huang, X.: Optimal object matching via convexification and composition, ICCV 2011, pages 33-40
    • Jiang, H. and Tian, T.P. and Sclaroff, S.: Scale and rotation invariant matching using linearly augmented trees; CVPR 2011, pages 2473-2480
    • Lowe, D.G.: Distinctive image features from scale-invariant keypoints; International journal of computer vision, vol 60, no 2, pages 91-110, 2004
11. Multimodal Sign Language Recognition (NN; Supervisor: Yannick Gweth)
    References:
    
    • von Agris, U. and Knorr, M. and Kraiss, K.-F.: The Significance of Facial Features for Automatic Sign Language Recognition; in FG 2008
    • Kelly, Daniel: A Framework for Continuous Multimodal Sign Language Recognition. ICMI-MLMI 2009
    • Dan, Luan et al.: Human Gesture Analysis using Multimodal Features. IEEE International Conference on Multimedia and Expo Workshops

Guidelines for the article and presentation

• Online LaTeX-Documentation:

• LaTeX: "A document preparation system"
• LaTeX help 1.1
• The Not So Short Introduction to LaTeX
  
• LaTeX 2e for authors

• Document Templates:

• Article Template (164kB),  contains the template and all necessary files in tar format (or here 53kB in zip format).
• Presentation Slide Template (4.9MB), a zip file containing the template and all necessary graphics as well as the institute’s style template.

• Guidelines for articles and presentation slides:

• The aim of the seminar for the participants is to learn the following:
• to tackle a topic and to expand knowledge
• to critically analyze the literature
  
• to hold a presentation
  
• Take notice of references to other topics in the seminar and discuss topics with one another!
  
• Take care to stay within your own topic. To this end participants should be aware of the other topics in the seminar. If applicable, cross-reference other articles and presentations.
  

• Important: As part of the introduction, a slide should outline the most important literature used for the presentation. In addition, the presentation should clearly indicate which literature the particular elements of the presentation refer to.
  
• Take notice of references to other topics in the seminar and discuss topics with one another!
  
• Participants are expected to seek out additional literature on their topic. Assistance with the literature search is available at the faculty’s library. Access to literature is naturally also available at the Lehrstuhl für Informatik 6 library.
• Notation/Mathematical Formulas: consistent, correct notation is essential. When necessary, differing notation from various literature sources is to be modified or standardized in order to be clear and consistent. The lectures held by the Lehrstuhl für Informatik 6 should provide a guide as to what appropriate notation should look like.
  
• Tables must have titles (appearing above the table).
• Figures must have captions (appearing below the figure).
  
• In the case that no adequate translation of an English technical term is available, the term should be used unchanged.
• Articles and presentation slides can also be prepared in English.
  
• Completeness: acknowledge all literature and sources.
  
• Referencing must conform to the standard described in the article template.
• Examples should be used to illustrate points.
• Examples should be as complex as necessary but as simple as possible.
• Slides should be used as presentation aids and not to replace the role of the presenter; specifically, slides should:
• illustrate important points and relationships;
• remind the audience (and the presenter) of important aspects and considerations;
  
• give the audience an overview of the presentation.
  
• Slides should not contain chunks of text or complicated sentences; rather they should consist of succinct words and terms.
• Use illustrations where appropriate - a picture says a thousand words!
• Abbreviations should be defined at the first usage in the manner demonstrated in the following example: "[...] at the Rheinisch-Westfälischen Technischen Hochschule (RWTH) there are [...]".
  
• Take care to stay within your own topic. To this end participants should be aware of the other topics in the seminar. If applicable, cross-reference other articles and presentations.
• Usage of fonts, typefaces and colors in presentation slides must be consistent and appropriate. Such means should serve to clarify points or relationships, not be applied needlessly or at random.
  
• Care should be taken when selecting fonts for presentation slides (also within diagrams) to ensure legibility on a projector even for those seated far from the screen.

Contact

Dr. Ralf Schlüter
RWTH Aachen
Lehrstuhl für Informatik 6
Ahornstr. 55
52056 Aachen

Raum 6125b
Telefon: 0241 / 80-21612

E-Mail: schlueter@cs.rwth-aachen.de

Last modified: 2013-07-08 15:29:19 Disclaimer.