The Joint Submission of the TU Berlin and Fraunhofer FIRST (TUBFI) to the ImageCLEF2011 Photo Annotation Task
نویسندگان
چکیده
In this paper we present details on the joint submission of TU Berlin and Fraunhofer FIRST to the ImageCLEF 2011 Photo Annotation Task. We sought to experiment with extensions of Bag-of-Words (BoW) models at several levels and to apply several kernel-based learning methods recently developed in our group. For classifier training we used non-sparse multiple kernel learning (MKL) and an efficient multi-task learning (MTL) heuristic based on MKL over kernels from classifier outputs. For the multi-modal fusion we used a smoothing method on tag-based features inspired by Bag-of-Words soft mappings and Markov random walks. We submitted one multi-modal run extended by the user tags and four purely visual runs based on Bag-of-Words models. Our best visual result which used the MTL method was ranked first according to mean average precision (MAP) within the purely visual submissions. Our multi-modal submission achieved the first rank by MAP among the multi-modal submissions and the best MAP among all submissions. Submissions by other groups such as BPACAD, CAEN, UvA-ISIS, LIRIS were ranked closely.
منابع مشابه
Fraunhofer FIRST's Submission to ImageCLEF2009 Photo Annotation Task: Non-sparse Multiple Kernel Learning
In order to achieve good performance in image annotation tasks, it is necessary to combine information from various image features. In our submission, we applied the nonsparse multiple kernel learning for feature combination proposed by Kloft et al.(2009) to the ImageCLEF2009 photo annotation data. Since some of the concepts of the ImageCLEF task are rather abstract, we conjectured that color h...
متن کاملThe Fraunhofer IDMT at ImageCLEF 2011 Photo Annotation Task
This paper presents the participation of the Fraunhofer IDMT in the ImageCLEF 2011 Photo Annotation Task. Our approach is focused on text-based features and strategies to combine visual and textual information. First, we apply a pre-processing step on the provided Flickr tags to reduce noise. For each concept, tf-idf values per tag are computed and used to construct a text-based descriptor. Sec...
متن کاملAnnotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation
We describe systems we developed and submitted to ImageCLEF2011. These systems are applied to the confabulation model which is based on the human brain structure and are used for image recognition and retrieval. Simply put, these systems involve the co-occurrence of visual words. The visual words approach has recently become a focus of attention in the field of image recognition. We propose a n...
متن کاملAnalyzing the Impact of Service Accessibility Enhancement on Urban Energy Efficiency Based on GIS Network Analysis
متن کامل
Modellierung geschirmter Leistungskabel im Frequenzbereich der EMV
Stefan-Peter Weber, Leistungselektronik und EMV, Fraunhofer IZM, Berlin André Linde, Student der Elektrotechnik, TU Berlin Dr. Eckart Hoene, Leistungselektronik und EMV, Fraunhofer IZM, Berlin Dr. Stephan Guttowski, Advanced System Development, Fraunhofer IZM, Berlin Werner John, Advanced System Engineering, Fraunhofer IZM, Paderborn Prof. Dr.-Ing. Dr. E.h. Herbert Reichl, FSP Technologien der ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011