%0 Book Section %1 HerzogRohr95KI %A Herzog, Gerd %A Rohr, Karl %B KI-95: Advances in Artificial Intelligence, 19th Annual German Conference on Artificial Intelligence, Bielefeld, Germany %C Berlin %D 1995 %E Wachsmuth, Ipke %E Rollinger, Claus-Rainer %E Brauer, Wilfried %I Springer %K 01624 springer paper ai language processing image video analysis action recognition zzz.vitra %P 257--268 %R 10.1007/3-540-60343-3_42 %T Integrating Vision and Language: Towards Automatic Description of Human Movements %V 981 %X The integration of vision and natural language processing increasingly attracts attention in different areas of AI research. Up to now, however, there have only been a few attempts at connecting vision systems with natural language access systems. Within the SFB 314, special collaborative program on AI and knowledge-based systems, the automatic natural language description of real world image sequences constitutes a major research goal, which has been pursued during the last ten years. The aim of our approach is to obtain an incremental evaluation and simultaneous description of the perceived time-varying scenes. In this contribution we will report on new results of our joint efforts at combining the natural language access system Vitra with a vision system. We have investigated the problem of describing the movements of articulated bodies in image sequences within an integrated natural language and computer vision system. The paper will focus on our model-based approach for the recognition of pedestrians and on the further evaluation and language production in Vitra. %@ 978-3-540-60343-6

@incollection{HerzogRohr95KI, abstract = {The integration of vision and natural language processing increasingly attracts attention in different areas of AI research. Up to now, however, there have only been a few attempts at connecting vision systems with natural language access systems. Within the SFB 314, special collaborative program on AI and knowledge-based systems, the automatic natural language description of real world image sequences constitutes a major research goal, which has been pursued during the last ten years. The aim of our approach is to obtain an incremental evaluation and simultaneous description of the perceived time-varying scenes. In this contribution we will report on new results of our joint efforts at combining the natural language access system Vitra with a vision system. We have investigated the problem of describing the movements of articulated bodies in image sequences within an integrated natural language and computer vision system. The paper will focus on our model-based approach for the recognition of pedestrians and on the further evaluation and language production in Vitra.}, added-at = {2016-09-24T14:21:06.000+0200}, address = {Berlin}, author = {Herzog, Gerd and Rohr, Karl}, biburl = {https://www.bibsonomy.org/bibtex/27c769429f1158c5724876a2515945245/flint63}, booktitle = {KI-95: Advances in Artificial Intelligence, 19th Annual German Conference on Artificial Intelligence, Bielefeld, Germany}, crossref = {KI1995}, doi = {10.1007/3-540-60343-3_42}, editor = {Wachsmuth, Ipke and Rollinger, Claus-Rainer and Brauer, Wilfried}, file = {SpringerLink:1900-99/HerzogRohr95KI.pdf:PDF}, groups = {public}, interhash = {e048bce5fa22c1c6b51cb9f22415157a}, intrahash = {7c769429f1158c5724876a2515945245}, isbn = {978-3-540-60343-6}, issn = {1431-472X}, keywords = {01624 springer paper ai language processing image video analysis action recognition zzz.vitra}, pages = {257--268}, publisher = {Springer}, series = {Lecture Notes in Artificial Intelligence}, timestamp = {2017-07-13T17:38:03.000+0200}, title = {Integrating Vision and Language: Towards Automatic Description of Human Movements}, username = {flint63}, volume = 981, year = 1995 }