Zobrazeno 1 - 10
of 286
pro vyhledávání: '"Tamošiūnaitė, A."'
Autor:
Ziaeetabar, Fatemeh, Safabakhsh, Reza, Momtazi, Saeedeh, Tamosiunaite, Minija, Wörgötter, Florentin
Automatic video description requires the generation of natural language statements about the actions, events, and objects in the video. An important human trait, when we describe a video, is that we are able to do this with variable levels of detail.
Externí odkaz:
http://arxiv.org/abs/2311.07285
Autor:
Ziaeetabar, Fatemeh, Safabakhsh, Reza, Momtazi, Saeedeh, Tamosiunaite, Minija, Wörgötter, Florentin
Nuanced understanding and the generation of detailed descriptive content for (bimanual) manipulation actions in videos is important for disciplines such as robotics, human-computer interaction, and video content analysis. This study describes a novel
Externí odkaz:
http://arxiv.org/abs/2310.00670
Traditional AI-planning methods for task planning in robotics require a symbolically encoded domain description. While powerful in well-defined scenarios, as well as human-interpretable, setting this up requires substantial effort. Different from thi
Externí odkaz:
http://arxiv.org/abs/2211.08321
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems, 2023
Finding optimal paths in connected graphs requires determining the smallest total cost for traveling along the graph's edges. This problem can be solved by several classical algorithms where, usually, costs are predefined for all edges. Conventional
Externí odkaz:
http://arxiv.org/abs/2201.11104
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems, 2022
The question how neural systems (of humans) can perform reasoning is still far from being solved. We posit that the process of forming Concepts is a fundamental step required for this. We argue that, first, Concepts are formed as closed representatio
Externí odkaz:
http://arxiv.org/abs/2110.13665
Autor:
Selvan, Rosari Naveena, Cheng, Minghao, Siestrup, Sophie, Mecklenbrauck, Falko, Jainta, Benjamin, Pomp, Jennifer, Zahedi, Anoushiravan, Tamosiunaite, Minija, Wörgötter, Florentin, Schubotz, Ricarda I.
Publikováno v:
In NeuroImage 1 August 2024 296
Autor:
Ziaeetabar, Fatemeh, Pomp, Jennifer, Pfeiffer, Stefan, El-Sourani, Nadiya, Schubotz, Ricarda I., Tamosiunaite, Minija, Wörgötter, Florentin
Predicting other people's action is key to successful social interactions, enabling us to adjust our own behavior to the consequence of the others' future actions. Studies on action recognition have focused on the importance of individual visual feat
Externí odkaz:
http://arxiv.org/abs/2004.10518
Publikováno v:
22nd International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2013), September 11-13, 2013, Portoroz, Slovenia
Generalization in robotics is one of the most important problems. New generalization approaches use internet databases in order to solve new tasks. Modern search engines can return a large amount of information according to a query within millisecond
Externí odkaz:
http://arxiv.org/abs/2004.02607
Autor:
Kulvicius, Tomas, Herzog, Sebastian, Lüddecke, Timo, Tamosiunaite, Minija, Wörgötter, Florentin
Publikováno v:
The 3rd International Symposium on Swarm Behavior and Bioinspired Robotics (SWARM 2019), November 20-22, Okinawa, Japan
Path planning plays a crucial role in robot action execution, since a path or a motion trajectory for a particular action has to be defined first before the action can be executed. Most of the current approaches are iterative methods where the trajec
Externí odkaz:
http://arxiv.org/abs/2004.00568
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems, 2022
Trajectory- or path-planning is a fundamental issue in a wide variety of applications. Here we show that it is possible to solve path planning for multiple start- and end-points highly efficiently with a network that consists only of max pooling laye
Externí odkaz:
http://arxiv.org/abs/2004.00540