This paper considers the problem of designing an active observer to plan a sequence of decisions regarding what target to look at, through a foveal-sensing action. We propose a fr...
Most P2P VoD schemes focused on service architectures and overlays optimization without considering segments rarity and the performance of prefetching strategies. As a result, the...
Object/scene detection by discriminative kernel-based classification has gained great interest due to its promising performance and flexibility. In this paper, unlike traditional ...
— This video presents a humanoid two-arm system developed as a research platform for studying dexterous twohanded manipulation. The system is based on the modular DLR-Lightweight...
In this paper, we exploit the problem of inferring images’ semantic concepts from community-contributed images and their associated noisy tags. To infer the concepts more accura...