We present an interactive, hybrid human-computer method for object classification. The method applies to classes of objects that are recognizable by people with appropriate expert...
In this paper, we propose a general framework for fusing bottom-up segmentation with top-down object behavior classification over an image sequence. This approach is beneficial fo...
One of the major difficulties when applying Multiobjective Evolutionary Algorithms (MOEA) to real world problems is the large number of objective function evaluations. Approximate...
We introduce a new concept of co-recognition for object-level image matching between an arbitrary image pair. Our method augments putative local regionmatches to reliable object-...
Minsu Cho (Seoul National University), Young Min S...
The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...