Visual codebook has been popular in object classification as well as action analysis. However, its performance is often sensitive to the codebook size that is usually predefined. ...
Computing the pairwise semantic similarity between all words on the Web is a computationally challenging task. Parallelization and optimizations are necessary. We propose a highly...
Patrick Pantel, Eric Crestan, Arkady Borkovsky, An...
To tackle the vocabulary problem in conversational systems, previous work has applied unsupervised learning approaches on co-occurring speech and eye gaze during interaction to au...
Recent research effort in Content-Based Image Retrieval (CBIR) focuses on bridging the gap between low-level features and highlevel semantic contents of images as this gap has bec...
Mei-Ling Shyu, Shu-Ching Chen, Min Chen, Chengcui ...
There is a number of recent research lines addressing complex negotiations in highly rugged utility spaces. However, most of them focus on overcoming the problems imposed by the c...