Unsupervised discovery of acoustic tokens from audio corpora without annotation and learning vector representations for these tokens have been widely studied. Although these techniques have been shown successful in some applications such as query-byexample Spoken Term Detection (STD), the lack of mapping relationships between these discovered tokens and real phonemes have limited the down-strea...

This position paper deals with queries beyond text, mixing several multimedia contents: audio, video, image and text. Search approaches combining some of these formats have been studied, including query by example techniques in situations where only one format is considered. It is worth mentioning that most of these research works do not deal with text content. A new approach to allow users int...

Programming-by-example technologies let end users construct and run new programs by providing examples of the intended program behavior. But, the few provided examples seldom uniquely determine the intended program. Previous approaches to picking a program used a bias toward shorter or more naturally structured programs. Our work here gives a machine learning approach for learning to learn prog...

Programming by Example (PBE) targets at automatically inferring a computer program for accomplishing a certain task from sample input and output. In this paper, we propose a deep neural networks (DNN) based PBE model called Neural Programming by Example (NPBE), which can learn from input-output strings and induce programs that solve the string manipulation problems. Our NPBE model has four neur...

In this paper, an image retrieval methodology suited for search in large collections of heterogeneous images is presented. The proposed approach employs a fully unsupervised segmentation algorithm to divide images into regions. Low-level features describing the color, position, size and shape of the resulting regions are extracted and are automatically mapped to appropriate intermediatelevel de...

In this paper, 3D shape retrieval methodology suited for search in special category of 3D shape is presented. The proposed approach employs a fully unsupervised segmentation algorithm to decompose 3D models into components. Shape distribution vectors describing the resulting components are extracted and together with connectivity relations identify a 3D model. The 3D-shapes we are interested in...