We develop a two stage split vector quantization method with optimum bit allocation, for achieving minimum computational complexity. This also results in much lower memory requirement than the recently proposed switched split vector quantization method. To improve the rate-distortion performance further, a region specific normalization is introduced, which results in 1 bit/vector improvement ov...

This report presents some results and findings of our work on very-lowbit-rate video compression systems using vector quantization (VQ). We have identified multiscale segmentation and variable-rate coding as two important concepts whose effective use can lead to superior compression performance. Two VQ algorithms that attempt to use these two aspects are presented: one based on residual vector ...

With the purpose of learning and utilizing explicit dense topic embeddings, we propose three variations novel vector-quantization-based models (VQ-TMs): (1) Hard VQ-TM, (2) Soft (3) Multi-View VQ-TM. The model family capitalize on vector quantization techniques, embedded input documents, viewing words as mixtures topics. Guided by a comprehensive set evaluation metrics, conduct systematic quant...

Classifying large datasets without any a priori information poses a problem especially in the field of bioinformatics. In this work, we explore the problem of classifying hundreds of thousands of cell assay images obtained by a high-throughput screening camera. The goal is to label a few selected examples by hand and to automatically label the rest of the images afterwards. Up to now, such imag...