Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and complex classifiers that measure similarities between query images but left importance feature embeddings seldom explored. We show reliance sophisticated is not necessary, simple ...

This paper presents a local feature descriptor, the Local Distinctive Star Pattern (LDSP), for facial expression recognition. The feature is obtained from a local 3x3 pixels area by computing the directional edge response value. Each pixel is represented by two 4-bit binary patterns, which is named as LDSP feature for that pixel. Each face is divided into 81 equal sized blocks and histogram of ...

Since the local feature-based methods recognize interior content and utilize the rich information of the sketches and 2D views of 3D model, this paper proposes a novel sketch-based 3D model retrieval algorithm which utilizes local feature descriptors to describe the object shape. Firstly, we propose PCA-DAISY descriptor to create the efficient local feature descriptors. The DAISY descriptor con...

We present a line-scan stereo system and descriptor-based dense stereo matching for highperformance vision applications. The stochastic binary local descriptor (STABLE) descriptor is a local binary descriptor that builds upon the principles of compressed sensing theory. The most important properties of STABLE are the independence of the descriptor length from the matching window size and the po...

Surface registration is the process that brings scans into a common coordinate system by aligning their overlapping components, which can be achieved by finding a few pairs of matched points on each scan pair using shape descriptors and employing the matches to compute an alignment transformation. This paper proposes a local voxelizer descriptor, and the key idea is to define a unique local ref...