SPS Feed

Retrieving specific persons with various types of queries, e.g., a set of attributes or a portrait photo has great application potential in large-scale intelligent surveillance systems. In this paper, we propose a richly annotated pedestrian (RAP) dataset which serves as a unified benchmark for both attribute-based and image-based person retrieval in real surveillance scenarios.

Zero-shot learning (ZSL) for visual recognition aims to accurately recognize the objects of unseen classes through mapping the visual feature to an embedding space spanned by class semantic information. However, the semantic gap across visual features and their underlying semantics is still a big obstacle in ZSL. Conventional ZSL methods construct that the mapping typically focus on the original visual features that are independent of the ZSL tasks, thus degrading the prediction performance.

Recently, nested and coprime arrays have attracted considerable interest due to their capability of providing increased array aperture, enhanced degrees of freedom (DOFs), and reduced mutual coupling effect compared to uniform linear arrays (ULAs). These features are critical to improving the performance of direction-of-arrival estimation and adaptive beamforming. 

The state-of-the-art graph wavelet decomposition was constructed by maximum spanning tree (MST)-based downsampling and two-channel graph wavelet filter banks. In this work, we first show that: 1) the existing MST-based downsampling could become unbalanced, i.e., the sampling rate is far from 1/2, which eventually leads to low representation efficiency of the wavelet decomposition; and 2) not only low-pass components, but also some high-pass ones can be decomposed to potentially achieve better decomposition performance.