Feng Wu

TL;DR: This paper investigates how to generate RIP (restricted isometry property) preserving measurements of sensor readings by taking multi-hop communication cost into account and discovers that a simple form of measurement matrix has good RIP, and the data gathering scheme that realizes this measurement matrix can further reduce the communication cost of CDG for both chain-type and tree-type topology.

TL;DR: In this article, a Variable-filter-size Residue-learning CNN (VRCNN) was proposed to improve the performance and to accelerate network training for High Efficiency Video Coding.

TL;DR: Wang et al. as discussed by the authors proposed a Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoder-decoder architecture, including a pixel context based transformer and a part prototype based transformer decoder.

TL;DR: In this article, a deep neural network (DNN) based power control method that aims at solving the non-convex optimization problem of maximizing the sum rate of a fading multi-user interference channel is proposed.

TL;DR: This work designs a novel cross-attention mechanism, which is able to exploit not only the intra-modality relationship within each modality, but also the inter- modality relationship between image regions and sentence words to complement and enhance each other for image and sentence matching.