In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...

Abstract: Graph Convolution Networks (GCNs) have achieved remarkable success in representation of structured graph data. As we know that traditional GCNs are generally defined on the fixed first-order ...

Imagine Jo: Everyone in Jo's life recognizes her as an outstanding problem solver. She's the type of person who seems capable of almost anything. Jo excels at intuitive problem-solving. Over her life, ...

Abstract: This work investigates the problem of efficiently learning discriminative low-dimensional (LD) representations of multiclass image objects. We propose a generic end-to-end approach that ...