CRC-Aided Sparse Regression Codes for Unsourced Random Access.

Spatial-temporal injection network: exploiting auxiliary losses for action recognition with apparent difference and self-attention.

Using List Decoding to Improve the Finite-Length Performance of Sparse Regression Codes.

Dual-View Semantic Inference Network for image-text matching.

Multi-Attention Generative Adversarial Network for image captioning.

Hierarchical Attention-Based Fusion for Image Caption With Multi-Grained Rewards.

Refined Spatial Network for Human Action Recognition.