In this paper, an algorithm named stepwise subspace pursuit (SSP) is proposed for sparse signal recovery. Unlike existing algorithms that select support set from candidate sets directly, our approach eliminates useless information from the candidate through threshold processing at first and then recovers the signal through the largest correlation coefficients. We demonstrate that SSP significantly outperforms conventional techniques in recovering sparse signals whose nonzero values have exponentially decaying magnitudes or distribution of (0, 1). Experimental results of Lena show that SSP is better than CoSaMP, OMP, and SP in terms of peak signal to noise ratio (PSNR) by 5.5 db, 4.1 db, and 4.2 db, respectively.

In this paper, an algorithm named best wavelet packet tree decomposition (BWPTD) is proposed for image compression. In order to obtain better sparse representation of image, best wavelet packet basis is introduced to decompose image signal in the algorithm. Experimental results show that BWPTD is better than single layer wavelet decompression (SLWD) and original compressed sensing (OCS) in peak signal to noise ratio (PSNR) by 2db and 8db, respectively. In addition, the reconstruction time of BWPTD is only half as that of SLWD and OCS.

No abstract

No abstract

Cross-Lingual Summarization (CLS) is the task to generate a summary in one language for an article in a different language. Previous studies on CLS mainly take pipeline methods or train the end-to-end model using the translated parallel data. However, the quality of generated cross-lingual summaries needs more further efforts to improve, and the model performance has never been evaluated on the hand-written CLS dataset. Therefore, we first propose a clue-guided cross-lingual abstractive summarization method to improve the quality of cross-lingual summaries, and then construct a novel hand-written CLS dataset for evaluation. Specifically, we extract keywords, named entities, etc. of the input article as key clues for summarization and then design a clue-guided algorithm to transform an article into a graph with less noisy sentences. One Graph encoder is built to learn sentence semantics and article structures and one Clue encoder is built to encode and translate key clues, ensuring the information of important parts are reserved in the generated summary. These two encoders are connected by one decoder to directly learn cross-lingual semantics. Experimental results show that our method has stronger robustness for longer inputs and substantially improves the performance over the strong baseline, achieving an improvement of 8.55 ROUGE-1 (English-to-Chinese summarization) and 2.13 MoverScore (Chinese-to-English summarization) scores over the existing SOTA.