Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to human and -as usual -before being processed/analyzed by machine vision algorithms. For machine vision, it is more efficient at least conceptually, to process/analyze the coded representations directly without decoding them into pixels. Motivated by this concept, we propose a learned versatile video coding (LVVC) framework, which targets on learning compact representations to support both decoding and direct processing/analysis, thereby being versatile for both human and machine vision. Our LVVC framework has a feature-based compression loop, where one frame is encoded (resp. decoded) to intermediate features, and the intermediate features are referenced for encoding (resp. decoding) the following frames. Our proposed feature-based compression loop has two key technologies, one is feature-based temporal context mining, and the other is cross-domain motion encoder/decoder. With the LVVC framework, the intermediate features may be used to reconstruct videos, or be fed into different task networks. The LVVC framework is implemented and evaluated with video reconstruction, video processing, and video analysis tasks on the well-established benchmark datasets. The evaluation results demonstrate the compression efficiency of the proposed LVVC framework.

No abstract

No abstract

We address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. For temporal context mining, we propose to store not only the previously reconstructed frames, but also the propagated features into the generalized decoded picture buffer. From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder. Our scheme discards the parallelization-unfriendly auto-regressive entropy model to pursue a more practical decoding time. We compare our scheme with x264 and x265 (representing industrial software for H.264 and H.265, respectively) as well as the official reference software for H. 264, H.265, and H.266 (JM, HM, and VTM, respectively). When intra period is 32 and oriented to PSNR, our scheme outperforms H.265-HM by 14.4% bit rate saving; when oriented to MS-SSIM, our scheme outperforms H.266-VTM by 21.1% bit rate saving.

Purpose This study aims to investigate the prognostic value of the peripheral neutrophil-to-lymphocyte ratio (NLR) in patients with chronic internal carotid artery occlusion (CICAO) complicated by cerebral infarction. Patients and Methods The clinical data of 99 CICAO patients complicated by cerebral infarction were retrospectively analyzed. The modified Rankin Scale (mRS) was used to assess their 3-month prognosis, and a multivariate logistic regression model was established to explore risk factors for poor prognosis. Results Multivariate logistic regression analysis demonstrated that NLR (OR=2.114; 95% CI: 1.129–3.959) and baseline National Institute of Health Stroke Scale (NIHSS; OR=1.288, 95% CI: 1.053–1.574) score were risk factors of poor prognosis. The area under the receiver operator characteristic (ROC) curve of NLR in predicting the 3-month outcome after onset was 0.717 (95% CI: 0.606–0.828, P <0.000). The optimal cut-off value was 3.22, with a sensitivity of 0.743 and a specificity of 0.791. Conclusion NLR is an independent risk factor for the poor prognosis of CICAO patients complicated by cerebral infarction and can serve as an indicator for clinical prognosis.