arXiv subjects

Haoming Chen

Publications and source records attributed to Haoming Chen.

21 records · Page 2Linked to original sources

arXiv2021

CXR-Net: An Encoder-Decoder-Encoder Multitask Deep Neural Network for Explainable and Accurate Diagnosis of COVID-19 pneumonia with Chest X-ray Images

Accurate and rapid detection of COVID-19 pneumonia is crucial for optimal patient treatment. Chest X-Ray (CXR) is the first line imaging test for COVID-19 pneumonia diagnosis as it is fast, cheap and easily accessible. Inspired by the success of deep learning (DL) in computer vision, many DL-models have been proposed to detect COVID-19 pneumonia using CXR images. Unfortunately, these deep classifiers lack the transparency in interpreting findings, which may limit their applications in clinical practice. The existing commonly used visual explanation methods are either too noisy or imprecise, with low resolution, and hence are unsuitable for diagnostic purposes. In this work, we propose a novel explainable deep learning framework (CXRNet) for accurate COVID-19 pneumonia detection with an enhanced pixel-level visual explanation from CXR images. The proposed framework is based on a new Encoder-Decoder-Encoder multitask architecture, allowing for both disease classification and visual explanation. The method has been evaluated on real world CXR datasets from both public and private data sources, including: healthy, bacterial pneumonia, viral pneumonia and COVID-19 pneumonia cases The experimental results demonstrate that the proposed method can achieve a satisfactory level of accuracy and provide fine-resolution classification activation maps for visual explanation in lung disease detection. The Average Accuracy, the Precision, Recall and F1-score of COVID-19 pneumonia reached 0.879, 0.985, 0.992 and 0.989, respectively. We have also found that using lung segmented (CXR) images can help improve the performance of the model. The proposed method can provide more detailed high resolution visual explanation for the classification decision, compared to current state-of-the-art visual explanation methods and has a great potential to be used in clinical practice for COVID-19 pneumonia diagnosis.

eess.IV↗

arXiv2021

Deep Dual Consecutive Network for Human Pose Estimation

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to video sequences. Prevalent shortcomings include the failure to handle motion blur, video defocus, or pose occlusions, arising from the inability in capturing the temporal dependency among video frames. On the other hand, directly employing conventional recurrent neural networks incurs empirical difficulties in modeling spatial contexts, especially for dealing with pose occlusions. In this paper, we propose a novel multi-frame human pose estimation framework, leveraging abundant temporal cues between video frames to facilitate keypoint detection. Three modular components are designed in our framework. A Pose Temporal Merger encodes keypoint spatiotemporal context to generate effective searching scopes while a Pose Residual Fusion module computes weighted pose residuals in dual directions. These are then processed via our Pose Correction Network for efficient refining of pose estimations. Our method ranks No.1 in the Multi-frame Person Pose Estimation Challenge on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018. We have released our code, hoping to inspire future research.

cs.CV↗

arXiv2015

On Intra Prediction for Screen Content Video Coding

Screen content coding (SCC) is becoming increasingly important in various applications, such as desktop sharing, video conferencing, and remote education. When compared to natural camera- captured content, screen content has different characteristics, in particular sharper edges. In this paper, we propose a novel intra prediction scheme for screen content video. In the proposed scheme, bilinear interpolation in angular intra prediction in HEVC is selectively replaced by nearest-neighbor intra prediction to preserve the sharp edges in screen content video. We present three different variants of the proposed nearest neighbor prediction algorithm: two implicit methods where both the encoder, and the decoder derive whether to perform nearest neighbor prediction or not based on either (a) the sum of the absolute difference, or (b) the difference between the boundary pixels from which prediction is performed; and another variant where Rate-Distortion-Optimization (RDO) search is performed at the encoder to decide whether or not to use the nearest neighbor interpolation, and explicitly signaled to the decoder. We also discuss the various underlying trade-offs in terms of the complexity of the three variants. All the three proposed variants provide significant gains over HEVC, and simulation results show that average gains of 3.3% BD-bitrate in Intra-frame coding are achieved by the RDO variant for screen content video. To the best of our knowledge, this is the first paper that 1) points out current HEVC intra prediction scheme with bilinear interpolation does not work efficiently for screen content video and 2) uses different filters adaptively in the HEVC intra prediction interpolation.

cs.GR↗