Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization

The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization.

Single Shot Reversible GAN for BCG artifact removal in simultaneous EEG-fMRI

Simultaneous EEG-fMRI acquisition and analysis technology has been widely used in various research fields of brain science. However, how to remove the ballistocardiogram (BCG) artifacts in this scenario remains a huge challenge. Because it is impossible to obtain clean and BCG-contaminated EEG signals at the same time, BCG artifact removal is a typical unpaired signal-to-signal problem. To solve this problem, this paper proposed a new GAN training model - Single Shot Reversible GAN (SSRGAN). The model is allowing bidirectional input to better combine the characteristics of the two types of signals, instead of using two independent models for bidirectional conversion as in the past. Furthermore, the model is decomposed into multiple independent convolutional blocks with specific functions. Through additional training of the blocks, the local representation ability of the model is improved, thereby improving the overall model performance. Experimental results show that, compared with existing methods, the method proposed in this paper can remove BCG artifacts more effectively and retain the useful EEG information.

Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation

In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality.

Finding Action Tubes with a Sparse-to-Dense Framework

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatiotemporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor.

CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization. In this paper, we propose Coarse-to-Fine Action Detector (CFAD),an original end-to-end trainable framework for efficient spatio-temporal action localization. The CFAD introduces a new paradigm that first estimates coarse spatio-temporal action tubes from video streams, and then refines the tubes location based on key timestamps. This concept is implemented by two key components, the Coarse and Refine Modules in our framework. The parameterized modeling of long temporal information in the Coarse Module helps obtain accurate initial tube estimation, while the Refine Module selectively adjusts the tube location under the guidance of key timestamps. Against other methods, theproposed CFAD achieves competitive results on action detection benchmarks of UCF101-24, UCFSports and JHMDB-21 with inference speed that is 3.3x faster than the nearest competitors.

The short-term seasonal analyses between atmospheric environment and COVID-19 in epidemic areas of Cities in Australia, South Korea, and Italy

The impact of the outbreak of COVID-19 on health has been widely concerned. Disease risk assessment, prediction, and early warning have become a significant research field. Previous research suggests that there is a relationship between air quality and the disease. This paper investigated the impact of the atmospheric environment on the basic reproduction number (R$_0$) in Australia, South Korea, and Italy by using atmospheric environment data, confirmed case data, and the distributed lag non-linear model (DLNM) model based on Quasi-Poisson regression. The results show that the air temperature and humidity have lag and persistence on short-term R$_0$, and seasonal factors have an apparent decorating effect on R$_0$. PM$_{10}$ is the primary pollutant that affects the excess morbidity rate. Moreover, O$_3$, PM$_{2.5}$, and SO$_2$ as perturbation factors have an apparent cumulative effect. These results present beneficial knowledge for correlation between environment and COVID-19, which guiding prospective analyses of disease data.

TRP: Trained Rank Pruning for Efficient Deep Neural Networks

To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pretrained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. As a result, performance usually drops significantly and a sophisticated effort on fine-tuning is required to recover accuracy. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. TRP maintains the capacity of the original network while imposing low-rank constraints during training. A nuclear regularization optimized by stochastic sub-gradient descent is utilized to further promote low rank in TRP. The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression methods using low rank approximation.

A knowledge transfer model for COVID-19 predicting and non-pharmaceutical intervention simulation

Since December 2019, A novel coronavirus (2019-nCoV) has been breaking out in China, which can cause respiratory diseases and severe pneumonia. Mathematical and empirical models relying on the epidemic situation scale for forecasting disease outbreaks have received increasing attention. Given its successful application in the evaluation of infectious diseases scale, we propose a Susceptible-Undiagnosed-Infected-Removed (SUIR) model to offer the effective prediction, prevention, and control of infectious diseases. Our model is a modified susceptible-infected-recovered (SIR) model that injects undiagnosed state and offers pre-training effective reproduction number. Our SUIR model is more precise than the traditional SIR model. Moreover, we combine domain knowledge of the epidemic to estimate effective reproduction number, which addresses the initial susceptible population of the infectious disease model approach to the ground truth. These findings have implications for the forecasting of epidemic trends in COVID-19 as these could help the growth of estimating epidemic situation.

Ask2Me VarHarmonizer: A Python-Based Tool to Harmonize Variants from Cancer Genetic Testing Reports and Map them to the ClinVar Database

PURPOSE: The popularity of germline genetic panel testing has led to a vast accumulation of variant-level data. Variant names are not always consistent across laboratories and not easily mappable to public variant databases such as ClinVar. A tool that can automate the process of variants harmonization and mapping is needed to help clinicians ensure their variant interpretations are accurate. METHODS: We present a Python-based tool, Ask2Me VarHarmonizer, that incorporates data cleaning, name harmonization, and a four-attempt mapping to ClinVar procedure. We applied this tool to map variants from a pilot dataset collected from 11 clinical practices. Mapping results were evaluated with and without the transcript information. RESULTS: Using Ask2Me VarHarmonizer, 4728 out of 6027 variant entries (78%) were successfully mapped to ClinVar, corresponding to 3699 mappable unique variants. With the addition of 1099 unique unmappable variants, a total of 4798 unique variants were eventually identified. 427 (9%) of these had multiple names, of which 343 (7%) had multiple names within-practice. 99% mapping consistency was observed with and without transcript information. CONCLUSION: Ask2Me VarHarmonizer aggregates and structures variant data, harmonizes names, and maps variants to ClinVar. Performing harmonization removes the ambiguity and redundancy of variants from different sources.

Trained Rank Pruning for Efficient Deep Neural Networks

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. TRP maintains the capacity of the original network while imposing low-rank constraints during training. A nuclear regularization optimized by stochastic sub-gradient descent is utilized to further promote low rank in TRP. Networks trained with TRP has a low-rank structure in nature, and is approximated with negligible performance loss, thus eliminating fine-tuning after low rank approximation. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression counterparts using low rank approximation. Our code is available at: https://github.com/yuhuixu1993/Trained-Rank-Pruning.