Learning fine-grained interplay between vision and language contributes to a more accurate understanding for Vision-Language tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing works are either limited by text-agnostic and redundant regions obtained with the frozen region proposal module, or failing to scale further due to their heavy reliance on scarce grounding (gold) data to pre-train detectors. To solve these problems, we propose Self-Locator Aided Network (SLAN) for vision-language understanding tasks without any extra gold data. SLAN consists of a region filter and a region adaptor to localize regions of interest conditioned on different texts. By aggregating vision-language information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance. With detailed region-word alignments, SLAN can be easily generalized to many downstream tasks. It achieves fairly competitive results on five vision-language understanding tasks (e.g., 85.7% and 69.2% on COCO image-to-text and text-to-image retrieval, surpassing previous SOTA methods). SLAN also demonstrates strong zero-shot and fine-tuned transferability to two localization tasks. The code is available at https://github.com/scok30/SLAN.

For multichannel speech recognition systems, it is necessary to use a speech enhancement module to suppress ambient noises. Given second-order statistics, the multichannel Wiener filter (MWF) can be designed for noise reduction. It was shown that the MWF noise reduction performance depends on the selection of reference microphone and the rank of the speech correlation matrix. It is questionable how the reference microphone and rank would affect the subsequent recognition accuracy. In this paper, we present an experimental study on the low-rank approximation and reference microphone selection based MWF with application to noisy speech recognition. Further, we propose to maximize the input signal-to-noise ratio (SNR) for reference selection in the sense of signal quality. Experimental results show that the output SNR of rank-1 MWF is independent of the reference, while the speech intelligibility is always related to both the rank and reference microphone. The word error rate is positively affected by the rank, and the proposed reference selection method can improve the performance in terms of both speech intelligibility and speech recognition.

A rapid-accurate detection method for COVID-19 is rather important for avoiding its pandemic. In this work, we propose a bi-directional long short-term memory (BiLSTM) network based COVID-19 detection method using breath/speech/cough signals. Three kinds of acoustic signals are taken to train the network and individual models for three tasks are built, respectively, whose parameters are averaged to obtain an average model, which is then used as the initialization for the BiLSTM model training of each task. It is shown that such an initialization method can significantly improve the detection performance on three tasks. This is called supervised pre-training based detection. Besides, we utilize an existing pre-trained wav2vec2.0 model and pre-train it using the DiCOVA dataset, which is utilized to extract a high-level representation as the model input to replace conventional mel-frequency cepstral coefficients (MFCC) features. This is called self-supervised pre-training based detection. To reduce the information redundancy contained in the recorded sounds, silent segment removal, amplitude normalization and time-frequency masking are also considered. The proposed detection model is evaluated on the DiCOVA dataset and results show that our method achieves an area under curve (AUC) score of 88.44% on blind test in the fusion track. It is shown that using high-level features together with MFCC features is helpful for diagnosing accuracy.

Threshold quantum secret sharing schemes are incredibly complex systems, making even constructed schemes so complicated as to be very difficult to implement. In addition, most of these schemes share classical information rather than true quantum information. Weighted threshold quantum secret sharing schemes are especially complex, so much so that, to date, no one has been able to successfully construct one. In light of this, this study uses the Chinese Remainder Theorem and performs the phase shift operation on a quantum state to build a weighted threshold secret sharing scheme. The proposed scheme allocates each participant in the scheme their own weight. The dealer then selects a key and encodes it on a secret of quantum state with the phase shift operation. One this is achieved, the dealer divides the key into partial keys, and sends them to the participants. When the sum of the weights of participants is greater than or equal to a fixed threshold, the participants can reconstruct the secret and obtain the quantum information. The proposed scheme is an efficient and flexible weighted threshold quantum secret sharing and is simpler and easier to implement than earlier ones.

To satisfy the quality of service requirements of various electricity information interactive applications in power fiber to the home network, we propose a QoS-based optical network unit group planning algorithm. This method uses several ONUs to converge data from all kinds of sensors in a network and then transmit it to OLT through the optical fiber composite low-voltage cable. Process of this method is divided into two stages. First, based on QoS requirements of a network including packet delay, packet error probability and packet loss rate, the number of ONUs in a certain area is solved by a series of mathematical methods such as queuing theory. Then, locations of ONUs are planned by using a tabu-search-algorithm-based ONU location planning method to achieve the lowest power consumption of ONUs. Evaluation results show that our proposed method can guarantee QoS of a network and reduce total power consumption effectively.

Drivers dream of foreseeing traffic condition to enjoy efficient driving experience at all times. Given the historical patterns for different locations and different time, people should be able to guess the possible traffic speed in a near future moment. What is difficult and interesting for this task is that we need to filter the useful data that could help us for the next moment traffic speed prediction from a massive amount of historical data. On the other hand, the traffic condition could be highly dynamic and we can only give a reliable traffic prediction by using the most updated model for prediction. This implies that frequent retraining is necessary. To conquer the task, we propose a lazy learning approach for traffic speed prediction given massive historical data. The approach integrates the kNN and Gaussian process regression for efficient and robust traffic speed prediction. kNN can help us to select the most informative data for Gaussian process Regression using a big data framework. Thanks for the most recent progress of big data research, the processing of massive data for prediction in close to real time has become possible now compared to any time in the past. We aim at using a Hadoop framework for the prediction given heterogeneous data including traffic data such as speed, flow, occupancy, and weather data.