arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 1,045 records · Page 58Linked to original sources

arXiv2022

Video-based Cross-modal Auxiliary Network for Multimodal Sentiment Analysis

Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the insufficient unimodal features extraction and data redundancy of multimodal fusion. In this paper, a Video-based Cross-modal Auxiliary Network (VCAN) is proposed, which is comprised of an audio features map module and a cross-modal selection module. The first module is designed to substantially increase feature diversity in audio feature extraction, aiming to improve classification accuracy by providing more comprehensive acoustic representations. To empower the model to handle redundant visual features, the second module is addressed to efficiently filter the redundant visual frames during integrating audiovisual data. Moreover, a classifier group consisting of several image classification networks is introduced to predict sentiment polarities and emotion categories. Extensive experimental results on RAVDESS, CMU-MOSI, and CMU-MOSEI benchmarks indicate that VCAN is significantly superior to the state-of-the-art methods for improving the classification accuracy of multimodal sentiment analysis.

cs.CV↗

arXiv2022

GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals

Towards developing effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by electroencephalogram (EEG), is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and group-wise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet Dataset), 96.24% and 80.89% (High Gamma Dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step towards better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain motor imagery.

eess.SP↗

arXiv2022

Distance-Aware Occlusion Detection with Focused Attention

For humans, understanding the relationships between objects using visual signals is intuitive. For artificial intelligence, however, this task remains challenging. Researchers have made significant progress studying semantic relationship detection, such as human-object interaction detection and visual relationship detection. We take the study of visual relationships a step further from semantic to geometric. In specific, we predict relative occlusion and relative distance relationships. However, detecting these relationships from a single image is challenging. Enforcing focused attention to task-specific regions plays a critical role in successfully detecting these relationships. In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection. Specifically, our model increases the distance F1-score from 33.8% to 38.6% and boosts the occlusion F1-score from 34.4% to 41.2%. Our code is publicly available.

cs.CV↗

arXiv2022

GraphTTA: Test Time Adaptation on Graph Neural Networks

Recently, test time adaptation (TTA) has attracted increasing attention due to its power of handling the distribution shift issue in the real world. Unlike what has been developed for convolutional neural networks (CNNs) for image data, TTA is less explored for Graph Neural Networks (GNNs). There is still a lack of efficient algorithms tailored for graphs with irregular structures. In this paper, we present a novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data. Specifically, GAPGC employs a contrastive learning variant as a self-supervised task during TTA, equipped with Adversarial Learnable Augmenter and Group Pseudo-Positive Samples to enhance the relevance between the self-supervised task and the main task, boosting the performance of the main task. Furthermore, we provide theoretical evidence that GAPGC can extract minimal sufficient information for the main task from information theory perspective. Extensive experiments on molecular scaffold OOD dataset demonstrated that the proposed approach achieves state-of-the-art performance on GNNs.

cs.LG↗

arXiv2022

Resilience assessment and improvement for electric power transmission systems against typhoon disasters: A data-model hybrid driven approach

In response to the damage to electric power transmission systems caused by typhoon disasters in coastal areas, a planning-targeted resilience assessment framework that considers the impact of multiple factors is established to accurately find the weak links of the transmission system and improve the system resilience. Firstly, this paper constructs the attenuation model of the wind field and the comprehensive failure model of the system, in which the model drive to establish the cumulative failure model of the transmission system is adopted, and multiple data-driven schemes to correct the cumulative failure rate by relying on the feature factor information of the transmission system is adopted. At the same time, an analytic hierarchy process-weighted arithmetic averaging (AHP-WAA) method is introduced to select the optimal data-driven evaluation scheme. Secondly, this paper adopts the impact-increment-based state enumeration (IISE) method to establish resilience indicators for systems and corridors separately. On this basis, the optimal promotion strategy is selected according to the construction difficulty, resilience improvement ability, and cost analysis. Finally, simulations on the IEEE RTS-79 system have been carried out considering the influence of the real typhoon scenarios, micro-topographic and transmission corridor information factors. The results demonstrate that the hybrid-driven system resilience assessment and improvement method can assist planners in accurately judging the resilience level of the system against typhoon disasters and selecting the best resilience improvement strategy based on the cost-effectiveness ratio.

eess.SY↗

arXiv2022

Rethinking the Performance of ISAC System: From Efficiency and Utility Perspectives

Integrated sensing and communications (ISAC) is an essential technology for the 6G communication system, which enables the conventional wireless communication network capable of sensing targets around. The shared use of pilots is a promising strategy to achieve ISAC. It brings a trade-off between communication and sensing, which is still unclear under the imperfect channel estimation condition. To provide some insights, the trade-off between ergodic capacity with imperfect channel estimation and ergodic Cramer-Rao bound (CRB) of range sensing is investigated. Firstly, the closedform expressions of ergodic capacity and ergodic range CRB are derived, which are associated with the number of pilots. Secondly, two novel metrics named efficiency and utility are firstly proposed to evaluate the joint performance of capacity and range sensing error. Specifically, efficiency is used to evaluate the achievable capacity per unit of the sensing error, and utility is designed to evaluate the utilization degree of ISAC. Moreover, an algorithm of pilot length optimization is designed to achieve the best efficiency. Finally, simulation results are given to verify the accuracy of analytical results, and provide some insights on designing the slot structure.

cs.IT↗

arXiv2022

Uniqueness of some cylindrical tangent cones to special Lagrangians

We show that if an exact special Lagrangian $N\subset \mathbb{C}^n$ has a multiplicity one, cylindrical tangent cone of the form $\mathbb{R}^{k}\times \mathbf{C}$ where $\mathbf{C}$ is a special Lagrangian cone with smooth, connected link, then this tangent cone is unique provided $\mathbf{C}$ satisfies an integrability condition. This applies, for example, when $\mathbf{C}= \mathbf{C}_{HL}^{m}$ is the Harvey-Lawson $T^{m-1}$ cone for $m\ne 8,9$.

math.DG↗

arXiv2022

Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment

Human-centered AI considers human experiences with AI performance. While abundant research has been helping AI achieve superhuman performance either by fully automatic or weak supervision learning, fewer endeavors are experimenting with how AI can tailor to humans' preferred skill level given fine-grained input. In this work, we guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. To achieve this, we developed a portable, interactive platform that enables the user to interact with agents online via manipulating the task difficulty, observing performance, and providing curriculum feedback. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications that require millions of samples without a server. The result demonstrates the effectiveness of an interactive curriculum for reinforcement learning involving human-in-the-loop. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level. We believe this research will open new doors for achieving flow and personalized adaptive difficulties.

cs.AI↗

arXiv2022

Physical essence of propagable fractional-strength optical vortices in free space

Fractional-order vector vortex beams are recently demonstrated to be new carriers of fractional-strength optical vortices. However, why can those new vortex beams formed by the combination of both unstable states propagate stably in free space? Here, we solve this scientific problem by revealing the physical essence of propagable fractional-strength optical vortices in free space.Three new understandings regarding those peculiar vortex beams are therefore proposed, namely Abbe diffraction limit, phase evolution of vortex beam, and phase binary time vector property.For the first one, owing to Abbe diffraction limit, the inherent polarization modes are intertwined together, thereby maintaining the entire peculiar vortex beams in free space. For the second one, we demonstrate the phase evolution of vortex beam, which is the physical reason of polarization rotation of fractional-order VVBs. For the third one, the phase is not merely a scalar attribute of light beam, but manifests a binary time vector property. This work provides entirely different physical viewpoints on the phase of vortex beam and Abbe diffraction limit, which may deepen our knowledge on the behavior of light beam in classical optics.

physics.optics↗

arXiv2022

A Real-time Edge-AI System for Reef Surveys

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are ongoing to manage COTS populations to ecologically sustainable levels. In this paper, we present a comprehensive real-time machine learning-based underwater data collection and curation system on edge devices for COTS monitoring. In particular, we leverage the power of deep learning-based object detection techniques, and propose a resource-efficient COTS detector that performs detection inferences on the edge device to assist marine experts with COTS identification during the data collection phase. The preliminary results show that several strategies for improving computational efficiency (e.g., batch-wise processing, frame skipping, model input size) can be combined to run the proposed detection model on edge hardware with low resource consumption and low information loss.

cs.LG↗

arXiv2022

PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark

Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.). Previous work struggled in complex cases due to their simple designs of the spatial transformation between front view and bird's eye view (BEV) and the lack of a realistic dataset. Towards these issues, we present PersFormer: an end-to-end monocular 3D lane detector with a novel Transformer-based spatial feature transformation module. Our model generates BEV features by attending to related front-view local regions with camera parameters as a reference. PersFormer adopts a unified 2D/3D anchor design and an auxiliary task to detect 2D/3D lanes simultaneously, enhancing the feature consistency and sharing the benefits of multi-task learning. Moreover, we release one of the first large-scale real-world 3D lane datasets: OpenLane, with high-quality annotation and scenario diversity. OpenLane contains 200,000 frames, over 880,000 instance-level lanes, 14 lane categories, along with scene tags and the closed-in-path object annotations to encourage the development of lane detection and more industrial-related autonomous driving methods. We show that PersFormer significantly outperforms competitive baselines in the 3D lane detection task on our new OpenLane dataset as well as Apollo 3D Lane Synthetic dataset, and is also on par with state-of-the-art algorithms in the 2D task on OpenLane. The project page is available at https://github.com/OpenPerceptionX/PersFormer_3DLane and OpenLane dataset is provided at https://github.com/OpenPerceptionX/OpenLane.

cs.CV↗

arXiv2022

Quantitative Thomas-Yau uniqueness

Under Floer theoretic conditions, we obtain quantitative estimates on the closeness (Hausdorff distance, flat norm, F-metric) between two Lagrangians, depending on the smallness of Lagrangian angles. Some applications include a strong-weak uniqueness theorem for special Lagrangians, and a characterization of varifold convergence to special Lagrangians in terms of Lagrangian angles.

math.SG↗

arXiv2022

Large time behavior of the solutions to 3D incompressible MHD system with horizontal dissipation or horizontal magnetic diffusion

In this paper, we consider the asymptotic behavior of global solutions to 3D anisotropic incompressible MHD systems. For the 3D MHD system with horizontal dissipation and full magnetic diffusion, it is shown that $\uh(t)$ decays at the rate of $O(t^{-(1-\f{1}{p})})$, $u_3(t)$ decays at the rate of $O(t^{-\f{3}{2}(1-\f{1}{p})})$ and $B(t)$ decays at the rate of $O(t^{-\f{3}{2}(1-\f{1}{p})-\f{1}{2}})$. Furthermore, we give the asymptotic expansion of solutions. We prove that the leading term of $\uh(t)$ is a combination of linear solution and two integrals from nonlinear coupling effects, while for $u_3(t)$ the leading term is given by only the linear solution without the influence of magnetic field. Though the dissipation of velocity is weak, we show that the full magnetic diffusion is robust enough to keep the asymptotic expansion of magnetic field basically expected. However, the magnetic field turns out to affect the higher order asymptotic expansions of $u_3(t)$. The obtained results reveal the crucial role played by the magnetic field in the asymptotic analysis of anisotropic incompressible MHD equations and are expected to enhance the understanding of incompressible MHD equations from the viewpoint of mathematics.

math.AP↗

arXiv2022

Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation

Spiking neural network (SNN) has been attached to great importance due to the properties of high biological plausibility and low energy consumption on neuromorphic hardware. As an efficient method to obtain deep SNN, the conversion method has exhibited high performance on various large-scale datasets. However, it typically suffers from severe performance degradation and high time delays. In particular, most of the previous work focuses on simple classification tasks while ignoring the precise approximation to ANN output. In this paper, we first theoretically analyze the conversion errors and derive the harmful effects of time-varying extremes on synaptic currents. We propose the Spike Calibration (SpiCalib) to eliminate the damage of discrete spikes to the output distribution and modify the LIPooling to allow conversion of the arbitrary MaxPooling layer losslessly. Moreover, Bayesian optimization for optimal normalization parameters is proposed to avoid empirical settings. The experimental results demonstrate the state-of-the-art performance on classification, object detection, and segmentation tasks. To the best of our knowledge, this is the first time to obtain SNN comparable to ANN on these tasks simultaneously. Moreover, we only need 1/50 inference time of the previous work on the detection task and can achieve the same performance under 0.492$\times$ energy consumption of ANN on the segmentation task.

cs.CV↗

arXiv2022

High-throughput decoder of quasi-cyclic LDPC codes with limited precision for continuous-variable quantum key distribution systems

More than Mbps secret key rate was demonstrated for continuous-variable quantum key distribution (CV-QKD) systems, but real-time postprocessing is not allowed, which is restricted by the throughput of the error correction decoding in postprocessing. In this paper, a high-throughput FPGA-based quasi-cyclic LDPC decoder is proposed and implemented to support Mbps real-time secret key rate generation for CV-QKD for the first time. A residual bit error correction algorithm is used to solve the problem of high frame errors rate (FER) caused by the limited precision of the decoder. Specifically, real-time high-speed decoding for CV-QKD systems with typical code rates 0.2 and 0.1 is implemented on a commercial FPGA, and two throughputs of 360.92Mbps and 194.65Mbps are achieved, respectively, which can support 17.97 Mbps and 2.48 Mbps real-time generation of secret key rates under typical transmission distances of 25km and 50km, correspondingly. The proposed method paves the way for high-rate real-time CV-QKD deployment in secure metropolitan area network.

quant-ph↗

arXiv2022

Community Size and User Migration: Population Model Based on opinion Dynamics

Due to its significance in the recommendation system and community operations, user migration has garnered the interest of cyber-demography experts from numerous disciplines. However, contemporary research frequently overlooks the theory behind related prediction techniques, such as the Hidden Markov model. By combining the two fundamental processes of "opinion evolution" and "individual migration" in this research, the mechanistic explanation of online user migration is established and merged into a composite model. Simultaneously, some fundamental theorems and exploratory conclusions related to our model's consensus and steady population state are established via theoretical proof and numerical simulation.

cs.SI↗

arXiv2022

Auto-Encoder-Extreme Learning Machine Model for Boiler NOx Emission Concentration Prediction

An automatic encoder (AE) extreme learning machine (ELM)-AE-ELM model is proposed to predict the NOx emission concentration based on the combination of mutual information algorithm (MI), AE, and ELM. First, the importance of practical variables is computed by the MI algorithm, and the mechanism is analyzed to determine the variables related to the NOx emission concentration. Then, the time delay correlations between the selected variables and NOx emission concentration are further analyzed to reconstruct the modeling data. Subsequently, the AE is applied to extract hidden features within the input variables. Finally, an ELM algorithm establishes the relationship between the NOx emission concentration and deep features. The experimental results on practical data indicate that the proposed model shows promising performance compared to state-of-art models.

cs.LG↗

arXiv2022

Scalable $\rm Al_2O_3-TiO_2$ Conductive Oxide Interfaces as Defect Reservoirs for Resistive Switching Devices

Resistive switching devices herald a transformative technology for memory and computation, offering considerable advantages in performance and energy efficiency. Here we employ a simple and scalable material system of conductive oxide interfaces and leverage their unique properties for a new type of resistive switching device. For the first time, we demonstrate an $\rm Al_2O_3-TiO_2$ based valence-change resistive switching device, where the conductive oxide interface serves both as the back electrode and as a reservoir of defects for switching. The amorphous-polycrystalline $\rm Al_2O_3-TiO_2$ conductive interface is obtained following the technological path of simplifying the fabrication of the two-dimensional electron gases (2DEGs), making them more scalable for practical mass integration. We combine physical analysis of the device chemistry and microstructure with comprehensive electrical analysis of its switching behavior and performance. We pinpoint the origin of the resistive switching to the conductive oxide interface, which serves as the bottom electrode and as a reservoir of oxygen vacancies. The latter plays a key role in valence-change resistive switching devices. The new device, based on scalable and complementary metal-oxide-semiconductor (CMOS) technology-compatible fabrication processes, opens new design spaces towards increased tunability and simplification of the device selection challenge.

physics.app-ph↗