arXiv subjects

Chen Chen

Publications and source records attributed to Chen Chen.

At least 811 records · Page 45Linked to original sources

arXiv2022

Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network

Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture. To tackle the unique difficulty in TAD, we make important improvements over the original framework. We propose a new Context-Adaptive Proposal Module and an innovative Fake-Proposal Generation Block. What's more, we use atomic action features to improve the performance. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance on lots of benchmarks, i.e., ActivityNet-1.3 (40.01% mAP), HACS Segments (38.39% mAP), SoccerNet-Action Spotting (54.09% mAP). It outperforms existing single-network detector by a large margin.

cs.CV↗

arXiv2022

Primal-dual Estimator Learning: an Offline Constrained Moving Horizon Estimation Method with Feasibility and Near-optimality Guarantees

This paper proposes a primal-dual framework to learn a stable estimator for linear constrained estimation problems leveraging the moving horizon approach. To avoid the online computational burden in most existing methods, we learn a parameterized function offline to approximate the primal estimate. Meanwhile, a dual estimator is trained to check the suboptimality of the primal estimator during execution time. Both the primal and dual estimators are learned from data using supervised learning techniques, and the explicit sample size is provided, which enables us to guarantee the quality of each learned estimator in terms of feasibility and optimality. This in turn allows us to bound the probability of the learned estimator being infeasible or suboptimal. Furthermore, we analyze the stability of the resulting estimator with a bounded error in the minimization of the cost function. Since our algorithm does not require the solution of an optimization problem during runtime, state estimates can be generated online almost instantly. Simulation results are presented to show the accuracy and time efficiency of the proposed framework compared to online optimization of moving horizon estimation and Kalman filter. To the best of our knowledge, this is the first learning-based state estimator with feasibility and near-optimality guarantees for linear constrained systems.

eess.SY↗

arXiv2022

Nucleon axial-vector and pseudoscalar form factors, and PCAC relations

We use a continuum quark+diquark approach to the nucleon bound-state problem in relativistic quantum field theory to deliver parameter-free predictions for the nucleon axial and induced pseudoscalar form factors, $G_A$ and $G_P$, and unify them with the pseudoscalar form factor $G_5$ or, equivalently, the pion-nucleon form factor $G_{πNN}$. We explain how partial conservation of the axial-vector current and the associated Goldberger-Treiman relation are satisfied once all necessary couplings of the external current to the building blocks of the nucleon are constructed consistently; in particular, we fully resolve the seagull couplings to the diquark-quark vertices associated with the axial-vector and pseudoscalar currents. Among the results we describe, the following are worth highlighting. A dipole form factor defined by an axial charge $g_A=G_A(0)=1.25(3)$ and a mass-scale $M_A = 1.23(3) m_N$, where $m_N$ is the nucleon mass, can accurately describe the pointwise behaviour of $G_A$. Concerning $G_P$, we obtain the pseudoscalar charge $g_p^\ast = 8.80(23)$, and find that the pion pole dominance approach delivers a reliable estimate of the directly computed result. Our computed value of the pion-nucleon coupling constant, $g_{πNN}/m_N =14.02(33)/{\rm GeV}$ is consistent with recent precision determinations.

hep-ph↗

arXiv2022

Evidence for quasar fast outflows being accelerated at the scale of tens of parsecs

Quasar outflows may play a crucial role in regulating the host galaxy, although the spatial scale of quasar outflows remain a major enigma, with their acceleration mechanism poorly understood. The kinematic information of outflow is the key to understanding its origin and acceleration mechanism. Here, we report the galactocentric distances of different outflow components for both a sample and an individual quasar. We find that the outflow distance increases with velocity, with a typical value from several parsecs to more than one hundred parsecs, providing direct evidence for an acceleration happening at a scale of the order of 10 parsecs. These outflows carry ~1% of the total quasar energy, while their kinematics are consistent with a dust driven model with a launching radius comparable to the scale of a dusty torus, indicating that the coupling between dust and quasar radiation may produce powerful feedback that is crucial to galaxy evolution.

astro-ph.GA↗

arXiv2022

Resilient Distribution System Restoration with Communication Recovery by Drone Small Cells

Distribution system (DS) restoration after natural disasters often faces the challenge of communication failures to feeder automation (FA) facilities, resulting in prolonged load pick-up process. This letter discusses the utilization of drone small cells for wireless communication recovery of FA, and proposes an integrated DS restoration strategy with communication recovery. Demonstrative case studies are conducted to validate the proposed model, and its advantages are illustrated by comparing to benchmark strategies.

eess.SY↗

arXiv2022

TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization

The dominant CNN-based methods for cross-view image geo-localization rely on polar transform and fail to model global correlation. We propose a pure transformer-based approach (TransGeo) to address these limitations from a different perspective. TransGeo takes full advantage of the strengths of transformer related to global information modeling and explicit position information encoding. We further leverage the flexibility of transformer input and propose an attention-guided non-uniform cropping method, so that uninformative image patches are removed with negligible drop on performance to reduce computation cost. The saved computation can be reallocated to increase resolution only for informative patches, resulting in performance improvement with no additional computation cost. This "attend and zoom-in" strategy is highly similar to human behavior when observing images. Remarkably, TransGeo achieves state-of-the-art results on both urban and rural datasets, with significantly less computation cost than CNN-based methods. It does not rely on polar transform and infers faster than CNN-based methods. Code is available at https://github.com/Jeff-Zilence/TransGeo2022.

cs.CV↗

arXiv2022

GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing

Compositing-aware object search aims to find the most compatible objects for compositing given a background image and a query bounding box. Previous works focus on learning compatibility between the foreground object and background, but fail to learn other important factors from large-scale data, i.e. geometry and lighting. To move a step further, this paper proposes GALA (Geometry-and-Lighting-Aware), a generic foreground object search method with discriminative modeling on geometry and lighting compatibility for open-world image compositing. Remarkably, it achieves state-of-the-art results on the CAIS dataset and generalizes well on large-scale open-world datasets, i.e. Pixabay and Open Images. In addition, our method can effectively handle non-box scenarios, where users only provide background images without any input bounding box. A web demo (see supplementary materials) is built to showcase applications of the proposed method for compositing-aware search and automatic location/scale prediction for the foreground object.

cs.CV↗

arXiv2022

Topological Corner States in Graphene by Bulk and Edge Engineering

Two-dimensional higher-order topology is usually studied in (nearly) particle-hole symmetric models, so that an edge gap can be opened within the bulk one. But more often deviates the edge anticrossing even into the bulk, where corner states are difficult to pinpoint. We address this problem in a graphene-based $\mathbb{Z}_2$ topological insulator with spin-orbit coupling and in-plane magnetization both originating from substrates through a Slater-Koster multi-orbital model. The gapless helical edge modes cross inside the bulk, where is also located the magnetization-induced edge gap. After demonstrating its second-order nontriviality in bulk topology by a series of evidence, we show that a difference in bulk-edge onsite energy can adiabatically tune the position of the crossing/anticrossing of the edge modes to be inside the bulk gap. This can help unambiguously identify two pairs of topological corner states with nonvanishing energy degeneracy for a rhombic flake. We further find that the obtuse-angle pair is more stable than the acute-angle one. These results not only suggest an accessible way to "find" topological corner states, but also provide a higher-order topological version of "bulk-boundary correspondence".

cond-mat.mes-hall↗

arXiv2022

SPAct: Self-supervised Privacy Preservation for Action Recognition

Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating privacy leakage in action recognition require privacy labels along with the action labels from the video dataset. However, annotating frames of video dataset for privacy labels is not feasible. Recent developments of self-supervised learning (SSL) have unleashed the untapped potential of the unlabeled data. For the first time, we present a novel training framework which removes privacy information from input video in a self-supervised manner without requiring privacy labels. Our training framework consists of three main components: anonymization function, self-supervised privacy removal branch, and action recognition branch. We train our framework using a minimax optimization strategy to minimize the action recognition cost function and maximize the privacy cost function through a contrastive self-supervised loss. Employing existing protocols of known-action and privacy attributes, our framework achieves a competitive action-privacy trade-off to the existing state-of-the-art supervised methods. In addition, we introduce a new protocol to evaluate the generalization of learned the anonymization function to novel-action and privacy attributes and show that our self-supervised framework outperforms existing supervised methods. Code available at: https://github.com/DAVEISHAN/SPAct

cs.CV↗

arXiv2022

Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such plenty of in-domain data is not always available in the real-life world. In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (Simu-GAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. Furthermore, we also propose a dual-path speech recognition system to improve the robustness of the system under noisy conditions. Experimental results show that the proposed speech recognition system achieves 7.3% absolute improvement with simulated noisy data by Simu-GAN over the best baseline in terms of word error rate (WER).

cs.SD↗

arXiv2022

Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information

Speech Emotion Recognition (SER) aims to help the machine to understand human's subjective emotion from only audio information. However, extracting and utilizing comprehensive in-depth audio information is still a challenging task. In this paper, we propose an end-to-end speech emotion recognition system using multi-level acoustic information with a newly designed co-attention module. We firstly extract multi-level acoustic information, including MFCC, spectrogram, and the embedded high-level acoustic information with CNN, BiLSTM and wav2vec2, respectively. Then these extracted features are treated as multimodal inputs and fused by the proposed co-attention mechanism. Experiments are carried on the IEMOCAP dataset, and our model achieves competitive performance with two different speaker-independent cross-validation strategies. Our code is available on GitHub.

cs.SD↗

arXiv2022

Category Guided Attention Network for Brain Tumor Segmentation in MRI

Objective: Magnetic resonance imaging (MRI) has been widely used for the analysis and diagnosis of brain diseases. Accurate and automatic brain tumor segmentation is of paramount importance for radiation treatment. However, low tissue contrast in tumor regions makes it a challenging task.Approach: We propose a novel segmentation network named Category Guided Attention U-Net (CGA U-Net). In this model, we design a Supervised Attention Module (SAM) based on the attention mechanism, which can capture more accurate and stable long-range dependency in feature maps without introducing much computational cost. Moreover, we propose an intra-class update approach to reconstruct feature maps by aggregating pixels of the same category. Main results: Experimental results on the BraTS 2019 datasets show that the proposed method outperformers the state-of-the-art algorithms in both segmentation performance and computational complexity. Significance: The CGA U-Net can effectively capture the global semantic information in the MRI image by using the SAM module, while significantly reducing the computational cost. Code is available at https://github.com/delugewalker/CGA-U-Net.

eess.IV↗

arXiv2022

Observation of Dual-band Topological Corner Modes in Acoustic Kagome Lattice with Long-range Interactions

The recent exotic topological corner modes (CMs) in photonic higher-order topological insulators with long-distance interactions have attracted numerous attentions and enriched the physics than their condensed-matter counterparts. While the next-nearest-neighbour (NNN) coupling appears between NNN lattice sites unselectively, and the NNN coupling and their associated dynamics remains elusive in acoustics due to the waveguide-resonator model, an analogy of tight-binding model (TBM), drastically hinders its NNN coupling. Here, in acoustics, we demonstrate selective NNN coupling-induced CMs in split-ring resonators-based kagome crystal and observe dual-band CMs. Three types of CMs are demonstrated in the first bulk gap which can be explained by TBM considering NNN coupling and one type of CMs is observed in the second. All of these findings are verified theoretically and experimentally which reveals rich physics in acoustics, opening a new way towards tunable or multi-band metamaterials design, and offering opportunities for intriguing acoustic manipulation and energy localization.

physics.app-ph↗

arXiv2022

Composition of low-lying $\mathbf{J=\tfrac{3}{2}^\pm \,Δ}$-baryons

A Poincaré-covariant quark+diquark Faddeev equation is used to develop insights into the structure of the four lightest $(I,J^P=\tfrac{3}{2},\tfrac{3}{2}^\pm)$ baryon multiplets. Whilst these systems can contain isovector-axialvector and isovector-vector diquarks, one may neglect the latter and still arrive at a reliable description. The $(\tfrac{3}{2},\tfrac{3}{2}^+)$ states are the simpler systems, with features that bear some resemblance to quark model pictures, \emph{e.g}., their most prominent rest-frame orbital angular momentum component is $\mathsf S$-wave and the $Δ(1600)\tfrac{3}{2}^+$ may reasonably be viewed as a radial excitation of the $Δ(1232)\tfrac{3}{2}^+$. The $(\tfrac{3}{2},\tfrac{3}{2}^-)$ states are more complex: the $Δ(1940)\tfrac{3}{2}^-$ expresses little of the character of a radial excitation of the $Δ(1700)\tfrac{3}{2}^-$; and whilst the rest-frame wave function of the latter is predominantly $\mathsf P$-wave, the leading piece in the $Δ(1940)\tfrac{3}{2}^-$ wave function is $\mathsf S$-wave, in conflict with quark model expectations. Experiments that can test these predictions, such as large momentum transfer resonance electroexcitation, may shed light on the nature of emergent hadron mass.

hep-ph↗

arXiv2022

Mutual Inclination of Ultra-Short-Period Planets with Time Varying Stellar J2-moment

Systems with ultra-short-period planets (USPs) tend to possess larger mutual inclinations compared to those with planets located farther from their host stars. This could be explained due to precession caused by stellar oblateness at early times when the host star was rapidly spinning. However, stellar oblateness reduces over time due to the decrease in the stellar rotation rate, and this may further shape the planetary mutual inclinations. In this work, we investigate in detail how the final mutual inclination varies under the effect of a decreasing $J_2$. We find that different initial parameters (e.g., the magnitude of $J_2$ and planetary inclinations) will contribute to different final mutual inclinations, providing a constraint on the formation mechanisms of USPs. In general, if the inner planets start in the same plane as the stellar equator (or co-planar while misaligned with the stellar spin-axis), the mutual inclination decreases (or increases then decreases) over time due to the decay of the $J_2$ moment. This is because the inner orbit typically possesses less orbital angular momentum than the outer ones. However, if the outer planet is initially aligned with the stellar spin while the inner one is misaligned, the mutual inclination nearly stays the same. Overall, our results suggest that either the USP planets formed early and acquired significant inclinations (e.g., $\gtrsim30^\circ$ with its companion or $\gtrsim10^\circ$ with its host star spin-axis for Kepler-653c) or they formed late ($\gtrsim$Gyr) when their host stars rotate slower.

astro-ph.EP↗

arXiv2022

A quasar shedding its dust cocoon at redshift 2

We present the first near-IR spectroscopy and joint analyses of multi-wavelength observations for SDSS J082747.14+425241.1, a dust-reddened, weak broad emission-line quasar (WLQ) undergoing a remarkable broad absorption line (BAL) transformation. The systemic redshift is more precisely measured to be $z=2.070\pm0.001$ using H$β$ compared to $z=2.040\pm0.003$ using \mgii\ from the literature, signifying an extreme \mgii\ blueshift of $2140\pm530$ \kms\ relative to H$β$. Using the H$β$-based single-epoch scaling relation with a systematic uncertainty of 0.3 dex, its black hole (BH) mass and Eddington ratio are estimated to be $M_{\rm BH}\sim6.1\times10^8M_\odot$ and $λ_{\rm Edd}\sim0.71$, indicative of being in a rapidly accreting phase. Our investigations confirm the WLQ nature and the LoBAL$\rightarrow$HiBAL transformation, along with a factor of 2 increase in the \mgii+\feii\ emission strength and a decrease of 0.1 in $E(B-V)$ over two decades. The kinetic power of this LoBAL wind at $R\sim$15 pc from its BH is estimated to be $\sim$43\% of the Eddington luminosity, sufficient for quasar feedback upon its host galaxy albeit with an order-of-magnitude uncertainty. This quasar provides a clear example of the long-sought scenario where LoBAL quasars are surrounded by dust cocoons, and wide-angle nuclear winds play a key role in the transition for red quasars evolving into the commonly seen blue quasars.

astro-ph.GA↗

arXiv2022

Full-scale validation of CFD simulations of buoyancy-driven ventilation in a three-story office building

Computational fluid dynamics (CFD) is frequently used to support the design of naturally ventilated buildings; however, the model accuracy should be thoroughly assessed, ideally through validation with full-scale measurements. The present study aims to (1) validate transient CFD simulations with uncertainty quantification (UQ) for buoyancy-driven natural ventilation against full-scale experiments in an operational atrium building, and (2) quantify the sensitivity of the CFD results to the thermal boundary conditions. The UQ and sensitivity analysis consider uncertainties in the initial and boundary conditions for the temperatures. Considering the volume-averaged air temperature on each floor, the predictions and measurements agree well with discrepancies less than 0.3 °C. When considering the temperature averaged over smaller zones on each floor, two trends can be observed. First, in zones not adjacent to windows, the discrepancies between the CFD and measurements can be explained by uncertainty in the boundary conditions and the measurements. Second, in zones adjacent to windows, higher discrepancies are observed due to oscillations in the inflow jets just downstream of the windows, and due to geometrical simplifications in the CFD model. The sensitivity analysis demonstrates that the boundary conditions for the thermal mass surface temperature and the outdoor temperature have a dominant effect on the indoor air temperature predictions, with their relative importance varying as function of proximity to the windows.

physics.flu-dyn↗

arXiv2022

Geometric Transformers for Protein Interface Contact Prediction

Computational methods for predicting the interface contacts between proteins come highly sought after for drug discovery as they can significantly advance the accuracy of alternative approaches, such as protein-protein docking, protein function analysis tools, and other computational methods for protein bioinformatics. In this work, we present the Geometric Transformer, a novel geometry-evolving graph transformer for rotation and translation-invariant protein interface contact prediction, packaged within DeepInteract, an end-to-end prediction pipeline. DeepInteract predicts partner-specific protein interface contacts (i.e., inter-protein residue-residue contacts) given the 3D tertiary structures of two proteins as input. In rigorous benchmarks, DeepInteract, on challenging protein complex targets from the 13th and 14th CASP-CAPRI experiments as well as Docking Benchmark 5, achieves 14% and 1.1% top L/5 precision (L: length of a protein unit in a complex), respectively. In doing so, DeepInteract, with the Geometric Transformer as its graph-based backbone, outperforms existing methods for interface contact prediction in addition to other graph-based neural network backbones compatible with DeepInteract, thereby validating the effectiveness of the Geometric Transformer for learning rich relational-geometric features for downstream tasks on 3D protein structures.

cs.LG↗