arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 577 records · Page 32Linked to original sources

arXiv2024

Probabilistic Visibility-Aware Trajectory Planning for Target Tracking in Cluttered Environments

Target tracking has numerous significant civilian and military applications, and maintaining the visibility of the target plays a vital role in ensuring the success of the tracking task. Existing visibility-aware planners primarily focus on keeping the target within the limited field of view of an onboard sensor and avoiding obstacle occlusion. However, the negative impact of system uncertainty is often neglected, rendering the planners delicate to uncertainties in practice. To bridge the gap, this work proposes a real-time, non-myopic trajectory planner for visibility-aware and safe target tracking in the presence of system uncertainty. For more accurate target motion prediction, we introduce the concept of belief-space probability of detection (BPOD) to measure the predictive visibility of the target under stochastic robot and target states. An Extended Kalman Filter variant incorporating BPOD is developed to predict target belief state under uncertain visibility within the planning horizon. To reach real-time trajectory planning, we propose a computationally efficient algorithm to uniformly calculate both BPOD and the chance-constrained collision risk by utilizing linearized signed distance function (SDF), and then design a two-stage strategy for lightweight calculation of SDF in sequential convex programming. Extensive simulation results with benchmark comparisons show the capacity of the proposed approach to robustly maintain the visibility of the target under high system uncertainty. The practicality of the proposed trajectory planner is validated by real-world experiments.

cs.RO↗

arXiv2024

Shotgun crystal structure prediction using machine-learned formation energies

Stable or metastable crystal structures of assembled atoms can be predicted by finding the global or local minima of the energy surface within a broad space of atomic configurations. Generally, this requires repeated first-principles energy calculations, which is often impractical for large crystalline systems. Here, we present significant progress toward solving the crystal structure prediction problem: we performed noniterative, single-shot screening using a large library of virtually created crystal structures with a machine-learning energy predictor. This shotgun method (ShotgunCSP) has two key technical components: transfer learning for accurate energy prediction of pre-relaxed crystalline states, and two generative models based on element substitution and symmetry-restricted structure generation to produce promising and diverse crystal structures. First-principles calculations were performed only to generate the training samples and to refine a few selected pre-relaxed crystal structures. The ShotunCSP method is computationally less intensive than conventional methods and exhibits exceptional prediction accuracy, reaching 93.3% in benchmark tests with 90 different crystal structures.

physics.comp-ph↗

arXiv2024

Towards Personalized Federated Multi-Scenario Multi-Task Recommendation

In modern recommender systems, especially in e-commerce, predicting multiple targets such as click-through rate (CTR) and post-view conversion rate (CTCVR) is common. Multi-task recommender systems are increasingly popular in both research and practice, as they leverage shared knowledge across diverse business scenarios to enhance performance. However, emerging real-world scenarios and data privacy concerns complicate the development of a unified multi-task recommendation model. In this paper, we propose PF-MSMTrec, a novel framework for personalized federated multi-scenario multi-task recommendation. In this framework, each scenario is assigned to a dedicated client utilizing the Multi-gate Mixture-of-Experts (MMoE) structure. To address the unique challenges of multiple optimization conflicts, we introduce a bottom-up joint learning mechanism. First, we design a parameter template to decouple the expert network parameters, distinguishing scenario-specific parameters as shared knowledge for federated parameter aggregation. Second, we implement personalized federated learning for each expert network during a federated communication round, using three modules: federated batch normalization, conflict coordination, and personalized aggregation. Finally, we conduct an additional round of personalized federated parameter aggregation on the task tower network to obtain prediction results for multiple tasks. Extensive experiments on two public datasets demonstrate that our proposed method outperforms state-of-the-art approaches. The source code and datasets will be released as open-source for public access.

cs.IR↗

arXiv2024

Rapid infrared imaging for rhombohedral graphene

The extrinsic stacking sequence based on intrinsic crystal symmetry in multilayer two-dimensional materials plays a significant role in determining their electronic and optical properties. Compared with Bernal-stacked (ABA) multilayer graphene, rhombohedral (ABC) multilayer graphene hosts stronger electron-electron interaction due to its unique dispersion at low-energy excitations and has been utiliazed as a unique platform to explore strongly correlated physics. However, discerning the stacking sequence has always been a quite time-consuming process by scanning mapping methods. Here, we report a rapid recognition method for ABC- stacked graphene with high accuracy by infrared imaging based on the distinct optical responses at infrared range. The optical contrast of the image between ABC and ABA stacked graphene is strikingly clear, and the discernibility is comparable to traditional optical Raman microscopy but with higher consistency and throughput. We further demonstrate that the infrared imaging technique can be integrated with dry transfer techniques commonly used in the community. This rapid and convenient infrared imaging technique will significantly improve the sorting efficiency for differently stacked multilayer graphene, thereby accelerating the exploration of the novel emergent correlated phenomena in ABC stacked graphene.

cond-mat.mes-hall↗

arXiv2024

TDNetGen: Empowering Complex Network Resilience Prediction with Generative Augmentation of Topology and Dynamics

Predicting the resilience of complex networks, which represents the ability to retain fundamental functionality amidst external perturbations or internal failures, plays a critical role in understanding and improving real-world complex systems. Traditional theoretical approaches grounded in nonlinear dynamical systems rely on prior knowledge of network dynamics. On the other hand, data-driven approaches frequently encounter the challenge of insufficient labeled data, a predicament commonly observed in real-world scenarios. In this paper, we introduce a novel resilience prediction framework for complex networks, designed to tackle this issue through generative data augmentation of network topology and dynamics. The core idea is the strategic utilization of the inherent joint distribution present in unlabeled network data, facilitating the learning process of the resilience predictor by illuminating the relationship between network topology and dynamics. Experiment results on three network datasets demonstrate that our proposed framework TDNetGen can achieve high prediction accuracy up to 85%-95%. Furthermore, the framework still demonstrates a pronounced augmentation capability in extreme low-data regimes, thereby underscoring its utility and robustness in enhancing the prediction of network resilience. We have open-sourced our code in the following link, https://github.com/tsinghua-fib-lab/TDNetGen.

cs.AI↗

arXiv2024

MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking

Existing RGB-T tracking algorithms have made remarkable progress by leveraging the global interaction capability and extensive pre-trained models of the Transformer architecture. Nonetheless, these methods mainly adopt imagepair appearance matching and face challenges of the intrinsic high quadratic complexity of the attention mechanism, resulting in constrained exploitation of temporal information. Inspired by the recently emerged State Space Model Mamba, renowned for its impressive long sequence modeling capabilities and linear computational complexity, this work innovatively proposes a pure Mamba-based framework (MambaVT) to fully exploit spatio-temporal contextual modeling for robust visible-thermal tracking. Specifically, we devise the long-range cross-frame integration component to globally adapt to target appearance variations, and introduce short-term historical trajectory prompts to predict the subsequent target states based on local temporal location clues. Extensive experiments show the significant potential of vision Mamba for RGB-T tracking, with MambaVT achieving state-of-the-art performance on four mainstream benchmarks while requiring lower computational costs. We aim for this work to serve as a simple yet strong baseline, stimulating future research in this field. The code and pre-trained models will be made available.

cs.CV↗

arXiv2024

UVMap-ID: A Controllable and Personalized UV Map Generative Model

Recently, diffusion models have made significant strides in synthesizing realistic 2D human images based on provided text prompts. Building upon this, researchers have extended 2D text-to-image diffusion models into the 3D domain for generating human textures (UV Maps). However, some important problems about UV Map Generative models are still not solved, i.e., how to generate personalized texture maps for any given face image, and how to define and evaluate the quality of these generated texture maps. To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model. Unlike traditional large-scale training methods in 2D, we propose to fine-tune a pre-trained text-to-image diffusion model which is integrated with a face fusion module for achieving ID-driven customized generation. To support the finetuning strategy, we introduce a small-scale attribute-balanced training dataset, including high-quality textures with labeled text and Face ID. Additionally, we introduce some metrics to evaluate the multiple aspects of the textures. Finally, both quantitative and qualitative analyses demonstrate the effectiveness of our method in controllable and personalized UV Map generation. Code is publicly available via https://github.com/twowwj/UVMap-ID.

cs.CV↗

arXiv2024

SN 2023zaw: an ultra-stripped, nickel-poor supernova from a low-mass progenitor

We present SN 2023zaw $-$ a sub-luminous ($\mathrm{M_r} = -16.7$ mag) and rapidly-evolving supernova ($\mathrm{t_{1/2,r}} = 4.9$ days), with the lowest nickel mass ($\approx0.002$ $\mathrm{M_\odot}$) measured among all stripped-envelope supernovae discovered to date. The photospheric spectra are dominated by broad He I and Ca NIR emission lines with velocities of $\sim10\ 000 - 12\ 000$ $\mathrm{km\ s^{-1}}$. The late-time spectra show prominent narrow He I emission lines at $\sim$1000$\ \mathrm{km\ s^{-1}}$, indicative of interaction with He-rich circumstellar material. SN 2023zaw is located in the spiral arm of a star-forming galaxy. We perform radiation-hydrodynamical and analytical modeling of the lightcurve by fitting with a combination of shock-cooling emission and nickel decay. The progenitor has a best-fit envelope mass of $\approx0.2$ $\mathrm{M_\odot}$ and an envelope radius of $\approx50$ $\mathrm{R_\odot}$. The extremely low nickel mass and low ejecta mass ($\approx0.5$ $\mathrm{M_\odot}$) suggest an ultra-stripped SN, which originates from a mass-losing low mass He-star (ZAMS mass $<$ 10 $\mathrm{M_\odot}$) in a close binary system. This is a channel to form double neutron star systems, whose merger is detectable with LIGO. SN 2023zaw underscores the existence of a previously undiscovered population of extremely low nickel mass ($< 0.005$ $\mathrm{M_\odot}$) stripped-envelope supernovae, which can be explored with deep and high-cadence transient surveys.

astro-ph.HE↗

arXiv2024

Local excitation of kagome spin ice magnetism in HoAgGe seen by scanning tunneling microscopy

The kagome spin ice can host frustrated magnetic excitations by flipping its local spin. Under an inelastic tunneling condition, the tip in a scanning tunneling microscope can flip the local spin, and we apply this technique to kagome metal HoAgGe with a long-range ordered spin ice ground state. Away from defects, we discover a pair of pronounced dips in the local tunneling spectrum at symmetrical bias voltages with negative intensity values, serving as a striking inelastic tunneling signal. This signal disappears above the spin ice formation temperature and has a dependence on the magnetic fields, demonstrating its intimate relation with the spin ice magnetism. We provide a two-level spin-flip model to explain the tunneling dips considering the spin ice magnetism under spin-orbit coupling. Our results uncover a local emergent excitation of spin ice magnetism in a kagome metal, suggesting that local electrical field induced spin flip climbs over a barrier caused by spin-orbital locking.

cond-mat.str-el↗

arXiv2024

Momentum Capture and Prediction System Based on Wimbledon Open2023 Tournament Data

There is a hidden energy in tennis, which cannot be seen or touched. It is the force that controls the flow of the game and is present in all types of matches. This mysterious force is Momentum. This study introduces an evaluation model that synergizes the Entropy Weight Method (EWM) and Gray Relation Analysis (GRA) to quantify momentum's impact on match outcomes. Empirical validation was conducted through Mann-Whitney U and Kolmogorov-Smirnov tests, which yielded p values of 0.0043 and 0.00128,respectively. These results underscore the non-random association between momentum shifts and match outcomes, highlighting the critical role of momentum in tennis. Otherwise, our investigation foucus is the creation of a predictive model that combines the advanced machine learning algorithm XGBoost with the SHAP framework. This model enables precise predictions of match swings with exceptional accuracy (0.999013 for multiple matches and 0.992738 for finals). The model's ability to identify the influence of specific factors on match dynamics,such as bilateral distance run during points, demonstrates its prowess.The model's generalizability was thoroughly evaluated using datasets from the four Grand Slam tournaments. The results demonstrate its remarkable adaptability to different match scenarios,despite minor variations in predictive accuracy. It offers strategic insights that can help players effectively respond to opponents' shifts in momentum,enhancing their competitive edge.

cs.LG↗

arXiv2024

Eigenvalues and spanning trees with constrained degree

In this paper, we study some spanning trees with bounded degree and leaf degree from eigenvalues. For any integer $k\geq2$, a $k$-tree is a spanning tree in which every vertex has degree no more than $k$. Let $T$ be a spanning tree of a connected graph. The leaf degree of $T$ is the maximum number of end-vertices attached to $v$ in $T$ for any $v\in V(T)$. By referring to the technique shown in [Eigenvalues and $[a,b]$-factors in regular graphs, J. Graph Theory. 100 (2022) 458-469], for an $r$-regular graph $G$, we provide an upper bound for the fourth largest adjacency eigenvalue of $G$ to guarantee the existence of a $k$-tree. Moreover, for a $t$-connected graph, we prove a tight sufficient condition for the existence of a spanning tree with leaf degree at most $k$ in terms of spectral radius. This generalizes a result of Theorem 1.5 in [Spectral radius and spanning trees of graphs, Discrete Math. 346 (2023) 113400]. Finally, for a general graph $G$, we present two sufficient conditions for the existence of a spanning tree with leaf degree at most $k$ via the Laplacian eigenvalues of $G$ and the spectral radius of the complement of $G$, respectively.

math.CO↗

arXiv2024

MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition

Open-set text recognition, which aims to address both novel characters and previously seen ones, is one of the rising subtopics in the text recognition field. However, the current open-set text recognition solutions only focuses on horizontal text, which fail to model the real-life challenges posed by the variety of writing directions in real-world scene text. Multi-orientation text recognition, in general, faces challenges from the diverse image aspect ratios, significant imbalance in data amount, and domain gaps between orientations. In this work, we first propose a Multi-Oriented Open-Set Text Recognition task (MOOSTR) to model the challenges of both novel characters and writing direction variety. We then propose a Multi-Orientation Sharing Experts (MOoSE) framework as a strong baseline solution. MOoSE uses a mixture-of-experts scheme to alleviate the domain gaps between orientations, while exploiting common structural knowledge among experts to alleviate the data scarcity that some experts face. The proposed MOoSE framework is validated by ablative experiments, and also tested for feasibility on the existing open-set benchmark. Code, models, and documents are available at: https://github.com/lancercat/Moose/

cs.CV↗

arXiv2024

ParCo: Part-Coordinating Text-to-Motion Synthesis

We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts. Moreover, introducing finer-grained part concepts poses computational complexity challenges. In this paper, we propose Part-Coordinating Text-to-Motion Synthesis (ParCo), endowed with enhanced capabilities for understanding part motions and communication among different part motion generators, ensuring a coordinated and fined-grained motion synthesis. Specifically, we discretize whole-body motion into multiple part motions to establish the prior concept of different parts. Afterward, we employ multiple lightweight generators designed to synthesize different part motions and coordinate them through our part coordination module. Our approach demonstrates superior performance on common benchmarks with economic computations, including HumanML3D and KIT-ML, providing substantial evidence of its effectiveness. Code is available at https://github.com/qrzou/ParCo .

cs.CV↗

arXiv2024

End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling

Video Question Answering (VideoQA) has emerged as a challenging frontier in the field of multimedia processing, requiring intricate interactions between visual and textual modalities. Simply uniformly sampling frames or indiscriminately aggregating frame-level visual features often falls short in capturing the nuanced and relevant contexts of videos to well perform VideoQA. To mitigate these issues, we propose VidF4, a novel VideoQA framework equipped with tailored frame selection strategy for effective and efficient VideoQA. We propose three frame-scoring mechanisms that consider both question relevance and inter-frame similarity to evaluate the importance of each frame for a given question on the video. Furthermore, we design a differentiable adaptive frame sampling mechanism to facilitate end-to-end training for the frame selector and answer generator. The experimental results across three widely adopted benchmarks demonstrate that our model consistently outperforms existing VideoQA methods, establishing a new SOTA across NExT-QA (+0.3%), STAR (+0.9%), and TVQA (+1.0%). Furthermore, through both quantitative and qualitative analyses, we validate the effectiveness of each design choice.

cs.CV↗

arXiv2024

User Connection and Resource Allocation Optimization in Blockchain Empowered Metaverse over 6G Wireless Communications

The convergence of blockchain, Metaverse, and non-fungible tokens (NFTs) brings transformative digital opportunities alongside challenges like privacy and resource management. Addressing these, we focus on optimizing user connectivity and resource allocation in an NFT-centric and blockchain-enabled Metaverse in this paper. Through user work-offloading, we optimize data tasks, user connection parameters, and server computing frequency division. In the resource allocation phase, we optimize communication-computation resource distributions, including bandwidth, transmit power, and computing frequency. We introduce the trust-cost ratio (TCR), a pivotal measure combining trust scores from users' resources and server history with delay and energy costs. This balance ensures sustained user engagement and trust. The DASHF algorithm, central to our approach, encapsulates the Dinkelbach algorithm, alternating optimization, semidefinite relaxation (SDR), the Hungarian method, and a novel fractional programming technique from a recent IEEE JSAC paper [2]. The most challenging part of DASHF is to rewrite an optimization problem as Quadratically Constrained Quadratic Programming (QCQP) via carefully designed transformations, in order to be solved by SDR and the Hungarian algorithm. Extensive simulations validate the DASHF algorithm's efficacy, revealing critical insights for enhancing blockchain-Metaverse applications, especially with NFTs.

cs.ET↗

arXiv2024

LLM-Empowered State Representation for Reinforcement Learning

Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurate mappings from states to task rewards. Traditional methods typically depend on extensive sample learning to enrich state representations with task-specific information, which leads to low sample efficiency and high time costs. Recently, surging knowledgeable large language models (LLM) have provided promising substitutes for prior injection with minimal human intervention. Motivated by this, we propose LLM-Empowered State Representation (LESR), a novel approach that utilizes LLM to autonomously generate task-related state representation codes which help to enhance the continuity of network mappings and facilitate efficient training. Experimental results demonstrate LESR exhibits high sample efficiency and outperforms state-of-the-art baselines by an average of 29% in accumulated reward in Mujoco tasks and 30% in success rates in Gym-Robotics tasks.

cs.AI↗

arXiv2024

Perturbation-based Non-perturbative Method

This paper presents a nonperturbative method for solving eigenproblems. This method applies to almost all potentials and provides nonperturbative approximations for any energy level. The method converts an eigenproblem into a perturbation problem, obtains perturbation solutions through standard perturbation theory, and then analytically continues the perturbative solution into a nonperturbative solution. Concretely, we follow three main steps: (1) Introduce an auxiliary potential that can be solved exactly and treat the potential to be solved as a perturbation on this auxiliary system. (2) Use perturbation theory to obtain an approximate polynomial of the eigenproblem. (3) Use a rational approximation to analytically continue this approximate polynomial into the nonperturbative region.

quant-ph↗

arXiv2024

EmoFace: Audio-driven Emotional 3D Face Animation

Audio-driven emotional 3D face animation aims to generate emotionally expressive talking heads with synchronized lip movements. However, previous research has often overlooked the influence of diverse emotions on facial expressions or proved unsuitable for driving MetaHuman models. In response to this deficiency, we introduce EmoFace, a novel audio-driven methodology for creating facial animations with vivid emotional dynamics. Our approach can generate facial expressions with multiple emotions, and has the ability to generate random yet natural blinks and eye movements, while maintaining accurate lip synchronization. We propose independent speech encoders and emotion encoders to learn the relationship between audio, emotion and corresponding facial controller rigs, and finally map into the sequence of controller values. Additionally, we introduce two post-processing techniques dedicated to enhancing the authenticity of the animation, particularly in blinks and eye movements. Furthermore, recognizing the scarcity of emotional audio-visual data suitable for MetaHuman model manipulation, we contribute an emotional audio-visual dataset and derive control parameters for each frames. Our proposed methodology can be applied in producing dialogues animations of non-playable characters (NPCs) in video games, and driving avatars in virtual reality environments. Our further quantitative and qualitative experiments, as well as an user study comparing with existing researches show that our approach demonstrates superior results in driving 3D facial models. The code and sample data are available at https://github.com/SJTU-Lucy/EmoFace.

cs.CV↗