arXiv subjects

Li Li

Publications and source records attributed to Li Li.

At least 307 records · Page 17Linked to original sources

arXiv2024

CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions

Accurately and promptly predicting accidents among surrounding traffic agents from camera footage is crucial for the safety of autonomous vehicles (AVs). This task presents substantial challenges stemming from the unpredictable nature of traffic accidents, their long-tail distribution, the intricacies of traffic scene dynamics, and the inherently constrained field of vision of onboard cameras. To address these challenges, this study introduces a novel accident anticipation framework for AVs, termed CRASH. It seamlessly integrates five components: object detector, feature extractor, object-aware module, context-aware module, and multi-layer fusion. Specifically, we develop the object-aware module to prioritize high-risk objects in complex and ambiguous environments by calculating the spatial-temporal relationships between traffic agents. In parallel, the context-aware is also devised to extend global visual information from the temporal to the frequency domain using the Fast Fourier Transform (FFT) and capture fine-grained visual features of potential objects and broader context cues within traffic scenes. To capture a wider range of visual cues, we further propose a multi-layer fusion that dynamically computes the temporal dependencies between different scenes and iteratively updates the correlations between different visual features for accurate and timely accident prediction. Evaluated on real-world datasets--Dashcam Accident Dataset (DAD), Car Crash Dataset (CCD), and AnAn Accident Detection (A3D) datasets--our model surpasses existing top baselines in critical evaluation metrics like Average Precision (AP) and mean Time-To-Accident (mTTA). Importantly, its robustness and adaptability are particularly evident in challenging driving scenarios with missing or limited training data, demonstrating significant potential for application in real-world autonomous driving systems.

cs.CV↗

arXiv2024

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation

Temporal Sentence Grounding in Videos (TSGV) aims to detect the event timestamps described by the natural language query from untrimmed videos. This paper discusses the challenge of achieving efficient computation in TSGV models while maintaining high performance. Most existing approaches exquisitely design complex architectures to improve accuracy with extra layers and loss, suffering from inefficiency and heaviness. Although some works have noticed that, they only make an issue of feature fusion layers, which can hardly enjoy the highspeed merit in the whole clunky network. To tackle this problem, we propose a novel efficient multi-teacher model (EMTM) based on knowledge distillation to transfer diverse knowledge from both heterogeneous and isomorphic networks. Specifically, We first unify different outputs of the heterogeneous models into one single form. Next, a Knowledge Aggregation Unit (KAU) is built to acquire high-quality integrated soft labels from multiple teachers. After that, the KAU module leverages the multi-scale video and global query information to adaptively determine the weights of different teachers. A Shared Encoder strategy is then proposed to solve the problem that the student shallow layers hardly benefit from teachers, in which an isomorphic teacher is collaboratively trained with the student to align their hidden states. Extensive experimental results on three popular TSGV benchmarks demonstrate that our method is both effective and efficient without bells and whistles.

cs.CV↗

arXiv2024

TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries

In this paper, we propose the task of \textit{Ranked Video Moment Retrieval} (RVMR) to locate a ranked list of matching moments from a collection of videos, through queries in natural language. Although a few related tasks have been proposed and studied by CV, NLP, and IR communities, RVMR is the task that best reflects the practical setting of moment search. To facilitate research in RVMR, we develop the TVR-Ranking dataset, based on the raw videos and existing moment annotations provided in the TVR dataset. Our key contribution is the manual annotation of relevance levels for 94,442 query-moment pairs. We then develop the $NDCG@K, IoU\geq μ$ evaluation metric for this new task and conduct experiments to evaluate three baseline models. Our experiments show that the new RVMR task brings new challenges to existing models and we believe this new dataset contributes to the research on multi-modality search. The dataset is available at \url{https://github.com/Ranking-VMR/TVR-Ranking}

cs.AI↗

arXiv2024

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem.

cs.CR↗

arXiv2024

Constraints on holographic QCD phase transitions from PTA observations

The underlying physics of QCD phase transition in the early Universe remains largely unknown due to its strong-coupling nature during the quark-gluon plasma/hadron gas transition, yet a holographic model has been proposed to quantitatively fit the lattice QCD data while with its duration of the first-order phase transition (FoPT) left undetermined. At specific baryon chemical potential, the first-order QCD phase transition agrees with the observational constraint of baryon asymmetry. It, therefore, provides a scenario for phase transition gravitational waves (GWs) within the Standard Model of particle physics. If these background GWs could contribute dominantly to the recently claimed common-spectrum red noise from pulsar timing array (PTA) observations, the duration of this FoPT can be well constrained, and the associated primordial black holes are still allowed by current observations.

hep-ph↗

arXiv2024

Uniformly Accelerated Motion Model for Inter Prediction

Inter prediction is a key technology to reduce the temporal redundancy in video coding. In natural videos, there are usually multiple moving objects with variable velocity, resulting in complex motion fields that are difficult to represent compactly. In Versatile Video Coding (VVC), existing inter prediction methods usually assume uniform speed motion between consecutive frames and use the linear models for motion estimation (ME) and motion compensation (MC), which may not well handle the complex motion fields in the real world. To address these issues, we introduce a uniformly accelerated motion model (UAMM) to exploit motion-related elements (velocity, acceleration) of moving objects between the video frames, and further combine them to assist the inter prediction methods to handle the variable motion in the temporal domain. Specifically, first, the theory of UAMM is mentioned. Second, based on that, we propose the UAMM-based parameter derivation and extrapolation schemes in the coding process. Third, we integrate the UAMM into existing inter prediction modes (Merge, MMVD, CIIP) to achieve higher prediction accuracy. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 0.38% and on average 0.13% BD-rate reduction compared to the VTM anchor, under the Low-delay P configuration, with a slight increase of time complexity on the encoding/decoding side.

eess.IV↗

arXiv2024

Bipartite Determinantal Ideals and concurrent vertex maps

Bipartite determinantal ideals are introduced by Illian and the author as a vast generalization of the classical determinantal ideals intensively studied in commutative algebra, algebraic geometry, representation theory and combinatorics. We introduce a combinatorial model called concurrent vertex maps to describe the Stanley-Reisner complex of the initial ideal of any bipartite determinantal ideal, and study properties and applications of this model including vertex decomposability, shelling orders, formulas of the Hilbert series and $h$-polynomials.

math.AC↗

arXiv2024

Navigating the Data Trading Crossroads: An Interdisciplinary Survey

Data has been increasingly recognized as a critical factor in the future economy. However, constructing an efficient data trading market faces challenges such as privacy breaches, data monopolies, and misuse. Despite numerous studies proposing algorithms to protect privacy and methods for pricing data, a comprehensive understanding of these issues and systemic solutions remain elusive. This paper provides an extensive review and evaluation of data trading research, aiming to identify existing problems, research gaps, and propose potential solutions. We categorize the challenges into three main areas: Compliance Challenges, Collateral Consequences, and Costly Transactions (the "3C problems"), all stemming from ambiguity in data rights. Through a quantitative analysis of the literature, we observe a paradigm shift from isolated solutions to integrated approaches. Addressing the unresolved issue of right ambiguity, we introduce the novel concept of "data usufruct," which allows individuals to use and benefit from data they do not own. This concept helps reframe data as a more conventional factor of production and aligns it with established economic theories, paving the way for a comprehensive framework of research theories, technical tools, and platforms. We hope this survey provides valuable insights and guidance for researchers, practitioners, and policymakers, thereby contributing to digital economy advancements.

cs.CY↗

arXiv2024

Audio Spotforming Using Nonnegative Tensor Factorization with Attractor-Based Regularization

Spotforming is a target-speaker extraction technique that uses multiple microphone arrays. This method applies beamforming (BF) to each microphone array, and the common components among the BF outputs are estimated as the target source. This study proposes a new common component extraction method based on nonnegative tensor factorization (NTF) for higher model interpretability and more robust spotforming against hyperparameters. Moreover, attractor-based regularization was introduced to facilitate the automatic selection of optimal target bases in the NTF. Experimental results show that the proposed method performs better than conventional methods in spotforming performance and also shows some characteristics suitable for practical use.

cs.SD↗

arXiv2024

LLM for Mobile: An Initial Roadmap

When mobile meets LLMs, mobile app users deserve to have more intelligent usage experiences. For this to happen, we argue that there is a strong need to appl LLMs for the mobile ecosystem. We therefore provide a research roadmap for guiding our fellow researchers to achieve that as a whole. In this roadmap, we sum up six directions that we believe are urgently required for research to enable native intelligence in mobile devices. In each direction, we further summarize the current research progress and the gaps that still need to be filled by our fellow researchers.

cs.SE↗

arXiv2024

Faithful geometric measures for genuine tripartite entanglement

We present a faithful geometric picture for genuine tripartite entanglement of discrete, continuous, and hybrid quantum systems. We first find that the triangle relation $\mathcal{E}^α_{i|jk}\leq \mathcal{E}^α_{j|ik}+\mathcal{E}^α_{k|ij}$ holds for all subadditive bipartite entanglement measure $\mathcal{E}$, all permutations under parties $i, j, k$, all $α\in [0, 1]$, and all pure tripartite states. It provides a geometric interpretation that bipartition entanglement, measured by $\mathcal{E}^α$, corresponds to the side of a triangle, of which the area with $α\in (0, 1)$ is nonzero if and only if the underlying state is genuinely entangled. Then, we rigorously prove the non-obtuse triangle area with $0<α\leq 1/2$ is a measure for genuine tripartite entanglement. Useful lower and upper bounds for these measures are obtained, and generalizations of our results are also presented. Finally, it is significantly strengthened for qubits that, given a set of subadditive and non-additive measures, some state is always found to violate the triangle relation for any $α>1$, and the triangle area is not a measure for any $α>1/2$. Hence, our results are expected to aid significant progress in studying both discrete and continuous multipartite entanglement.

quant-ph↗

arXiv2024

Efficient factored gradient descent algorithm for quantum state tomography

Reconstructing the state of quantum many-body systems is of fundamental importance in quantum information tasks, but extremely challenging due to the curse of dimensionality. In this work, we present an efficient quantum tomography protocol that combines the state-factored with eigenvalue mapping to address the rank-deficient issue and incorporates a momentum-accelerated gradient descent algorithm to speed up the optimization process. We implement extensive numerical experiments to demonstrate that our factored gradient descent algorithm efficiently mitigates the rank-deficient problem and admits orders of magnitude better tomography accuracy and faster convergence. We also find that our method can accomplish the full-state tomography of random 11-qubit mixed states within one minute.

quant-ph↗

arXiv2024

Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis

Synthesizing realistic 3D indoor scenes is a challenging task that traditionally relies on manual arrangement and annotation by expert designers. Recent advances in autoregressive models have automated this process, but they often lack semantic understanding of the relationships and hierarchies present in real-world scenes, yielding limited performance. In this paper, we propose Forest2Seq, a framework that formulates indoor scene synthesis as an order-aware sequential learning problem. Forest2Seq organizes the inherently unordered collection of scene objects into structured, ordered hierarchical scene trees and forests. By employing a clustering-based algorithm and a breadth-first traversal, Forest2Seq derives meaningful orderings and utilizes a transformer to generate realistic 3D scenes autoregressively. Experimental results on standard benchmarks demonstrate Forest2Seq's superiority in synthesizing more realistic scenes compared to top-performing baselines, with significant improvements in FID and KL scores. Our additional experiments for downstream tasks and ablation studies also confirm the importance of incorporating order as a prior in 3D scene generation.

cs.CV↗

arXiv2024

Identification of coupled Landau and anomalous resonances in space plasmas

Wave-particle resonance, a ubiquitous process in the plasma universe, occurs when resonant particles observe a constant wave phase to enable sustained energy transfer. Here, we present spacecraft observations of simultaneous Landau and anomalous resonances between oblique whistler waves and the same group of protons, which are evidenced, respectively, by phase-space rings in parallel-velocity spectra and phase-bunched distributions in gyro-phase spectra. Our results indicate the coupling between Landau and anomalous resonances via the overlapping of the resonance islands.

physics.space-ph↗

arXiv2024

Async Learned User Embeddings for Ads Delivery Optimization

In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance. The effectiveness of recommendation systems depends on the quality of user embedding. We propose to asynchronously learn high fidelity user embeddings for billions of users each day from sequence based multimodal user activities through a Transformer-like large scale feature learning module. The async learned user representations embeddings (ALURE) are further converted to user similarity graphs through graph learning and then combined with user realtime activities to retrieval highly related ads candidates for the ads delivery system. Our method shows significant gains in both offline and online experiments.

cs.IR↗

arXiv2024

Gröbner bases for bipartite determinantal ideals

Nakajima's graded quiver varieties naturally appear in the study of bases of cluster algebras. One particular family of these varieties, namely the bipartite determinantal varieties, can be defined for any bipartite quiver and gives a vast generalization of classical determinantal varieties with broad applications to algebra, geometry, combinatorics, and statistics. The ideals that define bipartite determinantal varieties are called bipartite determinantal ideals. We provide an elementary method of proof showing that the natural generators of a bipartite determinantal ideal form a Gröbner basis, using an S-polynomial construction method that relies on the Leibniz formula for determinants. This method is developed from an idea by Narasimhan and Caniglia--Guccione--Guccione. As applications, we study the connection between double determinantal ideals (which are bipartite determinantal ideals of a quiver with two vertices) and tensors, and provide an interpretation of these ideals within the context of algebraic statistics.

math.AC↗

arXiv2024

Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio

RemixIT and Remixed2Remixed are domain adaptation-based speech enhancement (DASE) methods that use a teacher model trained in full supervision to generate pseudo-paired data by remixing the outputs of the teacher model. The student model for enhancing real-world recorded signals is trained using the pseudo-paired data without ground truth. Since the noisy signals are recorded in natural environments, the dataset inevitably suffers data imbalance in some acoustic properties, leading to subpar performance for the underrepresented data. The signal-to-noise ratio (SNR), inherently balanced in supervised learning, is a prime example. In this paper, we provide empirical evidence that the SNR of pseudo data has a significant impact on model performance using the dataset of the CHiME-7 UDASE task, highlighting the importance of balanced SNR in DASE. Furthermore, we propose adopting curriculum learning to encompass a broad range of SNRs to boost performance for underrepresented data.

cs.SD↗

arXiv2024

Quantum analog to flapping of flags: interface instability for co-flow binary superfluids

We study the interface dynamics in immiscible binary superfluids using its holographic description, which naturally consists of an inviscid superfluid component and a viscous normal fluid component. We give the first theoretical realization of interface instability for two superfluid components moving with identical velocity, providing a quantum analog to the flapping of flags that is common in daily life. This behavior is in sharp contrast to the one from Gross-Pitaevskii equation for which no such co-flow instability develops in an isolated uniform system because of Galilean invariance. The real time evolution triggered by the dynamical instability exhibits intricate nonlinear patterns leading to quantum turbulence reminiscent of the quantum Kelvin-Helmholtz instability. Moreover, we show that such interface dynamics is essentially different from the Landau instability for which the frictionless flow becomes thermodynamically unstable above a critical superfluid velocity. Our study uncovers the rich interface dynamics of quantum fluids and the emergence of complex flow phenomena.

cond-mat.quant-gas↗