arXiv subjects

Jie Li

Publications and source records attributed to Jie Li.

At least 415 records · Page 23Linked to original sources

arXiv2023

MDS Array Codes With (Near) Optimal Repair Bandwidth for All Admissible Repair Degrees

Abundant high-rate (n, k) minimum storage regenerating (MSR) codes have been reported in the literature. However, most of them require contacting all the surviving nodes during a node repair process, resulting in a repair degree of d=n-1. In practical systems, it may not always be feasible to connect and download data from all surviving nodes, as some nodes may be unavailable. Therefore, there is a need for MSR code constructions with a repair degree of d k, and has a smaller sub-packetization level or finite field than some existing constructions. Additionally, in conjunction with a previous generic transformation to reduce the sub-packetization level, we obtain an MDS array code with a small sub-packetization level and $(1+ε)$-optimal repair bandwidth (i.e., $(1+ε)$ times the optimal repair bandwidth) for repair degree d=n-1. This code outperforms some existing ones in terms of either the sub-packetization level or the field size.

cs.IT↗

arXiv2023

Dual-modality Smart Shoes for Quantitative Assessment of Hemiplegic Patients' Lower Limbs' Muscle Strength

Stroke can lead to the impaired motor ability of the patient's lower limbs and hemiplegia. Accurate assessment of the lower limbs' motor ability is important for diagnosis and rehabilitation. To digitalize such assessment so that each test can be traced back any time and subjectivity can be avoided, we test how dual-modality smart shoes equipped with pressure-sensitive insoles and inertial measurement units can be used for this purpose. A 5m walking test protocol, including the left and right turns, is designed. Data are collected from 23 patients and 17 healthy subjects. For the lower limbs' motor ability, the tests are observed by two physicians and assessed using the five graded Medical Research Council scale for muscle examination. The average of two physicians' scores for the same patient is used as the ground truth. Using the feature set we developed, 100\% accuracy is achieved in classifying the patients and healthy subjects. For patients' muscle strength, a mean absolute error of 0.143 and a maximum error of 0.395 is achieved using our feature set and the regression method, closer to the ground truth than the scores from each physician (mean absolute error: 0.217, maximum error: 0.5). We thus validate the possibility of using such smart shoes to objectively and accurately evaluate the lower limbs' muscle strength of the stroke patients.

cs.HC↗

arXiv2023

Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition

How humans understand and recognize the actions of others is a complex neuroscientific problem that involves a combination of cognitive mechanisms and neural networks. Research has shown that humans have brain areas that recognize actions that process top-down attentional information, such as the temporoparietal association area. Also, humans have brain regions dedicated to understanding the minds of others and analyzing their intentions, such as the medial prefrontal cortex of the temporal lobe. Skeleton-based action recognition creates mappings for the complex connections between the human skeleton movement patterns and behaviors. Although existing studies encoded meaningful node relationships and synthesized action representations for classification with good results, few of them considered incorporating a priori knowledge to aid potential representation learning for better performance. LA-GCN proposes a graph convolution network using large-scale language models (LLM) knowledge assistance. First, the LLM knowledge is mapped into a priori global relationship (GPR) topology and a priori category relationship (CPR) topology between nodes. The GPR guides the generation of new "bone" representations, aiming to emphasize essential node information from the data level. The CPR mapping simulates category prior knowledge in human brain regions, encoded by the PC-AC module and used to add additional supervision-forcing the model to learn class-distinguishable features. In addition, to improve information transfer efficiency in topology modeling, we propose multi-hop attention graph convolution. It aggregates each node's k-order neighbor simultaneously to speed up model convergence. LA-GCN reaches state-of-the-art on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

cs.CV↗

arXiv2023

Quantum control of a single magnon in a macroscopic spin system

Non-classical quantum states are the pivotal features of a quantum system that differs from its classical counterpart. However, the generation and coherent control of quantum states in a macroscopic spin system remain an outstanding challenge. Here we experimentally demonstrate the quantum control of a single magnon in a macroscopic spin system (i.e., 1~mm-diameter yttrium-iron-garnet sphere) coupled to a superconducting qubit via a microwave cavity. By tuning the qubit frequency {\it in situ} via the Autler-Townes effect, we manipulate this single magnon to generate its non-classical quantum states, including the single-magnon state and the superposition state of a single magnon and vacuum. Moreover, we confirm the deterministic generation of these non-classical states by Wigner tomography. Our experiment offers the first reported deterministic generation of the non-classical quantum states in a macroscopic spin system and paves a way to explore its promising applications in quantum engineering.

quant-ph↗

arXiv2023

Proposal for optomagnonic teleportation and entanglement swapping

A protocol for realizing discrete-variable quantum teleportation in an optomagnonic system is provided. Using optical pulses, an arbitrary photonic qubit state encoded in orthogonal polarizations is transferred onto the joint state of a pair of magnonic oscillators in two macroscopic yttrium-iron-garnet (YIG) spheres that are placed in an optical interferometer. We further show that optomagnonic entanglement swapping can be realized in an extended dual-interferometer configuration with a joint Bell-state detection. Consequently, magnon Bell states are prepared. We analyze the effect of the residual thermal occupation of the magnon modes on the fidelity in both the teleportation and entanglement swapping protocols.

quant-ph↗

arXiv2023

Tracking through Containers and Occluders in the Wild

Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems. In this paper, we introduce $\textbf{TCOW}$, a new benchmark and model for visual tracking through heavy occlusion and containment. We set up a task where the goal is to, given a video sequence, segment both the projected extent of the target object, as well as the surrounding container or occluder whenever one exists. To study this task, we create a mixture of synthetic and annotated real datasets to support both supervised learning and structured evaluation of model performance under various forms of task variation, such as moving or nested containment. We evaluate two recent transformer-based video models and find that while they can be surprisingly capable of tracking targets under certain settings of task variation, there remains a considerable performance gap before we can claim a tracking model to have acquired a true notion of object permanence.

cs.CV↗

arXiv2023

Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint

Weakly Supervised Temporal Action Localization (WTAL) aims to classify and localize temporal boundaries of actions for the video, given only video-level category labels in the training datasets. Due to the lack of boundary information during training, existing approaches formulate WTAL as a classificationproblem, i.e., generating the temporal class activation map (T-CAM) for localization. However, with only classification loss, the model would be sub-optimized, i.e., the action-related scenes are enough to distinguish different class labels. Regarding other actions in the action-related scene ( i.e., the scene same as positive actions) as co-scene actions, this sub-optimized model would misclassify the co-scene actions as positive actions. To address this misclassification, we propose a simple yet efficient method, named bidirectional semantic consistency constraint (Bi-SCC), to discriminate the positive actions from co-scene actions. The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic consistency constraint (SCC) is used to enforce the predictions of the original video and augmented video to be consistent, hence suppressing the co-scene actions. However, we find that this augmented video would destroy the original temporal context. Simply applying the consistency constraint would affect the completeness of localized positive actions. Hence, we boost the SCC in a bidirectional way to suppress co-scene actions while ensuring the integrity of positive actions, by cross-supervising the original and augmented videos. Finally, our proposed Bi-SCC can be applied to current WTAL approaches, and improve their performance. Experimental results show that our approach outperforms the state-of-the-art methods on THUMOS14 and ActivityNet.

cs.CV↗

arXiv2023

Three Cases of Optical Periodic Modulation in Active Galactic Nuclei

We report on the case of optical periodic modulation discovered in two Active Galactic Nuclei (AGN) and one candidate AGN. Analyzing the archival optical data obtained from large transient surveys, namely the Catalina Real-Transient Survey (CRTS) and the Zwicky Transient Facility (ZTF), we find periodicities of 2169.7, 2103.1, and 1462.6\,day in sources J0122+1032, J1007+1248 (or PG~1004+1248), and J2131$-$1127, respectively. The optical spectra of the first two indicate that the first is likely a blazar and the second a type 1 Seyfert galaxy, and while no spectroscopic information is available for the third one, its overall properties suggest that it is likely an AGN. In addition, mid-infrared (MIR) light curve data of the three sources, taken by the Wide-field InfraredSurvey Explorer (WISE), are also analyzed. The light curves show significant variations, but not appearing related to the optical periodicities. Based on the widely-discussed super-massive black-hole binary (SMBHB) scenario, we discuss the origin of the optical modulation. Two possible interesting features, an additional 162-day short optical periodicity in J2131$-$1127 and the consistency the X-ray flux variations of J1007+1248 with its optical periodicity, are also discussed within the SMBHB scenario.

astro-ph.GA↗

arXiv2023

Viewpoint Equivariance for Multi-View 3D Object Detection

3D object detection from visual sensors is a cornerstone capability of robotic systems. State-of-the-art methods focus on reasoning and decoding object bounding boxes from multi-view camera input. In this work we gain intuition from the integral role of multi-view consistency in 3D scene understanding and geometric learning. To this end, we introduce VEDet, a novel 3D object detection framework that exploits 3D multi-view geometry to improve localization through viewpoint awareness and equivariance. VEDet leverages a query-based transformer architecture and encodes the 3D scene by augmenting image features with positional encodings from their 3D perspective geometry. We design view-conditioned queries at the output level, which enables the generation of multiple virtual frames during training to learn viewpoint equivariance by enforcing multi-view consistency. The multi-view geometry injected at the input level as positional encodings and regularized at the loss level provides rich geometric cues for 3D object detection, leading to state-of-the-art performance on the nuScenes benchmark. The code and model are made available at https://github.com/TRI-ML/VEDet.

cs.CV↗

arXiv2023

BS-GAT Behavior Similarity Based Graph Attention Network for Network Intrusion Detection

With the development of the Internet of Things (IoT), network intrusion detection is becoming more complex and extensive. It is essential to investigate an intelligent, automated, and robust network intrusion detection method. Graph neural networks based network intrusion detection methods have been proposed. However, it still needs further studies because the graph construction method of the existing methods does not fully adapt to the characteristics of the practical network intrusion datasets. To address the above issue, this paper proposes a graph neural network algorithm based on behavior similarity (BS-GAT) using graph attention network. First, a novel graph construction method is developed using the behavior similarity by analyzing the characteristics of the practical datasets. The data flows are treated as nodes in the graph, and the behavior rules of nodes are used as edges in the graph, constructing a graph with a relatively uniform number of neighbors for each node. Then, the edge behavior relationship weights are incorporated into the graph attention network to utilize the relationship between data flows and the structure information of the graph, which is used to improve the performance of the network intrusion detection. Finally, experiments are conducted based on the latest datasets to evaluate the performance of the proposed behavior similarity based graph attention network for the network intrusion detection. The results show that the proposed method is effective and has superior performance comparing to existing solutions.

cs.CR↗

arXiv2023

Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking

This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning for Tracking" (PF-Track). Specifically, our method adapts the "tracking by attention" framework and represents tracked instances coherently over time with object queries. To explicitly use historical cues, our "Past Reasoning" module learns to refine the tracks and enhance the object features by cross-attending to queries from previous frames and other objects. The "Future Reasoning" module digests historical information and predicts robust future trajectories. In the case of long-term occlusions, our method maintains the object positions and enables re-association by integrating motion predictions. On the nuScenes dataset, our method improves AMOTA by a large margin and remarkably reduces ID-Switches by 90% compared to prior approaches, which is an order of magnitude less. The code and models are made available at https://github.com/TRI-ML/PF-Track.

cs.CV↗

arXiv2023

Relaxed Actor-Critic with Convergence Guarantees for Continuous-Time Optimal Control of Nonlinear Systems

This paper presents the Relaxed Continuous-Time Actor-critic (RCTAC) algorithm, a method for finding the nearly optimal policy for nonlinear continuous-time (CT) systems with known dynamics and infinite horizon, such as the path-tracking control of vehicles. RCTAC has several advantages over existing adaptive dynamic programming algorithms for CT systems. It does not require the ``admissibility" of the initialized policy or the input-affine nature of controlled systems for convergence. Instead, given any initial policy, RCTAC can converge to an admissible, and subsequently nearly optimal policy for a general nonlinear system with a saturated controller. RCTAC consists of two phases: a warm-up phase and a generalized policy iteration phase. The warm-up phase minimizes the square of the Hamiltonian to achieve admissibility, while the generalized policy iteration phase relaxes the update termination conditions for faster convergence. The convergence and optimality of the algorithm are proven through Lyapunov analysis, and its effectiveness is demonstrated through simulations and real-world path-tracking tasks.

eess.SY↗

arXiv2023

Breaking the "Object" in Video Object Segmentation

The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape and texture can change dramatically, preserving virtually nothing of the original except for the identity itself. Yet, this important phenomenon is largely absent from existing video object segmentation (VOS) benchmarks. In this work, we close the gap by collecting a new dataset for Video Object Segmentation under Transformations (VOST). It consists of more than 700 high-resolution videos, captured in diverse environments, which are 21 seconds long on average and densely labeled with instance masks. A careful, multi-step approach is adopted to ensure that these videos focus on complex object transformations, capturing their full temporal extent. We then extensively evaluate state-of-the-art VOS methods and make a number of important discoveries. In particular, we show that existing methods struggle when applied to this novel task and that their main limitation lies in over-reliance on static appearance cues. This motivates us to propose a few modifications for the top-performing baseline that improve its capabilities by better modeling spatio-temporal information. But more broadly, the hope is to stimulate discussion on learning more robust video object representations.

cs.CV↗

arXiv2023

MRCN: A Novel Modality Restitution and Compensation Network for Visible-Infrared Person Re-identification

Visible-infrared person re-identification (VI-ReID), which aims to search identities across different spectra, is a challenging task due to large cross-modality discrepancy between visible and infrared images. The key to reduce the discrepancy is to filter out identity-irrelevant interference and effectively learn modality-invariant person representations. In this paper, we propose a novel Modality Restitution and Compensation Network (MRCN) to narrow the gap between the two modalities. Specifically, we first reduce the modality discrepancy by using two Instance Normalization (IN) layers. Next, to reduce the influence of IN layers on removing discriminative information and to reduce modality differences, we propose a Modality Restitution Module (MRM) and a Modality Compensation Module (MCM) to respectively distill modality-irrelevant and modality-relevant features from the removed information. Then, the modality-irrelevant features are used to restitute to the normalized visible and infrared features, while the modality-relevant features are used to compensate for the features of the other modality. Furthermore, to better disentangle the modality-relevant features and the modality-irrelevant features, we propose a novel Center-Quadruplet Causal (CQC) loss to encourage the network to effectively learn the modality-relevant features and the modality-irrelevant features. Extensive experiments are conducted to validate the superiority of our method on the challenging SYSU-MM01 and RegDB datasets. More remarkably, our method achieves 95.1% in terms of Rank-1 and 89.2% in terms of mAP on the RegDB dataset.

cs.CV↗

arXiv2023

Integrated Design of Cooperative Area Coverage and Target Tracking with Multi-UAV System

This paper systematically studies the cooperative area coverage and target tracking problem of multiple-unmanned aerial vehicles (multi-UAVs). The problem is solved by decomposing into three sub-problems: information fusion, task assignment, and multi-UAV behavior decision-making. Specifically, in the information fusion process, we use the maximum consistency protocol to update the joint estimation states of multi-targets (JESMT) and the area detection information. The area detection information is represented by the equivalent visiting time map (EVTM), which is built based on the detection probability and the actual visiting time of the area. Then, we model the task assignment problem of multi-UAV searching and tracking multi-targets as a network flow model with upper and lower flow bounds. An algorithm named task assignment minimum-cost maximum-flow (TAMM) is proposed. Cooperative behavior decision-making uses Fisher information as the mission reward to obtain the optimal tracking action of the UAV. Furthermore, a coverage behavior decision-making algorithm based on the anti-flocking method is designed for those UAVs assigned the coverage task. Finally, a distributed multi-UAV cooperative area coverage and target tracking algorithm is designed, which integrates information fusion, task assignment, and behavioral decision-making. Numerical and hardware-in-the-loop simulation results show that the proposed method can achieve persistent area coverage and cooperative target tracking.

cs.MA↗

arXiv2023

Analyzing Resource Utilization in an HPC System: A Case Study of NERSC Perlmutter

Resource demands of HPC applications vary significantly. However, it is common for HPC systems to primarily assign resources on a per-node basis to prevent interference from co-located workloads. This gap between the coarse-grained resource allocation and the varying resource demands can lead to HPC resources being not fully utilized. In this study, we analyze the resource usage and application behavior of NERSC's Perlmutter, a state-of-the-art open-science HPC system with both CPU-only and GPU-accelerated nodes. Our one-month usage analysis reveals that CPUs are commonly not fully utilized, especially for GPU-enabled jobs. Also, around 64% of both CPU and GPU-enabled jobs used 50% or less of the available host memory capacity. Additionally, about 50% of GPU-enabled jobs used up to 25% of the GPU memory, and the memory capacity was not fully utilized in some ways for all jobs. While our study comes early in Perlmutter's lifetime thus policies and application workload may change, it provides valuable insights on performance characterization, application behavior, and motivates systems with more fine-grain resource allocation.

cs.DC↗

arXiv2023

Rota-Baxter operators on Turaev's Hopf group (co)algebras I: Basic definitions and related algebraic structures

We find a natural compatible condition between the Rota-Baxter operator and Turaev's (Hopf) group-(co)algebras, which leads to the concept of Rota-Baxter Turaev's (Hopf) group-(co)algebra. Two characterizations of Rota-Baxter Turaev's group-algebras (abbr. T-algebras) are obtained: one by Atkinson factorization and the other by T-quasi-idempotent elements. The relations among some related Turaev's group algebraic structures (such as (tri)dendriform T-algebras, Zinbiel T-algebras, pre-Lie T-algebras, Lie T-algebras) are discussed, and some concrete examples from the algebras of dimensions 2,3 and 4 are given. At last we prove that Rota-Baxter Poisson T-algebras can produce pre-Poisson T-algebras and Poisson T-algebras can be obtained from pre-Poisson T-algebras.

math.RA↗

arXiv2023

On the Gamma-Ray Emission of the Andromeda Galaxy M31

Using the $γ$-ray data obtained with the Large Area Telescope (LAT) onboard {\it the Fermi Gamma-ray Space Telescope (Fermi)} for $\sim$14 years, we examine the high energy emission emanating from the center of the Andromeda Galaxy M31. Different from previously reported results, which show a seemingly extended source, we instead find two individual point sources, one consistent with being at the center and one 0\fdg4 south-east of the center. The emission of the former is well described using a Log-Parabola model, similar to those of previous studies, and that of the latter can be fitted with a power law. We discuss the possible origins for the two sources. M31's central source, now consistent with being a point source, necessitates a revisit of its previously discussed originations with this new property taken into consideration, in particular those cosmic rays or dark matter scenarios involving extended source distributions. The SE source appears to have a projected distance of $\sim$6\,kpc from M31's center, and the investigation is required as to whether it is a source locally associated with M31, or is instead a background extra-galactic one.

astro-ph.HE↗