arXiv subjects

Junfei Huang

Publications and source records attributed to Junfei Huang.

4 recordsLinked to original sources

arXiv2025

MoniRefer: A Real-world Large-scale Multi-modal Dataset based on Roadside Infrastructure for 3D Visual Grounding

3D visual grounding aims to localize the object in 3D point cloud scenes that semantically corresponds to given natural language sentences. It is very critical for roadside infrastructure system to interpret natural languages and localize relevant target objects in complex traffic environments. However, most existing datasets and approaches for 3D visual grounding focus on the indoor and outdoor driving scenes, outdoor monitoring scenarios remain unexplored due to scarcity of paired point cloud-text data captured by roadside infrastructure sensors. In this paper, we introduce a novel task of 3D Visual Grounding for Outdoor Monitoring Scenarios, which enables infrastructure-level understanding of traffic scenes beyond the ego-vehicle perspective. To support this task, we construct MoniRefer, the first real-world large-scale multi-modal dataset for roadside-level 3D visual grounding. The dataset consists of about 136,018 objects with 411,128 natural language expressions collected from multiple complex traffic intersections in the real-world environments. To ensure the quality and accuracy of the dataset, we manually verified all linguistic descriptions and 3D labels for objects. Additionally, we also propose a new end-to-end method, named Moni3DVG, which utilizes the rich appearance information provided by images and geometry and optical information from point cloud for multi-modal feature learning and 3D object localization. Extensive experiments and ablation studies on the proposed benchmarks demonstrate the superiority and effectiveness of our method. Our dataset and code will be released.

cs.CV↗

arXiv2018

On the Taylor Expansion of Value Functions

We introduce a framework for approximate dynamic programming that we apply to discrete time chains on $\mathbb{Z}_+^d$ with countable action sets. Our approach is grounded in the approximation of the (controlled) chain's generator by that of another Markov process. In simple terms, our approach stipulates applying a second-order Taylor expansion to the value function to replace the Bellman equation with one in continuous space and time where the transition matrix is reduced to its first and second moments. In some cases, the resulting equation (which we label {\bf TCP}) can be interpreted as corresponding to a Brownian control problem. When tractable, the TCP serves as a useful modeling tool. More generally, the TCP is a starting point for approximation algorithms. We develop bounds on the optimality gap---the sub-optimality introduced by using the control produced by the "Taylored" equation. These bounds can be viewed as a conceptual underpinning, analytical rather than relying on weak convergence arguments, for the good performance of controls derived from Brownian control problems. We prove that, under suitable conditions and for suitably "large" initial states, (i) the optimality gap is smaller than a $1-α$ fraction of the optimal value, where $α\in (0,1)$ is the discount factor, and (ii) the gap can be further expressed as the infinite horizon discounted value with a "lower-order" per period reward. Computationally, our framework leads to an "aggregation" approach with performance guarantees. While the guarantees are grounded in PDE theory, the practical use of this approach requires no knowledge of that theory.

math.OC↗

arXiv2015

A Unified Approach to Diffusion Analysis of Queues with General Patience-time Distributions

We propose a unified approach to establishing diffusion approximations for queues with impatient customers within a general framework of scaling customer patience time. The approach consists of two steps. The first step is to show that the diffusion-scaled abandonment process is asymptotically close to a function of the diffusion-scaled queue length process under appropriate conditions. The second step is to construct a continuous mapping not only to characterize the system dynamics using the system primitives, but also to help verify the conditions needed in the first step. The diffusion approximations can then be obtained by applying the continuous mapping theorem. The approach has two advantages: (i) it provides a unified procedure to establish the diffusion approximations regardless of the structure of the queueing model or the type of patience-time scaling; (ii) and it makes the diffusion analysis of queues with customer abandonment essentially the same as the diffusion analysis of queues without customer abandonment. We demonstrate the application of this approach via the single server system with Markov-modulated service speeds in the traditional heavy-traffic regime and the many-server system in the Halfin-Whitt regime and the non-degenerate slowdown regime.

math.PR↗

arXiv2015

A QoS Guarantee Strategy for Multimedia Conferencing based on Bayesian Networks

Service Oriented Architecture (SOA) is commonly employed in the design and implementation of web service systems. The key technology to enable media communications in the context of SOA is the Service Oriented Communication. To exploit the advantage of SOA, we design and implement a web-based multimedia conferencing system that provides users with a hybrid orchestration of web and communication services. As the current SOA lacks effective QoS guarantee solutions for multimedia services, the user satisfaction is greatly challenged with QoS violations, e.g., low video PSNR (Peak Signal-to-Noise Ratio) and long playback delay. Motivated by addressing the critical problem, we firstly employ the Business Process Execution Language (BPEL) service engine for the hybrid services orchestration and execution. Secondly, we propose a novel context-aware approach to quantify and leverage the causal relationships between QoS metrics and available contexts based on Bayesian networks (CABIN). This approach includes three phases: (1) information discretization, (2) causal relationship profiling, and (3) optimal context tuning. We implement CABIN in a real-life multimedia conferencing system and compare its performance with existing delay and throughput oriented schemes. Experimental results show that CABIN outperforms the competing approaches in improving the video quality in terms of PSNR. It also provides a one-stop shop controls both the web and communication services.

cs.MM↗