BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Zhiyong Liu

Zhiyong Liu appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Distributed, Parallel, and Cluster ComputingNetworking and Internet ArchitectureComputer VisionData Structures and Algorithmsastro-ph.SRhep-phMultimedia

Catalog footprint

What is connected

14works
7topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

14 published item(s)

preprint2026arXiv

Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval

Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a single matching moment for each query. This assumption does not always hold in real-world scenarios, where queries may correspond to multiple or no moments. Thus, we formulate Generalized Moment Retrieval (GMR), a unified setting that requires retrieving the complete set of relevant moments or predicting an empty set. To enable systematic study of GMR, we introduce Soccer-GMR, a large-scale benchmark built on challenging soccer videos that reflect general GMR scenarios, with realistic negative and positive queries. The benchmark is constructed via a duration-flexible semi-automated pipeline with human verification, enabling scalable data generation while maintaining high annotation quality. We further design a unified evaluation protocol with complementary metrics tailored for null-set rejection, positive-query localization, and end-to-end GMR performance. Finally, we establish strong baselines across two modeling paradigms: a lightweight plug-and-play GMR adapter for discriminative VMR models, and a GMR-tailored GRPO reward for fine-tuning multimodal large language models (MLLMs). Extensive experiments show consistent gains across all metrics and expose key limitations of current methods, positioning GMR as a more realistic and challenging benchmark for video-language understanding.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have only encountered some partial classes and images. Unlike other works on the NCD, we leverage the prototypes to emphasize the importance of category discrimination and alleviate the issue of missing annotations of novel classes. Concretely, we propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. In the first stage, we obtain a robust feature extractor, which could serve for all images with base and novel categories. This ability of instance and category discrimination of the feature extractor is boosted by self-supervised learning and adaptive prototypes. In the second stage, we utilize the prototypes again to rectify offline pseudo labels and train a final parametric classifier for category clustering. We conduct extensive experiments on four benchmark datasets and demonstrate the effectiveness and robustness of the proposed method with state-of-the-art performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Weakly Aligned Feature Fusion for Multimodal Object Detection

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, and depth. However, multimodal data often suffer from the position shift problem, i.e., the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multimodal features and puzzles the convolutional neural network (CNN) training. In this article, we propose a general multimodal detector named aligned region CNN (AR-CNN) to tackle the position shift problem. First, a region feature (RF) alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal RFs. Second, we propose a novel region of interest (RoI) jitter strategy to improve the robustness to unexpected shift patterns. Third, we present a new multimodal feature fusion method that selects the more reliable feature and suppresses the less useful one via feature reweighting. In addition, by locating bounding boxes in both modalities and building their relationships, we provide novel multimodal labeling named KAIST-Paired. Extensive experiments on 2-D and 3-D object detection, RGB-T, and RGB-D datasets demonstrate the effectiveness and robustness of our method.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Green Data Centers: A Survey, Perspectives, and Future Directions

At present, a major concern regarding data centers is their extremely high energy consumption and carbon dioxide emissions. However, because of the over-provisioning of resources, the utilization of existing data centers is, in fact, remarkably low, leading to considerable energy waste. Therefore, over the past few years, many research efforts have been devoted to increasing efficiency for the construction of green data centers. The goal of these efforts is to efficiently utilize available resources and to reduce energy consumption and thermal cooling costs. In this paper, we provide a survey of the state-of-the-art research on green data center techniques, including energy efficiency, resource management, thermal control and green metrics. Additionally, we present a detailed comparison of the reviewed proposals. We further discuss the key challenges for future research and highlight some future research issues for addressing the problem of building green data centers.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Multi-resource Energy-efficient Routing in Cloud Data Centers with Networks-as-a-Service

With the rapid development of software defined networking and network function virtualization, researchers have proposed a new cloud networking model called Network-as-a-Service (NaaS) which enables both in-network packet processing and application-specific network control. In this paper, we revisit the problem of achieving network energy efficiency in data centers and identify some new optimization challenges under the NaaS model. Particularly, we extend the energy-efficient routing optimization from single-resource to multi-resource settings. We characterize the problem through a detailed model and provide a formal problem definition. Due to the high complexity of direct solutions, we propose a greedy routing scheme to approximate the optimum, where flows are selected progressively to exhaust residual capacities of active nodes, and routing paths are assigned based on the distributions of both node residual capacities and flow demands. By leveraging the structural regularity of data center networks, we also provide a fast topology-aware heuristic method based on hierarchically solving a series of vector bin packing instances. Our simulations show that the proposed routing scheme can achieve significant gain on energy savings and the topology-aware heuristic can produce comparably good results while reducing the computation time to a large extent.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Single top and Higgs associated production in the minimal $B-L$ model at the LHC

In this paper, we study the single top production in association with a Higgs boson in the $U(1)_{B-L}$ extension of the Standard Model at the LHC. We calculate the production cross sections of the processes $pp\rightarrow thX(h=H_{1},H_{2};X=j,b,W)$ in this model. Then we further study the observability of the process $pp\rightarrow tH_{2}j$ through $pp\rightarrow t(\rightarrow q\bar{q'} b)H_{2}(\rightarrow 4\ell)j$. We find that the systematic significance can be improved obviously, but it is still challenging for the 14 TeV LHC with high-luminosity to detect this signal.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

A Joint Optimization of Operational Cost and Performance Interference in Cloud Data Centers

Virtual machine (VM) scheduling is an important technique to efficiently operate the computing resources in a data center. Previous work has mainly focused on consolidating VMs to improve resource utilization and thus to optimize energy consumption. However, the interference between collocated VMs is usually ignored, which can result in very worse performance degradation to the applications running in those VMs due to the contention of the shared resources. Based on this observation, we aim at designing efficient VM assignment and scheduling strategies where we consider optimizing both the operational cost of the data center and the performance degradation of running applications and then, we propose a general model which captures the inherent tradeoff between the two contradictory objectives. We present offline and online solutions for this problem by exploiting the spatial and temporal information of VMs where VM scheduling is done by jointly consider the combinations and the life-cycle overlapping of the VMs. Evaluation results show that the proposed methods can generate efficient schedules for VMs, achieving low operational cost while significantly reducing the performance degradation of applications in cloud data centers.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Energy-Efficient Flow Scheduling and Routing with Hard Deadlines in Data Center Networks

The power consumption of enormous network devices in data centers has emerged as a big concern to data center operators. Despite many traffic-engineering-based solutions, very little attention has been paid on performance-guaranteed energy saving schemes. In this paper, we propose a novel energy-saving model for data center networks by scheduling and routing "deadline-constrained flows" where the transmission of every flow has to be accomplished before a rigorous deadline, being the most critical requirement in production data center networks. Based on speed scaling and power-down energy saving strategies for network devices, we aim to explore the most energy efficient way of scheduling and routing flows on the network, as well as determining the transmission speed for every flow. We consider two general versions of the problem. For the version of only flow scheduling where routes of flows are pre-given, we show that it can be solved polynomially and we develop an optimal combinatorial algorithm for it. For the version of joint flow scheduling and routing, we prove that it is strongly NP-hard and cannot have a Fully Polynomial-Time Approximation Scheme (FPTAS) unless P=NP. Based on a relaxation and randomized rounding technique, we provide an efficient approximation algorithm which can guarantee a provable performance ratio with respect to a polynomial of the total number of flows.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Improving the Load Balance of MapReduce Operations based on the Key Distribution of Pairs

Load balance is important for MapReduce to reduce job duration, increase parallel efficiency, etc. Previous work focuses on coarse-grained scheduling. This study concerns fine-grained scheduling on MapReduce operations. Each operation represents one invocation of the Map or Reduce function. Scheduling MapReduce operations is difficult due to highly screwed operation loads, no support to collect workload statistics, and high complexity of the scheduling problem. So current implementations adopt simple strategies, leading to poor load balance. To address these difficulties, we design an algorithm to schedule operations based on the key distribution of intermediate pairs. The algorithm involves a sub-program for selecting operations for task slots, and we name it the Balanced Subset Sum (BSS) problem. We discuss properties of BSS and design exact and approximation algorithms for it. To transparently incorporate these algorithms into MapReduce, we design a communication mechanism to collect statistics, and a pipeline within Reduce tasks to increase resource utilization. To the best of our knowledge, this is the first work on scheduling MapReduce workload at this fine-grained level. Experiments on PUMA [T+12] benchmarks show consistent performance improvement. The job duration can be reduced by up to 37%, compared with standard MapReduce.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

OS4M: Achieving Global Load Balance of MapReduce Workload by Scheduling at the Operation Level

The efficiency of MapReduce is closely related to its load balance. Existing works on MapReduce load balance focus on coarse-grained scheduling. This study concerns fine-grained scheduling on MapReduce operations, with each operation representing one invocation of the Map or Reduce function. By default, MapReduce adopts the hash-based method to schedule Reduce operations, which often leads to poor load balance. In addition, the copy phase of Reduce tasks overlaps with Map tasks, which significantly hinders the progress of Map tasks due to I/O contention. Moreover, the three phases of Reduce tasks run in sequence, while consuming different resources, thereby under-utilizing resources. To overcome these problems, we introduce a set of mechanisms named OS4M (Operation Scheduling for MapReduce) to improve MapReduce's performance. OS4M achieves load balance by collecting statistics of all Map operations, and calculates a globally optimal schedule to distribute Reduce operations. With OS4M, the copy phase of Reduce tasks no longer overlaps with Map tasks, and the three phases of Reduce tasks are pipelined based on their operation loads. OS4M has been transparently incorporated into MapReduce. Evaluations on standard benchmarks show that OS4M's job duration can be shortened by up to 42%, compared with a baseline of Hadoop.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Energy-Efficient Scheduling with Time and Processors Eligibility Restrictions

While previous work on energy-efficient algorithms focused on assumption that tasks can be assigned to any processor, we initially study the problem of task scheduling on restricted parallel processors. The objective is to minimize the overall energy consumption while speed scaling (SS) method is used to reduce energy consumption under the execution time constraint (Makespan $C_{max}$). In this work, we discuss the speed setting in the continuous model that processors can run at arbitrary speed in $[s_{min},s_{max}]$. The energy-efficient scheduling problem, involving task assignment and speed scaling, is inherently complicated as it is proved to be NP-Complete. We formulate the problem as an Integer Programming (IP) problem. Specifically, we devise a polynomial time optimal scheduling algorithm for the case tasks have a uniform size. Our algorithm runs in $O(mn^3logn)$ time, where $m$ is the number of processors and $n$ is the number of tasks. We then present a polynomial time algorithm that achieves an approximation factor of $2^{α-1}(2-\frac{1}{m^α})$ ($α$ is the power parameter) when the tasks have arbitrary size work. Experimental results demonstrate that our algorithm could provide an efficient scheduling for the problem of task scheduling on restricted parallel processors.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

GreenDCN: a General Framework for Achieving Energy Efficiency in Data Center Networks

The popularization of cloud computing has raised concerns over the energy consumption that takes place in data centers. In addition to the energy consumed by servers, the energy consumed by large numbers of network devices emerges as a significant problem. Existing work on energy-efficient data center networking primarily focuses on traffic engineering, which is usually adapted from traditional networks. We propose a new framework to embrace the new opportunities brought by combining some special features of data centers with traffic engineering. Based on this framework, we characterize the problem of achieving energy efficiency with a time-aware model, and we prove its NP-hardness with a solution that has two steps. First, we solve the problem of assigning virtual machines (VM) to servers to reduce the amount of traffic and to generate favorable conditions for traffic engineering. The solution reached for this problem is based on three essential principles that we propose. Second, we reduce the number of active switches and balance traffic flows, depending on the relation between power consumption and routing, to achieve energy conservation. Experimental results confirm that, by using this framework, we can achieve up to 50 percent energy savings. We also provide a comprehensive discussion on the scalability and practicability of the framework.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Routing for Energy Minimization with Discrete Cost Functions

Energy saving is becoming an important issue in the design and use of computer networks. In this work we propose a problem that considers the use of rate adaptation as the energy saving strategy in networks. The problem is modeled as an integral demand-routing problem in a network with discrete cost functions at the links. The discreteness of the cost function comes from the different states (bandwidths) at which links can operate and, in particular, from the energy consumed at each state. This in its turn leads to the non-convexity of the cost function, and thus adds complexity to solve this problem. We formulate this routing problem as an integer program, and we show that the general case of this problem is NP-hard, and even hard to approximate. For the special case when the step ratio of the cost function is bounded, we show that effective approximations can be obtained. Our main algorithm executes two processes in sequence: relaxation and rounding. The relaxation process eliminates the non-convexity of the cost function, so that the problem is transformed into a fractional convex program solvable in polynomial time. After that, a randomized rounding process is used to get a feasible solution for the original problem. This algorithm provides a constant approximation ratio for uniform demands and an approximation ratio of $O(\log^{β-1} d)$ for non-uniform demands, where $β$ is a constant and $d$ is the largest demand.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

Observation of Interplanetary Scintillation with Single-Station Mode at Urumqi

The Sun affects the Earth's physical phenomena in multiple ways, in particular the material in interplanetary space comes from coronal expansion in the form of inhomogeneous plasma flow (solar wind), which is the primary source of the interplanetary medium. Ground-based Interplanetary Scintillation (IPS) observations are an important and effective method for measuring solar wind speed and the structures of small diameter radio sources. We discuss one mode of ground-based single-station observations: Single-Station Single-Frequency (SSSF) mode. To realize the SSSF mode, a new system has been established at Urumqi Astronomical Observatory (UAO), China, and a series of experimental observations were carried out successfully from May to December, 2008.

0 citations0 reviewsNo code linkedOpen access