检索结果-内蒙古大学图书馆

Multi-video Moment Ranking with Multimodal Clue

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hou, Danyang Pang, Liang Lan, Yanyan Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology CAS Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China

Video corpus moment retrieval (VCMR) is the task of retrieving a relevant video moment from a large corpus of untrimmed videos via a natural language query. State-of-the-art work for VCMR is based on two-stage method. In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference. (2) Latent key content: Different modalities of video have different key information for moment localization. To this end, we propose a two-stage model MultI-video raNking with mUlTimodal cluE (MINUTE). MINUTE uses Shared Normalization during both training and inference to rank candidate moments from multiple videos to solve moment predict bias, making it more efficient to predict target moment. In addition, Mutilmdaol Clue Mining (MCM) of MINUTE can discover key content of different modalities in video to localize moment more accurately. MINUTE outperforms the baselines on TVR and DiDeMo datasets, achieving a new state-of-the-art of VCMR. Our code will be available at GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Mingkun Bi, Keping Chen, Wei Chen, Quanrun Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS China School of Statistics University of International Business and Economics China CAS stands for Chinese Academy of Sciences China

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/TMLResearchGroup-cas/CausalDiff. Copyright © 2024, The Authors. All rights reserved.

关键词： Traffic signs

Beyond precision: A study on recall of initial retrieval with neural representations

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xiao, Yan Guo, Jiafeng Fan, Yixing Lan, Yanyan Xu, Jun Cheng, Xueqi University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic relatedness, leading to new possibilities to alleviate the vocabulary mismatch problem in IR. However, most existing efforts in this direction have been devoted to the re-ranking stage. That is to leverage neural representations to help re-rank a set of candidate documents, which are typically obtained from an initial retrieval stage based on some symbolic index and search scheme (e.g., BM25 over the inverted index). This naturally raises a question: If the relevant documents have not been found in the initial retrieval stage due to vocabulary mismatch, there would be no chance to re-rank them to the top positions later. Therefore, in this paper, we study the problem how to employ neural representations to improve the recall of relevant documents in the initial retrieval stage. Specifically, to meet the efficiency requirement of the initial stage, we introduce a neural index for the neural representations of documents, and propose two hybrid search schemes based on both neural and symbolic indices, namely the parallel search scheme and the sequential search scheme. Our experiments show that both hybrid index and search schemes can improve the recall of the initial retrieval stage with small overhead. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

Freeway: Adaptively isolating the elephant and mice flows on different transmission paths 22

学校读者我要写书评

暂无评论

Freeway: Adaptively isolating the elephant and mice flows on...

22nd IEEE International Conference on network Protocols, ICNP 2014

作者： Wang, Wei Sun, Yi Zheng, Kai Kaafar, Mohamed Ali Li, Dan Li, Zhongcheng Institute of Computing Technology CAS China State Key Laboratory of Networking and Switching Technology China University of Chinese Academy of Science China IBM China Research Lab China NICTA China Tsinghua University China

ISBN: (纸本)9781479962044

The network resource competition of today' data enters is extremely intense between long-lived elephant flows and latency-sensitive mice flows. Achieving both goals of high throughput and low latency respectively for the two types of flows requires compromise, which recent research has not successfully solved mainly due to the transfer of elephant and mice flows on shared links without any differentiation. However, current data enters usually adopt clos-based topology, e.g. Fat-tree/VL2, so there exist multiple shortest paths between any pair of source and destination. In this paper, we leverage on this observation to propose a flow scheduling scheme, Freeway, to adaptively partition the transmission paths into low latency paths and high throughput paths respectively for the two types of flows. An algorithm is proposed to dynamically adjust the number of the two types of paths according to the real-time traffic. And based on these separated transmission paths, we propose different flow type-specific scheduling and forwarding methods to make full utilization of the bandwidth. Our simulation results show that Freeway significantly reduces the delay of mice flow by 85.8% and achieves 9.2% higher throughput compared with Hedera. © 2014 IEEE.

关键词： Scheduling

Combat data shift in few-shot learning with knowledge graph

学校读者我要写书评

暂无评论

Frontiers of Computer science 2023年第1期17卷 101-111页

作者： Yongchun ZHU Fuzhen ZHUANG Xiangliang ZHANG Zhiyuan QI Zhiping SHI Juan CAO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Xiamen Institute of Data Intelligence Xiamen 361021China Computer Science and Engineering University of Notre DameIN 46556USA University of California San Diego La JollaCA 92093USA College of Information Engineering&Academy for Multidisciplinary Studies Capital Normal UniversityBeijing 100089China

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance.

关键词： few-shot data shift knowledge graph

Accurate Recovery of Internet Traffic data: A Sequential Tensor Completion Approach

学校读者我要写书评

暂无评论

Accurate Recovery of Internet Traffic Data: A Sequential Ten...

作者： Xie, Kun Wang, Lele Wang, Xin Xie, Gaogang Wen, Jigang Zhang, Guangxing Cao, Jiannong Zhang, Dafang College of Computer Science and Electronics Engineering Hunan University Changsha410006 China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Electrical and Computer Engineering State University of New York at Stony Brook Stony BrookNY11794 United States Network Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong

The inference of traffic volume of the whole network from partial traffic measurements becomes increasingly critical for various network engineering tasks, such as capacity planning and anomaly detection. Previous studies indicate that the matrix completion is a possible solution for this problem. However, as a 2-D matrix cannot sufficiently capture the spatial-temporal features of traffic data, these approaches fail to work when the data missing ratio is high. To fully exploit hidden spatial-temporal structures of the traffic data, this paper models the traffic data as a 3-way traffic tensor and formulates the traffic data recovery problem as a low-rank tensor completion problem. However, the high computation complexity incurred by the conventional tensor completion algorithms prevents its practical application for the traffic data recovery. To reduce the computation cost, we propose a novel sequential tensor completion algorithm, which can efficiently exploit the tensor decomposition result based on the previous traffic data to derive the tensor decomposition upon arriving of new data. Furthermore, to better capture the changes of data correlation over time, we propose a dynamic sequential tensor completion algorithm. To the best of our knowledge, we are the first to propose sequential tensor completion algorithms to significantly speed up the traffic data recovery process. This facilitates the modeling of Internet traffic with the tensor to well exploit the hidden structures of traffic data for more accurate missing data inference. We have done extensive simulations with the real traffic trace as the input. The simulation results demonstrate that our algorithms can achieve significantly better performance compared with the literature tensor and matrix completion algorithms even when the data missing ratio is high. © 1993-2012 IEEE.

关键词： Tensors

Strong quantum nonlocality without entanglement in multipartite quantum systems

学校读者我要写书评

暂无评论

Physical Review A 2020年第4期102卷 042228-042228页

作者： Pei Yuan Guojing Tian Xiaoming Sun CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences 100190 Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100049 China CAS Center of Excellence in Topological Quantum Computation Beijing 100049 China

In this paper, we generalize the concept of strong quantum nonlocality from two aspects. First, in a tripartite quantum system, we present a construction of strongly nonlocal quantum states containing 6(d−1)2 orthogonal product states in Cd⊗Cd⊗Cd and build 6d2−8d+4 product states in Cd⊗Cd⊗Cd+1, which have been proved to be strongly nonlocal. Obviously, both results turn out to be one order of magnitude smaller than the number of basis states d3 for d≥3. Second, we give explicit forms of strongly nonlocal orthogonal product basis in C3⊗C3⊗C3⊗C3 and C4⊗C4⊗C4⊗C4 quantum systems, where four is the largest known number of subsystems in which there exists strong quantum nonlocality without entanglement up to now. All the results positively answer the open problems raised by Halder et al. [Phys. Rev. Lett. 122, 040403 (2019)]; that is, there do exist a small number of quantum states that can demonstrate strong quantum nonlocality without entanglement.

关键词： Nonlocality

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Yunchang Pang, Liang Lan, Yanyan Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Cas University of Chinese Academy of Sciences Beijing China Data Intelligence System Research Center Institute of Computing Technology Cas Beijing China Institute for Ai Industry Research Tsinghua University Beijing China Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Cas University of Chinese Academy of Sciences Beijing China

Pseudo-relevance feedback (PRF) has proven to be an effective query reformulation technique to improve retrieval accuracy. It aims to alleviate the mismatch of linguistic expressions between a query and its potential relevant documents. Existing PRF methods independently treat revised queries originating from the same query but using different numbers of feedback documents, resulting in severe query drift. Without comparing the effects of two different revisions from the same query, a PRF model may incorrectly focus on the additional irrelevant information increased in the more feedback, and thus reformulate a query that is less effective than the revision using the less feedback. Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be. To bridge this gap, we propose the Loss-over-Loss (LoL) framework to compare the reformulation losses between different revisions of the same query during training. Concretely, we revise an original query multiple times in parallel using different amounts of feedback and compute their reformulation losses. Then, we introduce an additional regularization loss on these reformulation losses to penalize revisions that use more feedback but gain larger losses. With such comparative regularization, the PRF model is expected to learn to suppress the extra increased irrelevant information by comparing the effects of different revised queries. Further, we present a differentiable query reformulation method to implement this framework. This method revises queries in the vector space and directly optimizes the retrieval performance of query vectors, applicable for both sparse and dense retrieval models. Empirical evaluation demonstrates the effectiveness and robustness of our method for two typical sparse and dense retrieval models. © 2022, CC BY.

关键词： Feedback

An In-Context Schema Understanding Method for Knowledge Base Question Answering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yantao Li, Zixuan Jin, Xiaolong Guo, Yucao Bai, Long Guan, Saiping Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

The Knowledge Base Question Answering (KBQA) task aims to answer natural language questions based on a given knowledge base. Recently, Large Language Models (LLMs) have shown strong capabilities in language understanding and can be used to solve this task. In doing so, a major challenge for LLMs is to overcome the immensity and heterogeneity of knowledge base schemas. Existing methods bypass this challenge by initially employing LLMs to generate drafts of logic forms without schema-specific details. Then, an extra module is used to inject schema information to these drafts. In contrast, in this paper, we propose a simple In-Context Schema Understanding (ICSU) method that enables LLMs to directly understand schemas by leveraging in-context learning. Specifically, ICSU provides schema information to LLMs using schema-related annotated examples. We investigate three example retrieval strategies based on raw questions, anonymized questions, and generated SPARQL queries. Experimental results show that ICSU demonstrates competitive performance compared to baseline methods on both the KQA Pro and WebQSP datasets. © 2023, CC BY.

关键词： Knowledge based systems