检索结果-内蒙古大学图书馆

ControlVideo: conditional control for one-shot text-driven video editing and beyond

Science China(Information Sciences) 2025年第3期68卷 150-162页

作者： Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML CenterTsinghua Laboratory of Brain and Intelligence Lab Tsinghua University ShengShu Technology Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Pazhou Laboratory (Huangpu)

This paper presents ControlVideo for text-driven video editing — generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions(such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing(e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous studies achieved. The code is available at https://***/thu-ml/controlvideo.

关键词： diffusion models controllable generation text-driven editing video editing long video editing

来源：评论

学校读者我要写书评

暂无评论

ICLEval: Evaluating In-Context Learning Ability of Large Language Models 31

ICLEval: Evaluating In-Context Learning Ability of Large Lan...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Wentong Lin, Yankai Zhou, ZhenHao Huang, HongYun Jia, Yantao Cao, Zhao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Huawei Poisson Lab China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Information Renmin University of China China

ISBN: (纸本)9798891761964

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our understanding of how this ability is acquired at the training stage. However, existing evaluation frameworks primarily focus on language abilities and knowledge, often overlooking the assessment of ICL ability. In this work, we introduce the ICLEval benchmark to evaluate the ICL abilities of LLMs, which encompasses two key sub-abilities: exact copying and rule learning. Through the ICLEval benchmark, we demonstrate that ICL ability is universally present in different LLMs, and model size is not the sole determinant of ICL efficacy. Surprisingly, we observe that ICL abilities, particularly copying, develop early in the pretraining process and stabilize afterward. Our source codes and benchmark are released at https://***/RUCBM/ICLEval. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A General Multi-Context Embedding Model for Mining Human Trajectory data

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2016年第8期28卷 1945-1958页

作者： Zhou, Ningnan Zhao, Wayne Xin Zhang, Xiao Wen, Ji-Rong Wang, Shan Renmin Univ China Sch Informat Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

The proliferation of location-based social networks, such as Foursquare and Facebook Places, offers a variety of ways to record human mobility, including user generated geo-tagged contents, check-in services, and mobile apps. Although trajectory data is of great value to many applications, it is challenging to analyze and mine trajectory data due to the complex characteristics reflected in human mobility, which is affected by multiple contextual information. In this paper, we propose a Multi-Context Trajectory Embedding Model, called MC-TEM, to explore contexts in a systematic way. MC-TEM is developed in the distributed representation learning framework, and it is flexible to characterize various kinds of useful contexts for different applications. To the best of our knowledge, it is the first time that the distributed representation learning methods apply to trajectory data. We formally incorporate multiple context information of trajectory data into the proposed model, including user-level, trajectory-level, location-level, and temporal contexts. All the context information is represented in the same embedding space. We apply MC-TEM to two challenging tasks, namely location recommendation and social link prediction. We conduct extensive experiments on three real-world datasets. Extensive experiment results have demonstrated the superiority of our MC-TEM model over several state-of-the-art methods.

关键词： Human trajectory distributed representation contextual information location recommendation social link prediction

来源：评论

学校读者我要写书评

暂无评论

AP-GAN: Adversarial patch attack on content-based image retrieval systems

引用

GEOINFORMATICA 2022年第2期26卷 347-377页

作者： Zhao, Guoping Zhang, Mingyu Liu, Jiajun Li, Yaxian Wen, Ji-Rong Renmin Univ China Sch Informat Beijing 100872 Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

key Smart City applications such as traffic management and public security rely heavily on the intelligent processing of video and image data, often in the form of visual retrieval tasks, such as person Re-IDentification (ReID) and vehicle re-identification. For these tasks, Deep Neural Networks (DNNs) have been the dominant solution for the past decade, for their remarkable ability in learning discriminative features from images to boost retrieval performance. However, it is been discovered that DNNs are broadly vulnerable to maliciously constructed adversarial examples. By adding small perturbations to a query image, the returned retrieval results will be completely dissimilar from the query image. This poses serious challenges to vital systems in Smart City applications that depend on the DNN-based visual retrieval technology, as in the physical world, simple camouflage can be added on the subject (a few patches on the body or car), and turn the subject completely untrackable by person or vehicle Re-ID systems. To demonstrate the potential of such threats, this paper proposes a novel adversarial patch generative adversarial network (AP-GAN) to generate adversarial patches instead of modifying the entire image, which also causes the DNNs-based image retrieval models to return incorrect results. AP-GAN is trained in an unsupervised way that requires only a small amount of unlabeled data for training. Once trained, it produces query-specific perturbations for query images to form adversarial queries. Extensive experiments show that the AP-GAN achieves excellent attacking performance with various application scenarios that are based on deep features, including image retrieval, person ReID and vehicle ReID. The results of this study provide a warning that when deploying a DNNs-based image retrieval system, its security and robustness needs to be thoroughly considered.

关键词： Adversarial attack Adversarial patch Image retrieval GAN

来源：评论

学校读者我要写书评

暂无评论

Accelerating exploitation and integration of global renewable energy

引用

Innovation 2025年

作者： Wang, Jianxiao Chen, Xinjiang Zhuang, Minghao Li, Yan Ruan, Ziwen Wang, Yuhan Zhang, Ning Song, Jie He, Kebin Lu, Xi National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing100871 China Department of Industrial Engineering and Management College of Engineering Peking University Beijing100871 China Peking University Ordos Research Institute of Energy Ordos017000 China State Key Laboratory of Nutrient Use and Management College of Resources and Environmental Sciences China Agricultural University Beijing100193 China College of Environmental Science and Engineering Tongji University Shanghai200092 China School of Environment State Key Joint Laboratory of Environment Simulation and Pollution Control Tsinghua University Beijing100084 China State Key Lab of Power Systems Department of Electrical Engineering Tsinghua University Beijing100084 China Institute for Carbon Neutrality Tsinghua University Beijing100084 China

来源：评论

学校读者我要写书评

暂无评论

A Gain-Tuning Dynamic Negative Sampler for Recommendation 22

A Gain-Tuning Dynamic Negative Sampler for Recommendation

引用

31st ACM Web Conference (WWW)

作者： Qiannan Zhu Zhang, Haobo Qing He Dou, Zhicheng Renmin Univ China Beijing Key Lab Big Data Management & Anal Method Gaoling Sch Artificial Intelligence Beijing Peoples R China Renmin Univ China Sch Informat Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China Renmin Univ China Sch Finance Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

ISBN: (纸本)9781450390965

Selecting reliable negative training instances is the challenging task in the implicit feedback-based recommendation, which is optimized by pairwise learning on user feedback data. The existing methods usually exploit various negative samplers (i.e., heuristic-based or GAN-based sampling) on user feedback data to improve the quality of negative samples. However, these methods usually focused on maintaining the hard negative samples with a high gradient for training, causing the false negative samples to be selected preferentially. The limitation of the false negative noise amplification may lead to overfitting and further poor generalization of the model. To address this issue, we propose a Gain-Tuning Dynamic Negative Sampling GDNS to make the recommendation more robust and effective. Our proposed model designs an expectational gain sampler, concerning the expectation of user' preference gap between the positive and negative samples in training, to guide the negative selection dynamically. This gain-tuning negative sampler can effectively identify the false negative samples and further diminish the risk of introducing false negative instances. Moreover, for improving the training efficiency, we construct positive and negative groups for each user in each iteration, and develop a group-wise optimizer to optimize them in a cross manner. Experiments on two real-world datasets show our approach significantly outperforms state-of-the-art negative sampling baselines.

关键词： Recommendation system Negative sampler Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Deep cross-platform product matching in e-commerce

引用

INFORMATION RETRIEVAL JOURNAL 2020年第2期23卷 136-158页

作者： Li, Juan Dou, Zhicheng Zhu, Yutao Zuo, Xiaochen Wen, Ji-Rong Renmin Univ China Sch Informat Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

Online shopping has become more and more popular in recent years, which leads to a prosperity on online platforms. Generally, the identical products are provided by many sellers on multiple platforms. Thus the comparison between products on multiple platforms becomes a basic demand for both consumers and sellers. However, identifying identical products on multiple platforms is difficult because the description for a certain product can be various. In this work, we propose a novel neural matching model to solve this problem. Two kinds of descriptions (i.e. product titles and attributes), which are widely provided on online platforms, are considered in our method. We conduct experiments on a real-world data set which contains thousands of products on two online e-commerce platforms. The experimental results show that our method can take use of the product information contained in both titles and attributes and significantly outperform the state-of-the-art matching models.

关键词： Product matching Neural network Text matching

来源：评论

学校读者我要写书评

暂无评论

Curriculum Pre-training Heterogeneous Subgraph Transformer for Top-N Recommendation

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2023年第1期41卷 1-28页

作者： Wang, Hui Zhou, Kun Zhao, Xin Wang, Jingyuan Wen, Ji-Rong Renmin Univ China Sch Informat Beijing Key Lab Big Data Management & Anal Method Beijing 100872 Peoples R China Renmin Univ China Beijing Key Lab Big Data Management & Anal Method Gaoling Sch Artificial Intelligence Beijing 100872 Peoples R China Beihang Univ Lab Low Carbon Intelligent Governance Sch Comp Sci & Engn Beijing 100191 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Renmin Univ China Beijing Key Lab Big Data Management & Anal Method Sch Informat Gaoling Sch Artificial Intelligence Beijing 100872 Peoples R China

To characterize complex and heterogeneous side information in recommender systems, the heterogeneous information network (HIN) has shown superior performance and attracted much research attention. In HIN, the rich entities, relations, and paths can be utilized to model the correlations of users and items;such a task setting is often called HIN-based recommendation. Although HIN provides a general approach to modeling rich side information, it lacks special consideration on the goal of the recommendation task. The aggregated context from the heterogeneous graph is likely to incorporate irrelevant information, and the learned representations are not specifically optimized according to the recommendation task. Therefore, there is a need to rethink how to leverage the useful information from HIN to accomplish the recommendation task. To address the above issues, we propose a Curriculum pre-training based HEterogeneous Subgraph Transformer (called CHEST) with new data characterization, representation model, and learning algorithm. Specifically, we consider extracting useful information from HIN to compose the interaction-specific heterogeneous subgraph, containing highly relevant context information for recommendation. Then, we capture the rich semantics (e.g., graph structure and path semantics) within the subgraph via a heterogeneous subgraph Transformer, where we encode the subgraph into multi-slot sequence representations. Besides, we design a curriculum pre-training strategy to provide an elementary-to-advanced learning process. The elementary course focuses on capturing local context information within the subgraph, and the advanced course aims to learn global context information. In this way, we gradually capture useful semantic information from HIN for modeling user-item interactions. Extensive experiments conducted on four real-world datasets demonstrate the superiority of our proposed method over a number of competitive baselines, especially when only limited t

关键词： Curriculum pre-training heterogeneous information network recommender systems

来源：评论

学校读者我要写书评

暂无评论

Modeling the Parameter Interactions in Ranking SVM with Low-Rank Approximation

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2019年第6期31卷 1181-1193页

作者： Xu, Jun Zeng, Wei Lan, Yanyan Guo, Jiafeng Cheng, Xueqi Renmin Univ China Sch Informat Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China Chinese Acad Sci Inst Comp Technol CAS Key Lab Network Data Sci & Technol Beijing Peoples R China

Ranking SVM, which formalizes the problem of learning a ranking model as that of learning a binary SVM on preference pairs of documents, is a state-of-the-art ranking model in information retrieval. The dual form solution of a linear Ranking SVM model can be written as a linear combination of the preference pairs, i.e., w = Sigma((i,j)) alpha(ij) (x(i) - x(j)), where alpha(ij) denotes the Lagrange parameters associated with each preference pair (i, j). It is observed that there exist obvious interactions among the document pairs because two preference pairs could share a same document as their items, e.g., preference pairs (d(1), d(2)) and (d(1), d(3)) share the document d(1). Thus it is natural to ask if there also exist interactions over the model parameters alpha(ij), which may be leveraged to construct better ranking models. This paper aims to answer the question. We empirically found that there exists a low-rank structure over the rearranged Ranking SVM model parameters alpha(ij), which indicates that the interactions do exist. Based on the discovery, we made modifications on the original Ranking SVM model by explicitly applying low-rank constraints to the Lagrange parameters, achieving two novel algorithms called Factorized Ranking SVM and Regularized Ranking SVM, respectively. Specifically, in Factorized Ranking SVM each parameter alpha(ij) is decomposed as a product of two low-dimensional vectors, i.e., alpha(ij) = < v(i), v(j)>, where vectors v(i) and v(j) correspond to document i and j, respectively;In Regularized Ranking SVM, a nuclear norm is applied to the rearranged parameters matrix for controlling its rank. Experimental results on three LETOR datasets show that both of the proposed methods can outperform state-of-the-art learning to rank models including the conventional Ranking SVM.

关键词： Learning to rank ranking SVM parameter interactions low-rank approximation

来源：评论

学校读者我要写书评

暂无评论

Improving First-stage Retrieval of Point-of-interest Search by Pre-training Models

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2024年第3期42卷 1-27页

作者： Mei, Lang Mao, Jiaxin Hu, Juan Tan, Naiqiang Chai, Hua Wen, Ji-Rong Renmin Univ China Beijing Key Lab Big Data Management & Anal Method Gaoling Sch Artificial Intelligence Beijing 100872 Peoples R China Didi Chuxing Beijing Peoples R China

Point-of-interest (POI) search is important for location-based services, such as navigation and online ride-hailing service. The goal of POI search is to find the most relevant destinations from a large-scale POI database given a text query. To improve the effectiveness and efficiency of POI search, most existing approaches are based on a multi-stage pipeline that consists of an efficiency-oriented retrieval stage and one or more effectiveness-oriented re-rank stages. In this article, we focus on the first efficiency-oriented retrieval stage of the POI search. We first identify the limitations of existing first-stage POI retrieval models in capturing the semantic-geography relationship and modeling the fine-grained geographical context information. Then, we propose a Geo-Enhanced Dense Retrieval framework for POI search to alleviate the above problems. Specifically, the proposed framework leverages the capacity of pre-trained language models (e.g., BERT) and designs a pre-training approach to better model the semantic match between the query prefix and POIs. With the POI collection, we first perform a token-level pre-training task based on a geographical-sensitive masked language prediction and design two retrieval-oriented pre-training tasks that link the address of each POI to its name and geo-location. With the user behavior logs collected from an online POI search system, we design two additional pre-training tasks based on users' query reformulation behavior and the transitions between POIs. We also utilize a late-interaction network structure to model the fine-grained interactions between the text and geographical context information within an acceptable query latency. Extensive experiments on the real-world datasets collected from the Didichuxing application demonstrate that the proposed framework can achieve superior retrieval performance over existing first-stage POI retrieval methods.

关键词： Point-of-interest (POI) Search First-stage Retrieval Pre-training Model Interaction-based Model Geographical Context User Behavior

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：