检索结果-内蒙古大学图书馆

Siamese transformer with hierarchical concept embedding for fine-grained image recognition

Science China(Information Sciences) 2023年第3期66卷 188-203页

作者： Yilin LYU Liping JING Jiaqi WANG Mingzhe GUO Xinyue WANG Jian YU School of Computer and Information Technology Beijing Jiaotong University Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Alibaba Group

Distinguishing the subtle differences among fine-grained images from subordinate concepts of a concept hierarchy is a challenging task. In this paper, we propose a Siamese transformer with hierarchical concept embedding(STr HCE), which contains two transformer subnetworks sharing all configurations,and each subnetwork is equipped with the hierarchical semantic information at different concept levels for fine-grained image embeddings. In particular, one subnetwork is for coarse-scale patches to learn the discriminative regions with the aid of the innate multi-head self-attention mechanism of the transformer. The other subnetwork is for finer-scale patches, which are adaptively sampled from the discriminative regions, to capture subtle yet discriminative visual cues and eliminate redundant information. STr HCE connects the two subnetworks through a score margin adjustor to enforce the most discriminative regions generating more confident predictions. Extensive experiments conducted on four commonly-used benchmark datasets, including CUB-200-2011, FGVC-Aircraft, Stanford Dogs, and NABirds, empirically demonstrate the superiority of the proposed STr HCE over state-of-the-art baselines.

关键词： fine-grained image recognition transformer hierarchical concept embedding adaptive sampling Siamese network

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Enhancing Rumor Detection Methods with Propagation Structure Infused Language Model 31

Enhancing Rumor Detection Methods with Propagation Structure...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cui, Chaoqun Li, Siyuan Ma, Kunkun Jia, Caiyan School of Computer Science and Technology & Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9798891761964

Pretrained Language Models (PLMs) have excelled in various Natural Language Processing tasks, benefiting from large-scale pretraining and self-attention mechanism's ability to capture long-range dependencies. However, their performance on social media application tasks like rumor detection remains suboptimal. We attribute this to mismatches between pretraining corpora and social texts, inadequate handling of unique social symbols, and pretraining tasks ill-suited for modeling user engagements implicit in propagation structures. To address these issues, we propose a continue pretraining strategy called Post Engagement Prediction (PEP) to infuse information from propagation structures into PLMs. PEP makes models to predict root, branch, and parent relations between posts, capturing interactions of stance and sentiment crucial for rumor detection. We also curate and release large-scale Twitter corpus: TwitterCorpus (269GB text), and two unlabeled claim conversation datasets with propagation structures (UTwitter and UWeibo). Utilizing these resources and PEP strategy, we train a Twitter-tailored PLM called SoLM. Extensive experiments demonstrate PEP significantly boosts rumor detection performance across universal and social media PLMs, even in few-shot scenarios. On benchmark datasets, PEP enhances baseline models by 1.0-3.7% accuracy, even enabling it to outperform current state-of-the-art methods on multiple datasets. SoLM alone, without high-level modules, also achieves competitive results, highlighting the strategy's effectiveness in learning discriminative post interaction features. © 2025 Association for Computational Linguistics.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Towards Real-World Rumor Detection: Anomaly Detection Framework with Graph Supervised Contrastive Learning 31

Towards Real-World Rumor Detection: Anomaly Detection Framew...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cui, Chaoqun Jia, Caiyan School of Computer Science and Technology & Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9798891761964

Current rumor detection methods based on propagation structure learning predominately treat rumor detection as a class-balanced classification task on limited labeled data. However, real-world social media data exhibits an imbalanced distribution with a minority of rumors among massive regular posts. To address the data scarcity and imbalance issues, we construct two large-scale conversation datasets from Weibo and Twitter and analyze the domain distributions. We find obvious differences between rumor and non-rumor distributions, with non-rumors mostly in entertainment domains while rumors concentrate in news, indicating the conformity of rumor detection to an anomaly detection paradigm. Correspondingly, we propose the Anomaly Detection framework with Graph Supervised Contrastive Learning (AD-GSCL). It heuristically treats unlabeled data as non-rumors and adapts graph contrastive learning for rumor detection. Extensive experiments demonstrate AD-GSCL's superiority under class-balanced, imbalanced, and few-shot conditions. Our findings provide valuable insights for real-world rumor detection featuring imbalanced data distributions. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation

ICL: Iterative Continual Learning for Multi-domain Neural Ma...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Man, Zhibo Huang, Kaiyu Zhang, Yujie Chen, Yuanmeng Chen, Yufeng Xu, Jinan Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science and Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798891761681

In a practical scenario, multi-domain neural machine translation (MDNMT) aims to continuously acquire knowledge from new domain data while retaining old *** work separately learns each new domain knowledge based on parameter isolation methods, which effectively capture the new ***, task-specific parameters lead to isolation between models, which hinders the mutual transfer of knowledge between new *** the scarcity of domain-specific corpora, we consider making full use of the data from multiple new ***, our work aims to leverage previously acquired domain knowledge when modeling subsequent *** this end, we propose an Iterative Continual Learning (ICL) framework for multi-domain neural machine ***, when each new domain arrives, (1) we first build a pluggable incremental learning model, (2) then we design an iterative updating algorithm to continuously update the original model, which can be used flexibly for constructing subsequent domain ***, we design a domain knowledge transfer mechanism to enhance the fine-grained domain-specific representation, thereby solving the word ambiguity caused by mixing domain *** results on the UM-Corpus and OPUS multi-domain datasets show the superior performance of our proposed model compared to representative baselines. © 2024 Association for Computational Linguistics.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification 30

Context-Aware Non-Autoregressive Document-Level Translation ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yu, Hao Huang, Kaiyu Zhao, Anqi Liu, Junpeng Huang, Degen School of Computer Science and Technology Dalian University of Technology China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China

ISBN: (纸本)9782493814104

Previous studies employ the autoregressive translation (AT) paradigm in the document-to-document neural machine translation. These methods extend the translation unit from a single sentence to a pseudo-document and encode the full pseudo-document, avoiding the redundant computation problem in context. However, the AT methods cannot parallelize decoding and struggle with error accumulation, especially when the length of sentences increases. In this work, we propose a context-aware non-autoregressive framework with the sentence-aligned connectionist temporal classification (SA-CTC) loss for document-level neural machine translation. In particular, the SA-CTC loss reduces the search space of the decoding path by fixing the positions of the beginning and end tokens for each sentence in the document. Meanwhile, the context-aware architecture introduces preset nodes to represent sentence-level information and utilizes a hierarchical attention structure to regulate the attention hypothesis space. Experimental results show that our proposed method can achieve competitive performance compared with several strong baselines. Our method implements non-autoregressive modeling in Doc-to-Doc translation manner, achieving an average 46X decoding speedup compared to the document-level AT baselines on three benchmarks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Leveraging implicit social structures for recommendation via a Bayesian generative model

引用

Science China(Information Sciences) 2022年第4期65卷 269-271页

作者： Huafeng LIU Jingxuan WEN Liping JING Jian YU School of Computer and Information Technology Beijing Jiaotong University Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University

Dear editor,Social recommendation leverages the social relations between users and their past behaviors to model user preferences. While social recommendation is a core component in recommendation systems, discovering... 详细信息

关键词： Recommendation system Collaborative filtering Social recommendation Social networks Generative model

来源：评论

学校读者我要写书评

暂无评论

Spatial-Angular Multi-Scale Mechanism for Light Field Spatial Super-Resolution

Spatial-Angular Multi-Scale Mechanism for Light Field Spatia...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Gao, Chen Lin, Youfang Chang, Song Zhang, Shuo School of Computer and Information Technology Beijing Jiaotong University Beijing Key Lab of Traffic Data Analysis and Mining China

ISBN: (纸本)9798350302493

Light Field (LF) cameras are promising due to their ability to capture both spatial and angular information of scenes. However, the trade-off between spatial and angular resolution significantly limits the real-world applications. In this paper, we propose a spatial-angular multi-scale decoupling network to reconstruct high-resolution LF images. Considering the epipolar geometry, we propose a spatial-angular multi-scale processing approach to explore the correspondence of sub-pixel information with different disparity ranges between sub-aperture images in LFs. We extract sub-pixel information from various dimensions and fuse it to generate global high-frequency details. Finally, we combine upsampled low-frequency and high-frequency details to generate high resolution results. To further filter the correct interpolation information, we use the shear operation to change the disparity range of the LF images and fine-tune the results. Experimental results on synthetic and real-world datasets demonstrate that our method outperforms other state-of-the-art methods in visual and numerical evaluations, especially on datasets with small disparity ranges. Furthermore, our approach fully considers the epipolar geometry of the LF image, enabling us to recover information that better maintains the imaging consistency of the LF. © 2023 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

LMDTA: Molecular Pre-trained and Interaction Fine-tuned Attention Neural Network for Drug-Target Affinity Prediction

LMDTA: Molecular Pre-trained and Interaction Fine-tuned Atte...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Hu, Minjie Yang, Kuo Xu, Kuan Zhou, Xuezhong Beijing Jiaotong University Institute of Medical Intelligence Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing China

ISBN: (纸本)9798350386226

Accurately predicting drug-target binding affinity is crucial for advancing drug discovery. Recent molecular pre-training models and biological large models provide general molecular representations, but effectively leveraging these features for specific tasks like Drug-Target Affinity (DTA) prediction remains challenging. To address this, we propose LMDTA, a novel attention-based neural network combining molecular pre-training with interaction fine-tuning for affinity prediction. LMDTA learns complex drug and protein representations through pre-trained models, while fine-tuning an interaction-specific model for the DTA task. The two-side attention mechanism integrates pre-trained and fine-tuned features, capturing key drug-target interactions. Experiments on benchmark datasets show LMDTA achieves state-of-the-art performance, with ablation studies validating the model's design. © 2024 IEEE.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach to Improve Low-Resource Machine Translation Leveraging Domain Monolingual data 30

A Reinforcement Learning Approach to Improve Low-Resource Ma...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Hongxiao Liu, Mingtong Li, Chunyou Chen, Yufeng Xu, Jinan Zhou, Ming Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Beijing Lanzhou Technology Co. Ltd. Beijing China

ISBN: (纸本)9782493814104

Due to the lack of parallel data, the mainstream fine-tuning-based domain adaptation methods have the overfitting problem in the translation of low-resource domains, and it is difficult for the model to learn the in-domain generalization knowledge. To address the above issue, in this work, we propose a novel Reinforcement Learning Domain Adaptation method for Neural Machine Translation (RLDA-NMT) in the low-resource domain. RLDA-NMT utilizes in-domain source monolingual data to make up for the lack of parallel data, and reinforces domain features learning to make the translation model learn the domain-specific knowledge more fully. Specifically, we first train a ranking-based model with a small-scale in-domain parallel corpus, and then adopt it as the reward model to select higher-quality generated translations for reinforcement when fine-tuning pre-trained NMT model using in-domain source monolingual data. We conduct experiments on Education, Laws, Thesis, and Patent domains of Chinese⇔English translation tasks. Experimental results demonstrate that RLDA-NMT can alleviate overfitting and reinforce the NMT model to learn domain-specific knowledge. Additionally, the results also show that RLDA-NMT and back-translation (BT) are nicely complementary to each other, where combining RLDA-NMT with BT can further improve translation quality. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

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：