检索结果-内蒙古大学图书馆

From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Shiwei Zhang, Chao Chen, Joya Xu, Tong Wu, Likang Hu, Yao Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application School of Data Science and School of Computer Science University of Science and Technology of China China The College of Design and Engineering National University of Singapore Singapore The Xiaohongshu.Inc. China

People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique challenges to recognizing social relationships, requiring understanding and capturing the essence of these contexts from visual appearances. However, current methods of social relationship understanding rely on the basic classification paradigm of detected persons and objects, which fails to understand the comprehensive context and often overlooks decisive social factors, especially subtle visual cues. To highlight the social-aware context and intricate details, we propose a novel approach that recognizes Contextual Social Relationships (ConSoR) from a social cognitive perspective. Specifically, to incorporate social-aware semantics, we build a lightweight adapter upon the frozen CLIP to learn social concepts via our novel multi-modal side adapter tuning mechanism. Further, we construct social-aware descriptive language prompts (e.g., scene, activity, objects, emotions) with social relationships for each image, and then compel ConSoR to concentrate more intensively on the decisive visual social factors via visual-linguistic contrasting. Impressively, ConSoR outperforms previous methods with a 12.2% gain on the People-in-Social-Context (PISC) dataset and a 9.8% increase on the People-in-Photo-Album (PIPA) benchmark. Furthermore, we observe that ConSoR excels at finding critical visual evidence to reveal social relationships. © 2024, CC BY.

关键词： Modal analysis

BDLR:lncRNA identification using ensemble learning

学校读者我要写书评

暂无评论

BIOCELL 2022年第4期46卷 951-960页

作者： LEJUN GONG SHEHAI ZHOU JINGMEI CHEN YONGMIN LI LI ZHANG ZHIHONG GAO Jiangsu Key Lab of Big Data Security&Intelligent Processing School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing210046China Smart Health Big Data Analysis and Location Services Engineering Laboratory of Jiangsu Province Nanjing210046China Zhejiang Engineering Research Center of Intelligent Medicine Wenzhou325035China College of Computer Science and Technology Nanjing Forestry UniversityNanjing210037China

Long non-coding RNAs(lncRNAs)play an important role in many life activities such as epigenetic material regulation,cell cycle regulation,dosage compensation and cell differentiation regulation,and are associated with many human *** are many limitations in identifying and annotating lncRNAs using traditional biological experimental *** the development of high-throughput sequencing technology,it is of great practical significance to identify the lncRNAs from massive RNA sequence data using machine learning *** on the Bagging method and Decision Tree algorithm in ensemble learning,this paper proposes a method of lncRNAs gene sequence identification called *** identification results of this classification method are compared with the identification results of several models including Byes,Support Vector Machine,Logical Regression,Decision Tree and Random *** experimental results show that the lncRNAs identification method named BDLR proposed in this paper has an accuracy of 86.61%in the human test set and 90.34%in the mouse for lncRNAs,which is more than the identification results of the other ***,the proposed method offers a reference for researchers to identify lncRNAs using the ensemble learning.

关键词： lncRNAs High-throughput sequencing Ensemble learning Bagging Decision Tree

Learning Subpocket Prototypes for Generalizable Structure-based Drug Design

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zaixi Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China

Generating molecules with high binding affinities to target proteins (a.k.a. structure-based drug design) is a fundamental and challenging task in drug discovery. Recently, deep generative models have achieved remarkable success in generating 3D molecules conditioned on the protein pocket. However, most existing methods consider molecular generation for protein pockets independently while neglecting the underlying connections such as subpocket-level similarities. Subpockets are the local protein environments of lig- and fragments and pockets with similar subpockets may bind the same molecular fragment (motif) even though their overall structures are different. Therefore, the trained models can hardly generalize to unseen protein pockets in real-world applications. In this paper, we propose a novel method DrugGPS for generalizable structure-based drug design. With the biochemical priors, we propose to learn subpocket prototypes and construct a global interaction graph to model the interactions between subpocket prototypes and molecular motifs. Moreover, a hierarchical graph transformer encoder and motif-based 3D molecule generation scheme are used to improve the model’s performance. The experimental results show that our model consistently outperforms baselines in generating realistic drug candidates with high affinities in challenging out-of-distribution settings. © 2023, CC BY-NC-SA.

关键词： Proteins

Unlocking the Potential of Reverse Distillation for Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Xinyue Wang, Jianyuan Leng, Biao Zhang, Shuo School of Computer Science and Engineering Beihang University China School of Intelligence Science and Technology University of Science and Technology Beijing China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer & Technology Beijing Jiaotong University China

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network’s over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To addresses this problem, the widely accepted Reverse Distillation (RD) paradigm designs asymmetry teacher and student network, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student’s ability to generate normal features and optimizes the teacher’s differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD’s potential. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAM

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Song, Ziying Zhang, Guoxing Liu, Lin Yang, Lei Xu, Shaoqing Jia, Caiyan Jia, Feiyang Wang, Li School of Computer Science and Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China Hebei University of Science and Technology China Tsinghua University China University of Macau China Beijing Institute of Technology China

Multi-modal 3D object detectors are dedicated to exploring secure and reliable perception systems for autonomous driving (AD). Although achieving state-of-the-art (SOTA) performance on clean benchmark datasets, they tend to overlook the complexity and harsh conditions of real-world environments. With the emergence of visual foundation models (VFMs), opportunities and challenges are presented for improving the robustness and generalization of multi-modal 3D object detection in AD. Therefore, we propose RoboFusion, a robust framework that leverages VFMs like SAM to tackle out-of-distribution (OOD) noise scenarios. We first adapt the original SAM for AD scenarios named SAM-AD. To align SAM or SAM-AD with multi-modal methods, we then introduce AD-FPN for upsampling the image features extracted by SAM. We employ wavelet decomposition to denoise the depth-guided images for further noise reduction and weather interference. At last, we employ self-attention mechanisms to adaptively reweight the fused features, enhancing informative features while suppressing excess noise. In summary, RoboFusion significantly reduces noise by leveraging the generalization and robustness of VFMs, thereby enhancing the resilience of multimodal 3D object detection. Consequently, RoboFusion achieves SOTA performance in noisy scenarios, as demonstrated by the KITTI-C and nuScenes-C benchmarks. Code is available at https://***/adept-thu/RoboFusion. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Estimated Time of Arrival Prediction via Modeling the Spatial-Temporal Interactions between Links and Crosses 21

学校读者我要写书评

暂无评论

Estimated Time of Arrival Prediction via Modeling the Spatia...

29th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL 2021

作者： Mao, Xiaowei Cai, Tianyue Peng, Wenchuang Wan, Huaiyu School of Computer and Information Technology Beijing Jiaotong University Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing China

ISBN: (纸本)9781450386647

The ACM SIGSPATIAL GIS CUP 2021 focuses on Estimated Time of Arrival (ETA) prediction, which is important to the travel scheduling and decision-making of ride-hailing platforms. Accurate ETA prediction is very challenging since ETA is affected by many heterogeneous influencing factors, including static features (e.g., number of links) and dynamic features (e.g., real-time road conditions). Meanwhile, ETA can also be affected by complex spatial-temporal dependencies between links and crosses in the route. To tackle the above challenges, we propose a deep learning method based on the Wide-Deep-Recurrent (WDR) architecture while modeling the interactions between links and crosses. We adopt Neural Factorization Machines (NFM) to memorize the historical patterns and a multiple layer perceptron (MLP) to integrate various heterogeneous influencing factors. We also model links and crosses jointly to learn their spatial-temporal dependencies in the route. Extensive experiments conducted on a real dataset show that our method achieves a high prediction accuracy. The source code is available at: https://***/wanhuaiyu/WDR-LC. © 2021 ACM.

关键词： Forecasting

Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-Based Artificial Bias

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wu, Shangxi He, Qiuyang Lu, Dongyuan Sang, Jitao Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100091 China School of Information Technology and Management University of International Business and Economics Beijing100029 China

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing methods face challenges such as poor utilization of data or intricate training requirements. In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training. Considering the strong adjustability of backdoor triggers, we are motivated to mitigate the model bias by carefully designing reverse artificial bias created from backdoor attack. Based on this, we propose a backdoor debiasing framework based on knowledge distillation, which effectively reduces the model bias from original data and minimizes security risks from the backdoor attack. The proposed solution is validated on both image and structured datasets, showing promising results. This work advances the understanding of backdoor attacks and highlights its potential for beneficial applications. The code for the study can be found at \url{https://***/r/BaDe/}. © 2024, The Authors. All rights reserved.

关键词： Distillation

KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank 39

学校读者我要写书评

暂无评论

KGCRR: An Effective Metric-Driven Knowledge Graph Completion...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Kuan Yang, Kuo Liu, Jian Lu, Xiangkui Wu, Jun Zhou, Xuezhong School of Computer Science & Technology Beijing Jiaotong University Beijing 100044 China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing 100044 China MoE Key Lab of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Beijing 100044 China University of Science and Technology Beijing Beijing 100083 China

ISBN: (纸本)157735897X

Knowledge Graph Embedding (KGE) methods have achieved great success in predicting missing links in knowledge graphs, a task also known as Knowledge Graph Completion (KGC). Under this task, the Reciprocal Rank (RR) of ground-truth items serve as a key indicator for evaluating the method's performance. However, most existing studies have overlooked the inconsistency between the ranking metric, RR, and the optimization objective functions, resulting in sub-optimal KGC performance. To address this issue, we propose a KGC framework called KGCRR, which introduces an objective function named CRR that serves as an upper bound to RR. By introducing the parameter-pressure ρ to adjust the sigmoid function, CRR achieves a better approximation to RR compared to existing objective functions. We theoretically prove that by adjusting ρ, CRR can achieve a more effective approximation to RR. By narrowing the discrepancy with RR and alleviating the gradient vanishing issue associated with the direct optimization of RR loss, CRR demonstrates an advantage in optimizing RR. CRR serves as a plug-and-play objective, capable of seamless integration into various KGE methods. Through extensive experiments conducted on FB15k-237 and WN18RR datasets, we have obtained promising results, with an average improvement of 19.06% in MRR, indicating that CRR significantly enhances the performance of existing methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

Communication-Efficient Distributed Learning with Local Immediate Error Compensation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cheng, Yifei Shen, Li Xu, Linli Qian, Xun Wu, Shiwei Zhou, Yiming Zhang, Tie Tao, Dacheng Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence School of Data Science School of Computer Science University of Science and Technology China The JD Explore Academy China The Shanghai Artificial Intelligence Laboratory China

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Error compensation