Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence最新文献_第5页

Fast Fluid Simulation via Dynamic Multi-Scale Gridding 基于动态多尺度网格的快速流体仿真

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i2.25255

Jinxian Liu, Ye Chen, Bingbing Ni, Wei Ren, Zhenbo Yu, Xiaoyang Huang

{"title":"Fast Fluid Simulation via Dynamic Multi-Scale Gridding","authors":"Jinxian Liu, Ye Chen, Bingbing Ni, Wei Ren, Zhenbo Yu, Xiaoyang Huang","doi":"10.1609/aaai.v37i2.25255","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25255","url":null,"abstract":"Recent works on learning-based frameworks for Lagrangian (i.e., particle-based) fluid simulation, though bypassing iterative pressure projection via efficient convolution operators, are still time-consuming due to excessive amount of particles. To address this challenge, we propose a dynamic multi-scale gridding method to reduce the magnitude of elements that have to be processed, by observing repeated particle motion patterns within certain consistent regions. Specifically, we hierarchically generate multi-scale micelles in Euclidean space by grouping particles that share similar motion patterns/characteristics based on super-light motion and scale estimation modules. With little internal motion variation, each micelle is modeled as a single rigid body with convolution only applied to a single representative particle. In addition, a distance-based interpolation is conducted to propagate relative motion message among micelles. With our efficient design, the network produces high visual fidelity fluid simulations with the inference time to be only 4.24 ms/frame (with 6K fluid particles), hence enables real-time human-computer interaction and animation. Experimental results on multiple datasets show that our work achieves great simulation acceleration with negligible prediction error increase.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"63 1","pages":"1675-1682"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85630739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network 面向异构图神经网络的细粒度可解释性

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i7.26040

Tong Li, Jiale Deng, Yanyan Shen, Luyu Qiu, Hu Yongxiang, Caleb Chen Cao

{"title":"Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network","authors":"Tong Li, Jiale Deng, Yanyan Shen, Luyu Qiu, Hu Yongxiang, Caleb Chen Cao","doi":"10.1609/aaai.v37i7.26040","DOIUrl":"https://doi.org/10.1609/aaai.v37i7.26040","url":null,"abstract":"Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs. Despite the superior performance, insights about the predictions made from HGNs are obscure to humans. Existing explainability techniques are mainly proposed for GNNs on homogeneous graphs. They focus on highlighting salient graph objects to the predictions whereas the problem of how these objects affect the predictions remains unsolved. Given heterogeneous graphs with complex structures and rich semantics, it is imperative that salient objects can be accompanied with their influence paths to the predictions, unveiling the reasoning process of HGNs. In this paper, we develop xPath, a new framework that provides fine-grained explanations for black-box HGNs specifying a cause node with its influence path to the target node. In xPath, we differentiate the influence of a node on the prediction w.r.t. every individual influence path, and measure the influence by perturbing graph structure via a novel graph rewiring algorithm. Furthermore, we introduce a greedy search algorithm to find the most influential fine-grained explanations efficiently. Empirical results on various HGNs and heterogeneous graphs show that xPath yields faithful explanations efficiently, outperforming the adaptations of advanced GNN explanation approaches.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"16 1","pages":"8640-8647"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85875455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Social Relation Reasoning Based on Triangular Constraints 基于三角约束的社会关系推理

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i1.25151

Yunfei Guo, Fei Yin, Wei Feng, Xudong Yan, Tao Xue, Shuqi Mei, Chengxiao Liu

{"title":"Social Relation Reasoning Based on Triangular Constraints","authors":"Yunfei Guo, Fei Yin, Wei Feng, Xudong Yan, Tao Xue, Shuqi Mei, Chengxiao Liu","doi":"10.1609/aaai.v37i1.25151","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25151","url":null,"abstract":"Social networks are essentially in a graph structure where persons act as nodes and the edges connecting nodes denote social relations. The prediction of social relations, therefore, relies on the context in graphs to model the higher-order constraints among relations, which has not been exploited sufficiently by previous works, however. In this paper, we formulate the paradigm of the higher-order constraints in social relations into triangular relational closed-loop structures, i.e., triangular constraints, and further introduce the triangular reasoning graph attention network (TRGAT). Our TRGAT employs the attention mechanism to aggregate features with triangular constraints in the graph, thereby exploiting the higher-order context to reason social relations iteratively. Besides, to acquire better feature representations of persons, we introduce node contrastive learning into relation reasoning. Experimental results show that our method outperforms existing approaches significantly, with higher accuracy and better consistency in generating social relation graphs.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"18 1","pages":"737-745"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85945175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

End-to-End Pipeline for Trigger Detection on Hit and Track Graphs 端到端管道触发检测命中和轨迹图

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26870

Tingting Xuan, Yimin Zhu, Giorgian Borca-Tasciuc, Ming Liu, Yu Sun, Cameron Dean, Y. C. Morales, Z. Shi, Dantong Yu

{"title":"End-to-End Pipeline for Trigger Detection on Hit and Track Graphs","authors":"Tingting Xuan, Yimin Zhu, Giorgian Borca-Tasciuc, Ming Liu, Yu Sun, Cameron Dean, Y. C. Morales, Z. Shi, Dantong Yu","doi":"10.1609/aaai.v37i13.26870","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26870","url":null,"abstract":"There has been a surge of interest in applying deep learning in particle and nuclear physics to replace labor-intensive offline data analysis with automated online machine learning tasks. This paper details a novel AI-enabled triggering solution for physics experiments in Relativistic Heavy Ion Collider and future Electron-Ion Collider. The triggering system consists of a comprehensive end-to-end pipeline based on Graph Neural Networks that classifies trigger events versus background events, makes online decisions to retain signal data, and enables efficient data acquisition. The triggering system first starts with the coordinates of pixel hits lit up by passing particles in the detector, applies three stages of event processing (hits clustering, track reconstruction, and trigger detection), and labels all processed events with the binary tag of trigger versus background events. By switching among different objective functions, we train the Graph Neural Networks in the pipeline to solve multiple tasks: the edge-level track reconstruction problem, the edge-level track adjacency matrix prediction, and the graph-level trigger detection problem. We propose a novel method to treat the events as track-graphs instead of hit-graphs. This method focuses on intertrack relations and is driven by underlying physics processing. As a result, it attains a solid performance (around 72% accuracy) for trigger detection and outperforms the baseline method using hit-graphs by 2% higher accuracy.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"13 1","pages":"15752-15758"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85974712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated Learning 用Cerberus中毒:对联邦学习的秘密和串通后门攻击

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i7.26083

Xiaoting Lyu, Yufei Han, Wen Wang, Jingkai Liu, Bin Wang, Jiqiang Liu, Xiangliang Zhang

{"title":"Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated Learning","authors":"Xiaoting Lyu, Yufei Han, Wen Wang, Jingkai Liu, Bin Wang, Jiqiang Liu, Xiangliang Zhang","doi":"10.1609/aaai.v37i7.26083","DOIUrl":"https://doi.org/10.1609/aaai.v37i7.26083","url":null,"abstract":"Are Federated Learning (FL) systems free from backdoor poisoning with the arsenal of various defense strategies deployed? This is an intriguing problem with significant practical implications regarding the utility of FL services. Despite the recent flourish of poisoning-resilient FL methods, our study shows that carefully tuning the collusion between malicious participants can minimize the trigger-induced bias of the poisoned local model from the poison-free one, which plays the key role in delivering stealthy backdoor attacks and circumventing a wide spectrum of state-of-the-art defense methods in FL. In our work, we instantiate the attack strategy by proposing a distributed backdoor attack method, namely Cerberus Poisoning (CerP). It jointly tunes the backdoor trigger and controls the poisoned model changes on each malicious participant to achieve a stealthy yet successful backdoor attack against a wide spectrum of defensive mechanisms of federated learning techniques. Our extensive study on 3 large-scale benchmark datasets and 13 mainstream defensive mechanisms confirms that Cerberus Poisoning raises a significantly severe threat to the integrity and security of federated learning practices, regardless of the flourish of robust Federated Learning methods.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"31 1","pages":"9020-9028"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76604395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

DisGUIDE: Disagreement-Guided Data-Free Model Extraction DisGUIDE:分歧引导的无数据模型提取

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i8.26150

Jonathan Rosenthal, Eric Enouen, H. Pham, Lin Tan

{"title":"DisGUIDE: Disagreement-Guided Data-Free Model Extraction","authors":"Jonathan Rosenthal, Eric Enouen, H. Pham, Lin Tan","doi":"10.1609/aaai.v37i8.26150","DOIUrl":"https://doi.org/10.1609/aaai.v37i8.26150","url":null,"abstract":"Recent model-extraction attacks on Machine Learning as a Service (MLaaS) systems have moved towards data-free approaches, showing the feasibility of stealing models trained with difficult-to-access data. However, these attacks are ineffective or limited due to the low accuracy of extracted models and the high number of queries to the models under attack. The high query cost makes such techniques infeasible for online MLaaS systems that charge per query.\u0000We create a novel approach to get higher accuracy and query efficiency than prior data-free model extraction techniques. Specifically, we introduce a novel generator training scheme that maximizes the disagreement loss between two clone models that attempt to copy the model under attack. This loss, combined with diversity loss and experience replay, enables the generator to produce better instances to train the clone models. Our evaluation on popular datasets CIFAR-10 and CIFAR-100 shows that our approach improves the final model accuracy by up to 3.42% and 18.48% respectively. The average number of queries required to achieve the accuracy of the prior state of the art is reduced by up to 64.95%. We hope this will promote future work on feasible data-free model extraction and defenses against such attacks.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"517 1","pages":"9614-9622"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77148921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Leveraging Sub-class Discimination for Compositional Zero-Shot Learning 利用子类差别进行作文零射击学习

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i1.25168

Xiaoming Hu, Zilei Wang

{"title":"Leveraging Sub-class Discimination for Compositional Zero-Shot Learning","authors":"Xiaoming Hu, Zilei Wang","doi":"10.1609/aaai.v37i1.25168","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25168","url":null,"abstract":"Compositional Zero-Shot Learning (CZSL) aims at identifying unseen compositions composed of previously seen attributes and objects during the test phase. In real images, the visual appearances of attributes and objects (primitive concepts) generally interact with each other. Namely, the visual appearances of an attribute may change when composed with different objects, and vice versa. But previous works overlook this important property. In this paper, we introduce a simple yet effective approach with leveraging sub-class discrimination. Specifically, we define the primitive concepts in different compositions as sub-classes, and then maintain the sub-class discrimination to address the above challenge. More specifically, inspired by the observation that the composed recognition models could account for the differences across sub-classes, we first propose to impose the embedding alignment between the composed and disentangled recognition to incorporate sub-class discrimination at the feature level. Then we develop the prototype modulator networks to adjust the class prototypes w.r.t. the composition information, which can enhance sub-class discrimination at the classifier level. We conduct extensive experiments on the challenging benchmark datasets, and the considerable performance improvement over state-of-the-art approaches is achieved, which indicates the effectiveness of our method. Our code is available at https://github.com/hxm97/SCD-CZSL.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"38 1","pages":"890-898"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80822271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis MTDiag:一个有效的多任务自动诊断框架

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i12.26666

Zhenyu Hou, Yukuo Cen, Ziding Liu, Dongxue Wu, Baoyan Wang, Xuanhe Li, Lei Hong, Jie Tang

{"title":"MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis","authors":"Zhenyu Hou, Yukuo Cen, Ziding Liu, Dongxue Wu, Baoyan Wang, Xuanhe Li, Lei Hong, Jie Tang","doi":"10.1609/aaai.v37i12.26666","DOIUrl":"https://doi.org/10.1609/aaai.v37i12.26666","url":null,"abstract":"Automatic diagnosis systems aim to probe for symptoms (i.e., symptom checking) and diagnose disease through multi-turn conversations with patients. Most previous works formulate it as a sequential decision process and use reinforcement learning (RL) to decide whether to inquire about symptoms or make a diagnosis. However, these RL-based methods heavily rely on the elaborate reward function and usually suffer from an unstable training process and low data efficiency. In this work, we propose an effective multi-task framework for automatic diagnosis called MTDiag. We first reformulate symptom checking as a multi-label classification task by direct supervision. Each medical dialogue is equivalently converted into multiple samples for classification, which can also help alleviate the data scarcity problem. Furthermore, we design a multi-task learning strategy to guide the symptom checking procedure with disease information and further utilize contrastive learning to better distinguish symptoms between diseases. Extensive experimental results show that our method achieves state-of-the-art performance on four public datasets with 1.7%~3.1% improvement in disease diagnosis, demonstrating the superiority of the proposed method. Additionally, our model is now deployed in an online medical consultant system as an assistant tool for real-life doctors.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"44 1","pages":"14241-14248"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81106184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

See Your Emotion from Gait Using Unlabeled Skeleton Data 使用未标记的骨骼数据从步态中看到你的情绪

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i2.25272

Haifeng Lu, Xiping Hu, B. Hu

{"title":"See Your Emotion from Gait Using Unlabeled Skeleton Data","authors":"Haifeng Lu, Xiping Hu, B. Hu","doi":"10.1609/aaai.v37i2.25272","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25272","url":null,"abstract":"This paper focuses on contrastive learning for gait-based emotion recognition. The existing contrastive learning approaches are rarely suitable for learning skeleton-based gait representations, which suffer from limited gait diversity and inconsistent semantics. In this paper, we propose a Cross-coordinate contrastive learning framework utilizing Ambiguity samples for self-supervised Gait-based Emotion representation (CAGE). First, we propose ambiguity transform to push positive samples into ambiguous semantic space. By learning similarities between ambiguity samples and positive samples, our model can learn higher-level semantics of the gait sequences and maintain semantic diversity. Second, to encourage learning the semantic invariance, we uniquely propose cross-coordinate contrastive learning between the Cartesian coordinate and the Spherical coordinate, which brings rich supervisory signals to learn the intrinsic semantic consistency information. Exhaustive experiments show that CAGE improves existing self-supervised methods by 5%–10% accuracy, and it achieves comparable or even superior performance to supervised methods.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"33 1","pages":"1826-1834"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81187420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MEID: Mixture-of-Experts with Internal Distillation for Long-Tailed Video Recognition 基于内部蒸馏的专家混合长尾视频识别

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i2.25230

Xinjie Li, Huijuan Xu

{"title":"MEID: Mixture-of-Experts with Internal Distillation for Long-Tailed Video Recognition","authors":"Xinjie Li, Huijuan Xu","doi":"10.1609/aaai.v37i2.25230","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25230","url":null,"abstract":"The long-tailed video recognition problem is especially challenging, as videos tend to be long and untrimmed, and each video may contain multiple classes, causing frame-level class imbalance. The previous method tackles the long-tailed video recognition only through frame-level sampling for class re-balance without distinguishing the frame-level feature representation between head and tail classes. To improve the frame-level feature representation of tail classes, we modulate the frame-level features with an auxiliary distillation loss to reduce the distribution distance between head and tail classes. Moreover, we design a mixture-of-experts framework with two different expert designs, i.e., the first expert with an attention-based classification network handling the original long-tailed distribution, and the second expert dealing with the re-balanced distribution from class-balanced sampling. Notably, in the second expert, we specifically focus on the frames unsolved by the first expert through designing a complementary frame selection module, which inherits the attention weights from the first expert and selects frames with low attention weights, and we also enhance the motion feature representation for these selected frames. To highlight the multi-label challenge in long-tailed video recognition, we create two additional benchmarks based on Charades and CharadesEgo videos with the multi-label property, called CharadesLT and CharadesEgoLT. Extensive experiments are conducted on the existing long-tailed video benchmark VideoLT and the two new benchmarks to verify the effectiveness of our proposed method with state-of-the-art performance. The code and proposed benchmarks are released at https://github.com/VisionLanguageLab/MEID.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"26 1","pages":"1451-1459"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81211794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1