Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fin...Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.展开更多
The present paper explores the special behavior of geminate consonants in Moroccan Arabic vis-á-vis short consonants and consonant clusters.By way of comparison,it is shown that geminates exhibit properties that ...The present paper explores the special behavior of geminate consonants in Moroccan Arabic vis-á-vis short consonants and consonant clusters.By way of comparison,it is shown that geminates exhibit properties that are reminiscent of both unit structures and cluster structures.In particular,we reveal that geminates in MA demonstrate an inconsistent behavior in relation to the process of schwa epenthesis.In this context,we ask whether geminates get split up in MA,and when and how that happens.In order to characterize the patterning of geminates in MA,different phonological representations of geminates are examined against the variable behavior of geminates.On this basis,it is eventually suggested that geminates should be depicted as two root nodes that are underlyingly associated with a mora at the prosodic level.展开更多
Anticipating others’actions is innate and essential in order for humans to navigate and interact well with others in dense crowds.This ability is urgently required for unmanned systems such as service robots and self...Anticipating others’actions is innate and essential in order for humans to navigate and interact well with others in dense crowds.This ability is urgently required for unmanned systems such as service robots and self-driving cars.However,existing solutions struggle to predict pedestrian anticipation accurately,because the influence of group-related social behaviors has not been well considered.While group relationships and group interactions are ubiquitous and significantly influence pedestrian anticipation,their influence is diverse and subtle,making it difficult to explicitly quantify.Here,we propose the group interaction field(GIF),a novel group-aware representation that quantifies pedestrian anticipation into a probability field of pedestrians’future locations and attention orientations.An end-to-end neural network,GIFNet,is tailored to estimate the GIF from explicit multidimensional observations.GIFNet quantifies the influence of group behaviors by formulating a group interaction graph with propagation and graph attention that is adaptive to the group size and dynamic interaction states.The experimental results show that the GIF effectively represents the change in pedestrians’anticipation under the prominent impact of group behaviors and accurately predicts pedestrians’future states.Moreover,the GIF contributes to explaining various predictions of pedestrians’behavior in different social states.The proposed GIF will eventually be able to allow unmanned systems to work in a human-like manner and comply with social norms,thereby promoting harmonious human-machine relationships.展开更多
针对现有推荐模型忽略用户兴趣的动态变化,导致推荐精度较低等问题,提出一个基于用户行为的长短期序列推荐模型(long and short term sequence recommendation model based on user behavior,UBLSR)。在序列信息挖掘部分设计一种多路空...针对现有推荐模型忽略用户兴趣的动态变化,导致推荐精度较低等问题,提出一个基于用户行为的长短期序列推荐模型(long and short term sequence recommendation model based on user behavior,UBLSR)。在序列信息挖掘部分设计一种多路空洞卷积网络,将网络扩展成多通路结构挖掘复杂的用户行为特征;将短期时间窗口内的序列行为和目标物品进行关联,通过自注意力网络动态地对用户短期兴趣进行建模;设计一种邻居用户表示方案,借助注意力机制关注邻域内有影响力的用户子集,对用户长期兴趣进行建模;将短期兴趣建模和长期兴趣建模的结果联合进行推荐预测。UBLSR模型在Gowalla、Movielens-1M两个数据集上进行实验,其结果表明,该模型优于其它基准模型,达到较为突出的性能。展开更多
How our flexible behavior was supported by the dynamic(re)coding in fronto parietal was explored by the research group led by Prof.Chen Antao(陈安涛)from the Faculty of Psychology,Southwest University with the collabo...How our flexible behavior was supported by the dynamic(re)coding in fronto parietal was explored by the research group led by Prof.Chen Antao(陈安涛)from the Faculty of Psychology,Southwest University with the collaboration of Prof.Tobias Egner from Duke University.The study was supported by the National Natural Science Foundation of China,and was recently published in Journal of Neuroscience(2017,0935-17).展开更多
文摘Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.
文摘The present paper explores the special behavior of geminate consonants in Moroccan Arabic vis-á-vis short consonants and consonant clusters.By way of comparison,it is shown that geminates exhibit properties that are reminiscent of both unit structures and cluster structures.In particular,we reveal that geminates in MA demonstrate an inconsistent behavior in relation to the process of schwa epenthesis.In this context,we ask whether geminates get split up in MA,and when and how that happens.In order to characterize the patterning of geminates in MA,different phonological representations of geminates are examined against the variable behavior of geminates.On this basis,it is eventually suggested that geminates should be depicted as two root nodes that are underlyingly associated with a mora at the prosodic level.
基金supported in part by the National Natural Science Foundation of China (NSFC,62125106,61860206003,and 62088102)in part by the Ministry of Science and Technology of China (2021ZD0109901)in part by the Provincial Key Research and Development Program of Zhejiang (2021C01016).
文摘Anticipating others’actions is innate and essential in order for humans to navigate and interact well with others in dense crowds.This ability is urgently required for unmanned systems such as service robots and self-driving cars.However,existing solutions struggle to predict pedestrian anticipation accurately,because the influence of group-related social behaviors has not been well considered.While group relationships and group interactions are ubiquitous and significantly influence pedestrian anticipation,their influence is diverse and subtle,making it difficult to explicitly quantify.Here,we propose the group interaction field(GIF),a novel group-aware representation that quantifies pedestrian anticipation into a probability field of pedestrians’future locations and attention orientations.An end-to-end neural network,GIFNet,is tailored to estimate the GIF from explicit multidimensional observations.GIFNet quantifies the influence of group behaviors by formulating a group interaction graph with propagation and graph attention that is adaptive to the group size and dynamic interaction states.The experimental results show that the GIF effectively represents the change in pedestrians’anticipation under the prominent impact of group behaviors and accurately predicts pedestrians’future states.Moreover,the GIF contributes to explaining various predictions of pedestrians’behavior in different social states.The proposed GIF will eventually be able to allow unmanned systems to work in a human-like manner and comply with social norms,thereby promoting harmonious human-machine relationships.
文摘针对现有推荐模型忽略用户兴趣的动态变化,导致推荐精度较低等问题,提出一个基于用户行为的长短期序列推荐模型(long and short term sequence recommendation model based on user behavior,UBLSR)。在序列信息挖掘部分设计一种多路空洞卷积网络,将网络扩展成多通路结构挖掘复杂的用户行为特征;将短期时间窗口内的序列行为和目标物品进行关联,通过自注意力网络动态地对用户短期兴趣进行建模;设计一种邻居用户表示方案,借助注意力机制关注邻域内有影响力的用户子集,对用户长期兴趣进行建模;将短期兴趣建模和长期兴趣建模的结果联合进行推荐预测。UBLSR模型在Gowalla、Movielens-1M两个数据集上进行实验,其结果表明,该模型优于其它基准模型,达到较为突出的性能。
文摘How our flexible behavior was supported by the dynamic(re)coding in fronto parietal was explored by the research group led by Prof.Chen Antao(陈安涛)from the Faculty of Psychology,Southwest University with the collaboration of Prof.Tobias Egner from Duke University.The study was supported by the National Natural Science Foundation of China,and was recently published in Journal of Neuroscience(2017,0935-17).
