GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Association for the Advancement of Artificial Intelligence (AAAI)  (9)
Material
Publisher
  • Association for the Advancement of Artificial Intelligence (AAAI)  (9)
Person/Organisation
Language
Years
  • 1
    Online Resource
    Online Resource
    Mis-Classified Vector Guided Softmax Loss for Face Recognition
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2020
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 34, No. 07 ( 2020-04-03), p. 12241-12248
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 34, No. 07 ( 2020-04-03), p. 12241-12248
    Abstract: Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v34i07.6906
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2020
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Exploiting Relationship for Complex-scene Image Generation
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2021
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 35, No. 2 ( 2021-05-18), p. 1584-1592
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 35, No. 2 ( 2021-05-18), p. 1584-1592
    Abstract: The significant progress on Generative Adversarial Networks (GANs) has facilitated realistic single-object image generation based on language input. However, complex-scene generation (with various interactions among multiple objects) still suffers from messy layouts and object distortions, due to diverse configurations in layouts and appearances. Prior methods are mostly object-driven and ignore their inter-relations that play a significant role in complex-scene images. This work explores relationship-aware complex-scene image generation, where multiple objects are inter-related as a scene graph. With the help of relationships, we propose three major updates in the generation framework. First, reasonable spatial layouts are inferred by jointly considering the semantics and relationships among objects. Compared to standard location regression, we show relative scales and distances serve a more reliable target. Second, since the relations between objects have significantly influenced an object's appearance, we design a relation-guided generator to generate objects reflecting their relationships. Third, a novel scene graph discriminator is proposed to guarantee the consistency between the generated image and the input scene graph. Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image. Experimental results on Visual Genome and HICO-DET datasets show that our proposed method significantly outperforms prior arts in terms of IS and FID metrics. Based on our user study and visual inspection, our method is more effective in generating logical layout and appearance for complex-scenes.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v35i2.16250
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2021
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Smooth Deep Image Generator from Noises
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2019
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 33, No. 01 ( 2019-07-17), p. 3731-3738
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 33, No. 01 ( 2019-07-17), p. 3731-3738
    Abstract: Generative Adversarial Networks (GANs) have demonstrated a strong ability to fit complex distributions since they were presented, especially in the field of generating natural images. Linear interpolation in the noise space produces a continuously changing in the image space, which is an impressive property of GANs. However, there is no special consideration on this property in the objective function of GANs or its derived models. This paper analyzes the perturbation on the input of the generator and its influence on the generated images. A smooth generator is then developed by investigating the tolerable input perturbation. We further integrate this smooth generator with a gradient penalized discriminator, and design smooth GAN that generates stable and high-quality images. Experiments on real-world image datasets demonstrate the necessity of studying smooth generator and the effectiveness of the proposed algorithm.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v33i01.33013731
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2019
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Visually Grounded Commonsense Knowledge Acquisition
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2023
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 37, No. 5 ( 2023-06-26), p. 6583-6592
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 37, No. 5 ( 2023-06-26), p. 6583-6592
    Abstract: Large-scale commonsense knowledge bases empower a broad range of AI applications, where the automatic extraction of commonsense knowledge (CKE) is a fundamental and challenging problem. CKE from text is known for suffering from the inherent sparsity and reporting bias of commonsense in text. Visual perception, on the other hand, contains rich commonsense knowledge about real-world entities, e.g., (person, can_hold, bottle), which can serve as promising sources for acquiring grounded commonsense knowledge. In this work, we present CLEVER, which formulates CKE as a distantly supervised multi-instance learning problem, where models learn to summarize commonsense relations from a bag of images about an entity pair without any human annotation on image instances. To address the problem, CLEVER leverages vision-language pre-training models for deep understanding of each image in the bag, and selects informative instances from the bag to summarize commonsense entity relations via a novel contrastive attention mechanism. Comprehensive experimental results in held-out and human evaluation show that CLEVER can extract commonsense knowledge in promising quality, outperforming pre-trained language model-based methods by 3.9 AUC and 6.4 mAUC points. The predicted commonsense scores show strong correlation with human judgment with a 0.78 Spearman coefficient. Moreover, the extracted commonsense can also be grounded into images with reasonable interpretability. The data and codes can be obtained at https://github.com/thunlp/CLEVER.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v37i5.25809
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2023
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    Reinforced Multi-Label Image Classification by Exploring Curriculum
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2018
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 32, No. 1 ( 2018-04-29)
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 32, No. 1 ( 2018-04-29)
    Abstract: Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Inspired by this curriculum learning mechanism, we propose a reinforced multi-label image classification approach imitating human behavior to label image from easy to complex. This approach allows a reinforcement learning agent to sequentially predict labels by fully exploiting image feature and previously predicted labels. The agent discovers the optimal policies through maximizing the long-term reward which reflects prediction accuracies. Experimental results on PASCAL VOC2007 and 2012 demonstrate the necessity of reinforcement multi-label learning and the algorithm’s effectiveness in real-world multi-label image classification tasks.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v32i1.11770
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2018
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-Supervised Action Recognition
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2022
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 36, No. 1 ( 2022-06-28), p. 762-770
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 36, No. 1 ( 2022-06-28), p. 762-770
    Abstract: In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to construct similar positive samples, which limits the ability to explore novel movement patterns. In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed. First, the extreme augmentations and the Energy-based Attention-guided Drop Module (EADM) are proposed to obtain diverse positive samples, which bring novel movement patterns to improve the universality of the learned representations. Second, since directly using extreme augmentations may not be able to boost the performance due to the drastic changes in original identity, the Dual Distributional Divergence Minimization Loss (D3M Loss) is proposed to minimize the distribution divergence in a more gentle way. Third, the Nearest Neighbors Mining (NNM) is proposed to further expand positive samples to make the abundant information mining process more reasonable. Exhaustive experiments on NTU RGB+D 60, PKU-MMD, NTU RGB+D 120 datasets have verified that our AimCLR can significantly perform favorably against state-of-the-art methods under a variety of evaluation protocols with observed higher quality action representations. Our code is available at https://github.com/Levigty/AimCLR.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v36i1.19957
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2022
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    Enhanced Multi-Relationships Integration Graph Convolutional Network for Inferring Substitutable and Complementary Items
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2023
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 37, No. 4 ( 2023-06-26), p. 4157-4165
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 37, No. 4 ( 2023-06-26), p. 4157-4165
    Abstract: Understanding the relationships between items can improve the accuracy and interpretability of recommender systems. Among these relationships, the substitute and complement relationships attract the most attention in e-commerce platforms. The substitutable items are interchangeable and might be compared with each other before purchasing, while the complementary items are used in conjunction and are usually bought together with the query item. In this paper, we focus on two issues of inferring the substitutable and complementary items: 1) how to model their mutual influence to improve the performance of downstream tasks, 2) how to further discriminate them by considering the strength of relationship for different item pairs. We propose a novel multi-task learning framework named Enhanced Multi-Relationships Integration Graph Convolutional Network (EMRIGCN). We regard the relationship inference task as a link prediction task in heterogeneous graph with different types of edges between nodes (items). To model the mutual influence between substitute and complement, EMRIGCN adopts a two-level integration module, i.e., feature and structure integration, based on experts sharing mechanism during message passing. To obtain the strength of relationship for item pairs, we build an auxiliary loss function to further increase or decrease the distances between embeddings of items with weak or strong relation in latent space. Extensive experiments on both public and industrial datasets prove that EMRIGCN significantly outperforms the state-of-the-art solutions. We also conducted A/B tests on real world recommender systems of Meituan Maicai, an online supermarket platform in China, and obtained 15.3% improvement on VBR and 15.34% improvement on RPM.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v37i4.25532
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2023
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 8
    Online Resource
    Online Resource
    Tied Transformers: Neural Machine Translation with Shared Encoder and Decoder
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2019
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 33, No. 01 ( 2019-07-17), p. 5466-5473
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 33, No. 01 ( 2019-07-17), p. 5466-5473
    Abstract: Sharing source and target side vocabularies and word embeddings has been a popular practice in neural machine translation (briefly, NMT) for similar languages (e.g., English to French or German translation). The success of such wordlevel sharing motivates us to move one step further: we consider model-level sharing and tie the whole parts of the encoder and decoder of an NMT model. We share the encoder and decoder of Transformer (Vaswani et al. 2017), the state-of-the-art NMT model, and obtain a compact model named Tied Transformer. Experimental results demonstrate that such a simple method works well for both similar and dissimilar language pairs. We empirically verify our framework for both supervised NMT and unsupervised NMT: we achieve a 35.52 BLEU score on IWSLT 2014 German to English translation, 28.98/29.89 BLEU scores on WMT 2014 English to German translation without/with monolingual data, and a 22.05 BLEU score on WMT 2016 unsupervised German to English translation.
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v33i01.33015466
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2019
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 9
    Online Resource
    Online Resource
    Pose-Guided Feature Disentangling for Occluded Person Re-identification Based on Transformer
    Association for the Advancement of Artificial Intelligence (AAAI) ; 2022
    In:  Proceedings of the AAAI Conference on Artificial Intelligence Vol. 36, No. 3 ( 2022-06-28), p. 2540-2549
    Details
    In: Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence (AAAI), Vol. 36, No. 3 ( 2022-06-28), p. 2540-2549
    Abstract: Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at https://github.com/WangTaoAs/PFD_Net
    Type of Medium: Online Resource
    ISSN: 2374-3468 , 2159-5399
    URL: Article
    DOI: 10.1609/aaai.v36i3.20155
    Language: Unknown
    Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
    Publication Date: 2022
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...