Filters








367 Hits in 2.1 sec

Gradient Correction beyond Gradient Descent [article]

Zefan Li, Bingbing Ni, Teng Li, WenJun Zhang, Wen Gao
<span title="2022-03-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The great success neural networks have achieved is inseparable from the application of gradient-descent (GD) algorithms. Based on GD, many variant algorithms have emerged to improve the GD optimization process. The gradient for back-propagation is apparently the most crucial aspect for the training of a neural network. The quality of the calculated gradient can be affected by multiple aspects, e.g., noisy data, calculation error, algorithm limitation, and so on. To reveal gradient information
more &raquo; ... yond gradient descent, we introduce a framework (GCGD) to perform gradient correction. GCGD consists of two plug-in modules: 1) inspired by the idea of gradient prediction, we propose a GC-W module for weight gradient correction; 2) based on Neural ODE, we propose a GC-ODE module for hidden states gradient correction. Experiment results show that our gradient correction framework can effectively improve the gradient quality to reduce training epochs by ∼ 20% and also improve the network performance.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.08345v1">arXiv:2203.08345v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/73pe5ees7fbjtbowiu5gyjv64e">fatcat:73pe5ees7fbjtbowiu5gyjv64e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220321041320/https://arxiv.org/pdf/2203.08345v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/26/5b/265b7d58bf812b277d162649c9c1db2a0a8bf63e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.08345v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Video Prediction via Example Guidance [article]

Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Trevor Darrell
<span title="2020-07-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In video prediction tasks, one major challenge is to capture the multi-modal nature of future contents and dynamics. In this work, we propose a simple yet effective framework that can efficiently predict plausible future states. The key insight is that the potential distribution of a sequence could be approximated with analogous ones in a repertoire of training pool, namely, expert examples. By further incorporating a novel optimization scheme into the training procedure, plausible predictions
more &raquo; ... an be sampled efficiently from distribution constructed from the retrieved examples. Meanwhile, our method could be seamlessly integrated with existing stochastic predictive models; significant enhancement is observed with comprehensive experiments in both quantitative and qualitative aspects. We also demonstrate the generalization ability to predict the motion of unseen class, i.e., without access to corresponding data during training phase.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01738v1">arXiv:2007.01738v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zamzwlyq6fdfrcer2qfpgjhpxa">fatcat:zamzwlyq6fdfrcer2qfpgjhpxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710132438/https://arxiv.org/pdf/2007.01738v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/23/dc23b1c8538a6810ad6fde3a95a60da617c38ec1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01738v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Predicting Human Interaction via Relative Attention Model [article]

Yichao Yan, Bingbing Ni, Xiaokang Yang
<span title="2017-05-26">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects. Also, only a small region in the scene is discriminative for identifying the on-going interaction. In this work, we propose a relative attention model to explicitly address these difficulties. Built on a tri-coupled deep recurrent structure representing both
more &raquo; ... teracting subjects and global interaction status, the proposed network collects spatio-temporal information from each subject, rectified with global interaction information, yielding effective interaction representation. Moreover, the proposed network also unifies an attention module to assign higher importance to the regions which are relevant to the on-going action. Extensive experiments have been conducted on two public datasets, and the results demonstrate that the proposed relative attention network successfully predicts informative regions between interacting subjects, which in turn yields superior human interaction prediction accuracy.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.09467v1">arXiv:1705.09467v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ngz7v3ssrf2le7hxxdhqbbr7e">fatcat:4ngz7v3ssrf2le7hxxdhqbbr7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911053823/https://arxiv.org/pdf/1705.09467v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/82/b7/82b7d5e0c14f909d6edef2eb821758dcbea7b058.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.09467v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Energy Attack: On Transferring Adversarial Examples [article]

Ruoxi Shi, Borui Yang, Yangzhou Jiang, Chenglong Zhao, Bingbing Ni
<span title="2021-09-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work we propose Energy Attack, a transfer-based black-box L_∞-adversarial attack. The attack is parameter-free and does not require gradient approximation. In particular, we first obtain white-box adversarial perturbations of a surrogate model and divide these perturbations into small patches. Then we extract the unit component vectors and eigenvalues of these patches with principal component analysis (PCA). Base on the eigenvalues, we can model the energy distribution of adversarial
more &raquo; ... turbations. We then perform black-box attacks by sampling from the perturbation patches according to their energy distribution, and tiling the sampled patches to form a full-size adversarial perturbation. This can be done without the available access to victim models. Extensive experiments well demonstrate that the proposed Energy Attack achieves state-of-the-art performance in black-box attacks on various models and several datasets. Moreover, the extracted distribution is able to transfer among different model architectures and different datasets, and is therefore intrinsic to vision architectures.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.04300v1">arXiv:2109.04300v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ua25ng7wybhstc3ciey6ahbesm">fatcat:ua25ng7wybhstc3ciey6ahbesm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210916000032/https://arxiv.org/pdf/2109.04300v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2b/cc/2bcceb3e073a3de90b4c8d9ccf2dc34619435a82.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.04300v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Half-CNN: A General Framework for Whole-Image Regression [article]

Jun Yuan, Bingbing Ni, Ashraf A.Kassim
<span title="2014-12-22">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The Convolutional Neural Network (CNN) has achieved great success in image classification. The classification model can also be utilized at image or patch level for many other applications, such as object detection and segmentation. In this paper, we propose a whole-image CNN regression model, by removing the full connection layer and training the network with continuous feature maps. This is a generic regression framework that fits many applications. We demonstrate this method through two
more &raquo; ... : simultaneous face detection & segmentation, and scene saliency prediction. The result is comparable with other models in the respective fields, using only a small scale network. Since the regression model is trained on corresponding image / feature map pairs, there are no requirements on uniform input size as opposed to the classification model. Our framework avoids classifier design, a process that may introduce too much manual intervention in model development. Yet, it is highly correlated to the classification network and offers some in-deep review of CNN structures.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.6885v1">arXiv:1412.6885v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3azarc4tvnakrabrc5n3csgvka">fatcat:3azarc4tvnakrabrc5n3csgvka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907163232/https://arxiv.org/ftp/arxiv/papers/1412/1412.6885.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ee/89/ee89b903af1d8f26a8894a3773915c74f038883e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.6885v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Collaborative Learning for Faster StyleGAN Embedding [article]

Shanyan Guan, Ying Tai, Bingbing Ni, Feida Zhu, Feiyue Huang, Xiaokang Yang
<span title="2020-07-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator. Embedding a given image back to the latent space of StyleGAN enables wide interesting semantic image editing applications. Although previous works are able to yield impressive inversion results based on an optimization framework, which however suffers from the efficiency issue. In this work, we propose a novel collaborative learning framework that
more &raquo; ... s of an efficient embedding network and an optimization-based iterator. On one hand, with the progress of training, the embedding network gives a reasonable latent code initialization for the iterator. On the other hand, the updated latent code from the iterator in turn supervises the embedding network. In the end, high-quality latent code can be obtained efficiently with a single forward pass through our embedding network. Extensive experiments demonstrate the effectiveness and efficiency of our work.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01758v1">arXiv:2007.01758v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mznwddz3vvaergpimwsegkvnqa">fatcat:mznwddz3vvaergpimwsegkvnqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902205230/https://arxiv.org/pdf/2007.01758v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8c/52/8c52b095a682182d481779761f58691773a1175e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.01758v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Context Graph for Person Search [article]

Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang
<span title="2019-04-03">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which
more &raquo; ... loys a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.01830v1">arXiv:1904.01830v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2zzxtoieavemtmy25knnuot4ba">fatcat:2zzxtoieavemtmy25knnuot4ba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930190949/https://arxiv.org/pdf/1904.01830v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b6/d4/b6d4c449d31a61914d62f78924b2577e51609644.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.01830v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Representation-Agnostic Shape Fields [article]

Xiaoyang Huang, Jiancheng Yang, Yanjun Wang, Ziyu Chen, Linguo Li, Teng Li, Bingbing Ni, Wenjun Zhang
<span title="2022-03-19">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
3D shape analysis has been widely explored in the era of deep learning. Numerous models have been developed for various 3D data representation formats, e.g., MeshCNN for meshes, PointNet for point clouds and VoxNet for voxels. In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. RASF is implemented with a learnable 3D grid with multiple channels to store local geometry. Based on RASF, shape
more &raquo; ... mbeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by coordinate indexing. While there are multiple ways to optimize the learnable parameters of RASF, we provide two effective schemes among all in this paper for RASF pre-training: shape reconstruction and normal estimation. Once trained, RASF becomes a plug-and-play performance booster with negligible cost. Extensive experiments on diverse 3D representation formats, networks and applications, validate the universal effectiveness of the proposed RASF. Code and pre-trained models are publicly available https://github.com/seanywang0408/RASF
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.10259v1">arXiv:2203.10259v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/igrjbkgkv5athcmurnps7pxnji">fatcat:igrjbkgkv5athcmurnps7pxnji</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220327205427/https://arxiv.org/pdf/2203.10259v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/27/91/27910a4e2da98c11f639259e6d8d61f122513756.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.10259v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Skeleton-aided Articulated Motion Generation [article]

Yichao Yan, Jingwei Xu, Bingbing Ni, Xiaokang Yang
<span title="2017-09-14">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This work make the first attempt to generate articulated human motion sequence from a single image. On the one hand, we utilize paired inputs including human skeleton information as motion embedding and a single human image as appearance reference, to generate novel motion frames, based on the conditional GAN infrastructure. On the other hand, a triplet loss is employed to pursue appearance-smoothness between consecutive frames. As the proposed framework is capable of jointly exploiting the
more &raquo; ... e appearance space and articulated/kinematic motion space, it generates realistic articulated motion sequence, in contrast to most previous video generation methods which yield blurred motion effects. We test our model on two human action datasets including KTH and Human3.6M, and the proposed framework generates very promising results on both datasets.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.01058v2">arXiv:1707.01058v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p3jccv3psrhq7chatdvvqq5oci">fatcat:p3jccv3psrhq7chatdvvqq5oci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831024900/https://arxiv.org/pdf/1707.01058v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/69/7d6957d2debc5e1606fc3b0a3b2d25a30a0a649a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.01058v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Assistive tagging

Meng Wang, Bingbing Ni, Xian-Sheng Hua, Tat-Seng Chua
<span title="2012-08-01">2012</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/eiea26iqqjcatatlgxdpzt637y" style="color: black;">ACM Computing Surveys</a> </i> &nbsp;
Along with the explosive growth of multimedia data, automatic multimedia tagging has attracted great interest of various research communities, such as computer vision, multimedia, and information retrieval. However, despite the great progress achieved in the past two decades, automatic tagging technologies still can hardly achieve satisfactory performance on real-world multimedia data that vary widely in genre, quality, and content. Meanwhile, the power of human intelligence has been fully
more &raquo; ... strated in the Web 2.0 era. If well motivated, Internet users are able to tag a large amount of multimedia data. Therefore, a set of new techniques has been developed by combining humans and computers for more accurate and efficient multimedia tagging, such as batch tagging, active tagging, tag recommendation, and tag refinement. These techniques are able to accomplish multimedia tagging by jointly exploring humans and computers in different ways. This article refers to them collectively as assistive tagging and conducts a comprehensive survey of existing research efforts on this theme. We first introduce the status of automatic tagging and manual tagging and then state why assistive tagging can be a good solution. We categorize existing assistive tagging techniques into three paradigms: (1) tagging with data selection & organization; (2) tag recommendation; and (3) tag processing. We introduce the research efforts on each paradigm and summarize the methodologies. We also provide a discussion on several future trends in this research direction.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2333112.2333120">doi:10.1145/2333112.2333120</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cvlxcazimvdjxigdvchjinnewe">fatcat:cvlxcazimvdjxigdvchjinnewe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808024605/http://lms.comp.nus.edu.sg/sites/default/files/publication-attachments/a25-wang.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fc/c1/fcc1ae9761926e9e7dbd23c2cb95ca39b0a71073.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2333112.2333120"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator [article]

Yugang Chen, Muchun Chen, Chaoyue Song, Bingbing Ni
<span title="2019-11-14">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Instance based photo cartoonization is one of the challenging image stylization tasks which aim at transforming realistic photos into cartoon style images while preserving the semantic contents of the photos. State-of-the-art Deep Neural Networks (DNNs) methods still fail to produce satisfactory results with input photos in the wild, especially for photos which have high contrast and full of rich textures. This is due to that: cartoon style images tend to have smooth color regions and
more &raquo; ... edges which are contradict to realistic photos which require clear semantic contents, i.e., textures, shapes etc. Previous methods have difficulty in satisfying cartoon style textures and preserving semantic contents at the same time. In this work, we propose a novel "CartoonRenderer" framework which utilizing a single trained model to generate multiple cartoon styles. In a nutshell, our method maps photo into a feature model and renders the feature model back into image space. In particular, cartoonization is achieved by conducting some transformation manipulation in the feature space with our proposed Soft-AdaIN. Extensive experimental results show our method produces higher quality cartoon style images than prior arts, with accurate semantic content preservation. In addition, due to the decoupling of whole generating process into "Modeling-Coordinating-Rendering" parts, our method could easily process higher resolution photos, which is intractable for existing methods.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.06102v1">arXiv:1911.06102v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n3riw7whsrb4pentysksfz7jtq">fatcat:n3riw7whsrb4pentysksfz7jtq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825111244/https://arxiv.org/pdf/1911.06102v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/60/0b/600b9eced5b9c399cf510dd3d908e97a61fd325f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.06102v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Cross-domain Detection via Graph-induced Prototype Alignment [article]

Minghao Xu, Hang Wang, Bingbing Ni, Qi Tian, Wenjun Zhang
<span title="2020-03-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Ni.  ...  noticed that the impressive performance of these models is established, to a great extent, on the basis of massive amounts of annotated data, of which the annotation process *The corresponding author is Bingbing  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12849v1">arXiv:2003.12849v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ha3iewm3ovbn7g5s4cpydoavee">fatcat:ha3iewm3ovbn7g5s4cpydoavee</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200407043826/https://arxiv.org/pdf/2003.12849v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12849v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Properties of the Iron Bacteria Biofouling on Ni–P–rGO Coating

Zhiming Xu, Mingyang Sun, Zuodong Liu, Bingbing Wang, Huishuang Di
<span title="2020-02-25">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
After the carbon steel and the Ni–P–rGO coating were immersed into an iron bacteria solution for 120 h, the weight of the iron bacteria biofouling on the Ni–P–rGO coating sharply decreased when compared  ...  However, in this paper, a nickel–phosphorus–reduced graphene oxide (Ni–P–rGO) coating was prepared on carbon steel by electroless plating to investigate the properties of iron bacteria biofouling.  ...  [5] studied the effect of electroless Ni-P and Ni-Cu-P coatings on the biofouling of iron bacteria, respectively, and they demonstrated that Ni-P and Ni-Cu-P coatings have excellent anti-fouling properties  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10051567">doi:10.3390/app10051567</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ejefnue4vaitoqh7hyqzvkbli">fatcat:6ejefnue4vaitoqh7hyqzvkbli</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200228030146/https://res.mdpi.com/d_attachment/applsci/applsci-10-01567/article_deploy/applsci-10-01567.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6f/c1/6fc199f9e12195cb7f05fc71c7444b8389ce9c11.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10051567"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Adversarial Domain Adaptation with Domain Mixup [article]

Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang
<span title="2019-12-04">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
*The corresponding author is Bingbing Ni. should be domain-invariant, which is the basic motivation of adversarial domain adaptation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.01805v1">arXiv:1912.01805v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qlak6wws25ey3akfv4ywkmj4pm">fatcat:qlak6wws25ey3akfv4ywkmj4pm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904133309/https://arxiv.org/pdf/1912.01805v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/78/fd/78fd36163d6fc32dce1ad7d5b8c1203e6b212fcf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.01805v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Hierarchical Style-based Networks for Motion Synthesis [article]

Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, Trevor Darrell
<span title="2020-08-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world. In this paper, we propose a self-supervised method for generating long-range, diverse and plausible behaviors to achieve a specific goal location. Our proposed method learns to model the motion of human by decomposing a long-range generation task in a hierarchical manner. Given the starting and ending states, a memory bank is used to retrieve motion references
more &raquo; ... as source material for short-range clip generation. We first propose to explicitly disentangle the provided motion material into style and content counterparts via bi-linear transformation modelling, where diverse synthesis is achieved by free-form combination of these two components. The short-range clips are then connected to form a long-range motion sequence. Without ground truth annotation, we propose a parameterized bi-directional interpolation scheme to guarantee the physical validity and visual naturalness of generated results. On large-scale skeleton dataset, we show that the proposed method is able to synthesise long-range, diverse and plausible motion, which is also generalizable to unseen motion data during testing. Moreover, we demonstrate the generated sequences are useful as subgoals for actual physical execution in the animated world.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.10162v1">arXiv:2008.10162v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yd4zkg64vzeqbf4xop7nzbfxv4">fatcat:yd4zkg64vzeqbf4xop7nzbfxv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827085930/https://arxiv.org/pdf/2008.10162v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.10162v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 367 results