scispace - formally typeset
Search or ask a question
Institution

Tencent

CompanyShenzhen, China
About: Tencent is a company organization based out in Shenzhen, China. It is known for research contribution in the topics: Terminal (electronics) & Feature (computer vision). The organization has 9780 authors who have published 10761 publications receiving 100197 citations. The organization is also known as: Téngxùn Kònggǔ Yǒuxiàn Gōngsī & AdvanceDataServices Limited.


Papers
More filters
Posted Content
TL;DR: A detailed review over existing graph neural network models is provided, systematically categorize the applications, and four open problems for future research are proposed.
Abstract: Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.

2,494 citations

Proceedings ArticleDOI
Hao Wang1, Yitong Wang1, Zhou Zheng1, Ji Xing1, Dihong Gong1, Jingchao Zhou1, Zhifeng Li1, Wei Liu1 
18 Jun 2018
TL;DR: In this article, the authors proposed a large margin cosine loss (LMCL), which normalizes both features and weight vectors to remove radial variations, based on which a cosine margin term is introduced to further maximize the decision margin in the angular space.
Abstract: Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature discrimination. However, the traditional softmax loss of deep CNNs usually lacks the power of discrimination. To address this problem, recently several loss functions such as center loss, large margin softmax loss, and angular softmax loss have been proposed. All these improved losses share the same idea: maximizing inter-class variance and minimizing intra-class variance. In this paper, we propose a novel loss function, namely large margin cosine loss (LMCL), to realize this idea from a different perspective. More specifically, we reformulate the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which a cosine margin term is introduced to further maximize the decision margin in the angular space. As a result, minimum intra-class variance and maximum inter-class variance are achieved by virtue of normalization and cosine decision margin maximization. We refer to our model trained with LMCL as CosFace. Extensive experimental evaluations are conducted on the most popular public-domain face recognition datasets such as MegaFace Challenge, Youtube Faces (YTF) and Labeled Face in the Wild (LFW). We achieve the state-of-the-art performance on these benchmarks, which confirms the effectiveness of our proposed approach.

1,879 citations

Proceedings ArticleDOI
20 Jun 2021
TL;DR: Zhang et al. as discussed by the authors proposed a pure transformer to encode an image as a sequence of patches, which can be combined with a simple decoder to provide a powerful segmentation model.
Abstract: Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

1,761 citations

Proceedings ArticleDOI
21 Jul 2017
TL;DR: This paper introduces a novel convolutional neural network dubbed SCA-CNN that incorporates Spatial and Channel-wise Attentions in a CNN that significantly outperforms state-of-the-art visual attention-based image captioning methods.
Abstract: Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the attention mechanism — a dynamic feature extractor that combines contextual fixations over time, as CNN features are naturally spatial, channel-wise and multi-layer. In this paper, we introduce a novel convolutional neural network dubbed SCA-CNN that incorporates Spatial and Channel-wise Attentions in a CNN. In the task of image captioning, SCA-CNN dynamically modulates the sentence generation context in multi-layer feature maps, encoding where (i.e., attentive spatial locations at multiple layers) and what (i.e., attentive channels) the visual attention is. We evaluate the proposed SCA-CNN architecture on three benchmark image captioning datasets: Flickr8K, Flickr30K, and MSCOCO. It is consistently observed that SCA-CNN significantly outperforms state-of-the-art visual attention-based image captioning methods.

1,527 citations

Journal ArticleDOI
01 Jan 2020
TL;DR: In this paper, the authors propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.
Abstract: Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.

1,266 citations


Authors

Showing all 9818 results

NameH-indexPapersCitations
Philip S. Yu1481914107374
Dacheng Tao133136268263
Jian Zhou128300791402
Alan L. Yuille11980478054
Bo Wang119290584863
David Zhang111102755118
Wei Liu102292765228
Wei Liu96153842459
Tong Zhang9341436519
Michael R. Lyu8969633257
Wen Gao88133636100
Yong Xu88139139268
Jiebo Luo8389331341
Xiang Wang8151524199
Jiaya Jia8029433545
Network Information
Related Institutions (5)
Facebook
10.9K papers, 570.1K citations

95% related

Google
39.8K papers, 2.1M citations

95% related

Microsoft
86.9K papers, 4.1M citations

93% related

Adobe Systems
8K papers, 214.7K citations

93% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
202313
202273
20211,343
20201,556
20191,503
20181,401