检索结果-内蒙古大学图书馆

Visual compositional learning for Human-Object interaction detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hou, Zhi Peng, Xiaojiang Qiao, Yu Tao, Dacheng UBTECH Sydney AI Centre School of Computer Science Faculty of Engineering University of Sydney DarlingtonNSW2008 Australia Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail distribution. We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decomposes an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection. Extensive experiments demonstrate that the proposed VCL can effectively improve the generalization of HOI detection on HICO-DET and V-COCO and outperforms the recent state-of-the-art methods on HICO-DET. Code is availab.e at https://***/zhihou7/VCL. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

ICDAR 2019 CROHME + TFD: Competition on recognition of handwritten mathematical expressions and typeset formula detection 15

学校读者我要写书评

暂无评论

ICDAR 2019 CROHME + TFD: Competition on recognition of handw...

15th IAPR International Conference on Document Analysis and recognition, ICDAR 2019

作者： Mahdavi, Mahshad Zanibbi, Richard Mouchere, Harold Viard-Gaudin, Christian Garain, Utpal Document and Pattern Recognition Lab Rochester Institute of Technology RochesterNY United States Christian Viard-Gaudin LS2N-UMR CNRS 6004 University of Nantes Nantes France Computer Vision and Pattern Recognition Unit Centre for Artif. Intel. and Mach. Leaning Indian Statistical Institute Kolkata India

ISBN: (纸本)9781728128610

We summarize the tasks, protocol, and outcome for the 6th Competition on recognition of Handwritten Mathematical Expressions (CROHME), which includes a new formula detection in document images task (+ TFD). For CROHME + TFD 2019, participants chose between two tasks for recognizing handwritten formulas from 1) online stroke data, or 2) images generated from the handwritten strokes. To compare LATEX strings and the lab.led directed trees over strokes (lab.l graphs) used in previous CROHMEs, we convert LATEX and stroke-based lab.l graphs to lab.l graphs defined over symbols (symbol-level lab.l graphs, or symLG). More than thirty (33) participants registered for the competition, with nineteen (19) teams submitting results. The strongest formula recognition results were produced by the USTC-iFLYTEK research team, for both stroke-based (81%) and image-based (77%) input. For the new typeset formula detection task, the Samsung R&D Institute Ukraine (Team 2) obtained a very strong F-score (93%). System performance has improved since the last CROHME-still, the competition results suggest that recognition of handwritten formulae remains a difficult structural pattern recognition task. © 2019 IEEE.

关键词： Trees (mathematics)

EfficientFCN: Holistically-guided decoding for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianbo He, Junjun Zhang, Jiawei Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SenseTime Research China

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Attention-driven dynamic graph convolutional network for multi-lab.l image recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ye, Jin He, Junjun Peng, Xiaojiang Wu, Wenhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Recent studies often exploit Graph Convolutional Network (GCN) to model lab.l dependencies to improve recognition accuracy for multi-lab.l image recognition. However, constructing a graph by counting the lab.l co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in test images. Our goal is to eliminate such bias and enhance the robustness of the learnt features. To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image. ADD-GCN adopts a Dynamic Graph Convolutional Network (D-GCN) to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Extensive experiments on public multi-lab.l benchmarks demonstrate the effectiveness of our method, which achieves mAPs of 85.2%, 96.0%, and 95.5% on MS-COCO, VOC2007, and VOC2012, respectively, and outperforms current state-of-the-art methods with a clear margin. All codes can be found at https://***/Yejin0111/ADD-GCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

TTPP: Temporal transformer with progressive prediction for efficient action anticipation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Wen Peng, Xiaojiang Su, Yanzhou Qiao, Yu Cheng, Jian School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

A learning-based method for online adjustment of C-arm cone-beam CT source trajectories for artifact avoidance

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Thies, Mareike Zäch, Jan-Nico Gao, Cong Taylor, Russell Navab, Nassir Maier, Andreas Unberath, Mathias Laboratory for Computational Sensing + Robotics Johns Hopkins University BaltimoreMD United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Computer Vision Laboratory Eidgenössische Technische Hochschule Zürich

Purpose: During spinal fusion surgery, screws are placed close to critical nerves suggesting the need for highly accurate screw placement. Verifying screw placement on high-quality tomographic imaging is essential. C-arm Cone-beam CT (CBCT) provides intraoperative 3D tomographic imaging which would allow for immediate verification and, if needed, revision. However, the reconstruction quality attainable with commercial CBCT devices is insufficient, predominantly due to severe metal artifacts in the presence of pedicle screws. These artifacts arise from a mismatch between the true physics of image formation and an idealized model thereof assumed during reconstruction. Prospectively acquiring views onto anatomy that are least affected by this mismatch can, therefore, improve reconstruction quality. Methods: We propose to adjust the C-arm CBCT source trajectory during the scan to optimize reconstruction quality with respect to a certain task, i.e. verification of screw placement. Adjustments are performed on-the-fly using a convolutional neural network that regresses a quality index over all possible next views given the current x-ray image. Adjusting the CBCT trajectory to acquire the recommended views results in non-circular source orbits that avoid poor images, and thus, data inconsistencies. Results: We demonstrate that convolutional neural networks trained on realistically simulated data are capable of predicting quality metrics that enable scene-specific adjustments of the CBCT source trajectory. Using both realistically simulated data as well as real CBCT acquisitions of a semianthropomorphic phantom, we show that tomographic reconstructions of the resulting scene-specific CBCT acquisitions exhibit improved image quality particularly in terms of metal artifacts. Conclusion: The proposed method is a step towards online patient-specific C-arm CBCT source trajectories that enable high-quality tomographic imaging in the operating room. Since the optimization objectiv

关键词： Convolution

Tensor Low-Rank Reconstruction for Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Wanli Zhu, Xinge Sun, Ruoqi He, Junjun Li, Ruiyu Shen, Xiaoyong Yu, Bei Chinese University of Hong Kong Hong Kong Shanghai Jiao Tong University China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SmartMore United States

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since the desired context consists of spatial-wise and channel-wise attentions, 3D representation is an appropriate formulation. However, these non-local methods describe 3D context information based on a 2D similarity matrix, where space compression may lead to channel-wise attention missing. An alternative is to model the contextual information directly without compression. However, this effort confronts a fundamental difficulty, namely the high-rank property of context information. In this paper, we propose a new approach to model the 3D context representations, which not only avoids the space compression but also tackles the high-rank difficulty. Here, inspired by tensor canonical-polyadic decomposition theory (i.e, a high-rank tensor can be expressed as a combination of rank-1 tensors.), we design a low-rank-to-high-rank context reconstruction framework (i.e, RecoNet). Specifically, we first introduce the tensor generation module (TGM), which generates a number of rank-1 tensors to capture fragments of context feature. Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM). Extensive experiments show that our method achieves state-of-the-art on various public datasets. Additionally, our proposed method has more than 100 times less computational cost compared with conventional non-local-based methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Tensors

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM Image Processing

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hu, Rui Cai, Jiaming Zheng, Wangjie Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai200240 China

ISBN: (纸本)9781728162157

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-lab.ls and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-lab.ls are updated iteratively to enhance the reliability of lab.ls. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools. © 2020 IEEE.

关键词： Image reconstruction

Conditional sequential modulation for efficient global image retouching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence Robotics for Society Korea Republic of University of Chinese Academy of Sciences China

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1×1 convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is availab.e at https://***/hejingwenhejingwen/CSRNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels