Don’t Hit Me! Glass Detection in Real-World Scenes

Mei, Haiyang; Yang, Xin; Wang, Yang; Liu, Yuan Yuan; He, Shengfeng; Zhang, Qiang; Wei, Xiaopeng; Lau, Rynson W. H.

doi:10.1109/cvpr42600.2020.00374

Cited by 92 publications

(110 citation statements)

References 36 publications

Supporting

Mentioning

110

Contrasting

Order By: Relevance

“…Motivated by the work in [11], which introduces a novel large-field contextual feature integration (LCFI) module, to capture long-range dependencies, we propose a deep dealiasing LCFI (LCFI++) block displayed in Figure 1. We replace the spatially separable convolution with shallow Unets in the parallel structure of LCFI.…”

Section: Lcfi++mentioning

confidence: 99%

Fine-Grained Mri Reconstruction Using Attentive Selection Generative Adversarial Networks

Liu

Yaghoobi

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Compressed sensing (CS) leverages the sparsity prior to provide the foundation for fast magnetic resonance imaging (fastMRI). However, iterative solvers for ill-posed problems hinder their adaption to time-critical applications. Moreover, such a prior can be neither rich to capture complicated anatomical structures nor applicable to meet the demand of high-fidelity reconstructions in modern MRI.Inspired by the state-of-the-art methods in image generation, we propose a novel attention-based deep learning framework to provide high-quality MRI reconstruction. We incorporate large-field contextual feature integration and attention selection in a generative adversarial network (GAN) framework. We demonstrate that the proposed model can produce superior results compared to other deep learning-based methods in terms of image quality, and relevance to the MRI reconstruction in an extremely low sampling rate diet.

show abstract

Section: Lcfi++mentioning

confidence: 99%

Fine-Grained Mri Reconstruction Using Attentive Selection Generative Adversarial Networks

Liu

Yaghoobi

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Recently, large-scale transparent object segmentation datasets emerge [14], [24], [42], [45], [46]. Mei et al [14] constructed the glass detection dataset in daily-life scenes.…”

Section: B Transparent Object Sensingmentioning

confidence: 99%

“…Recently, large-scale transparent object segmentation datasets emerge [14], [24], [42], [45], [46]. Mei et al [14] constructed the glass detection dataset in daily-life scenes. Xie et al [24], [46] built the Trans10K dataset and validated that while pure RGB-based transparent object segmentation is rather a largely unsolved task, it is potential for realworld usages with the increased data amount.…”

Section: B Transparent Object Sensingmentioning

confidence: 99%

Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance

Zhang¹,

Yang²,

Constantinescu³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…Visual object tracking is an important topic in computer vision, where the target object is identified in the first frame and tracked in all frames of a video. Due to the significant learning ability, deep convolutional neural networks (DCNNs) have been widely used to object detection [34,35,62], image matting [42,43,64], super-resolution [63,67,68], image enhancement [61,65] and visual object tracking [2,[11][12][13]15,19,22,28,32,33,38,47,58,[70][71][72]. However, RGB-based trackers suffer from bad environmental conditions, e.g., low illumination, fast motion, and so on.…”

Section: Introductionmentioning

confidence: 99%

Multi-domain collaborative feature representation for robust visual object tracking

et al. 2021

Self Cite

View full text Add to dashboard Cite

Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking. This paper focuses on effectively representing and utilizing complementary features from the frame domain and event domain for boosting object tracking performance in challenge scenarios. Specifically, we propose common features extractor to learn potential common representations from the RGB domain and event domain. For learning the unique features of the two domains, we utilize a unique extractor for event based on Spiking neural networks to extract edge cues in the event domain which may be missed in RGB in some challenging conditions, and a unique extractor for RGB based on deep convolutional neural networks to extract texture and semantic information in RGB domain. Extensive experiments on standard RGB benchmark and real event tracking dataset demonstrate the effectiveness of the proposed approach. We show our approach outperforms all compared state-of-the-art tracking algorithms and verify event-based data is a powerful cue for tracking in challenging scenes. Keywords Visual object tracking • Event-based camera • Multi-domain • Challenging conditions Jiqing Zhang and Kai Zhao have contributed equally to this study.

show abstract

Don’t Hit Me! Glass Detection in Real-World Scenes

Cited by 92 publications

References 36 publications

Fine-Grained Mri Reconstruction Using Attentive Selection Generative Adversarial Networks

Fine-Grained Mri Reconstruction Using Attentive Selection Generative Adversarial Networks

Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance

Multi-domain collaborative feature representation for robust visual object tracking

Contact Info

Product

Resources

About