BORRBangladesh Open Research Repository
SearchSubmitAboutContact
BORRResearch for a Better Bangladesh.
AboutSubmit PaperContactTermsPolicyGitHub

© 2026 Bangladesh Open Research Repository.

Filters

Sort By

Sort by relevanceSort by dateSort by citations
Year Range
to

Results for “"Xinmei Tian"”

8 results

Gaussian Temporal Awareness Networks for Action Localization

Verified

Fuchen Long, Ting Yao, Zhaofan Qiu, Xinmei Tian et al.

Year: 2019Citations: 382

Temporally localizing actions in a video is a fundamental challenge in video understanding. Most existing approaches have often drawn inspiration from image object detection and extended the advances, e.g., SSD and Faster R-CNN, to produce temporal locations of an action in a 1D sequence. Neverthele...

Physical Sciences
Computer Science
Computer Vision and Pattern Recognition
Read Source

Exploring Object Relation in Mean Teacher for Cross-Domain Detection

Verified

Qi Cai, Yingwei Pan, Chong‐Wah Ngo, Xinmei Tian et al.

Year: 2019Citations: 356

Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may lead to high generalization error on real images due to doma...

Physical SciencesComputer ScienceArtificial Intelligence
Read Source

Learning Spatio-Temporal Representation With Local and Global Diffusion

Verified

Zhaofan Qiu, Ting Yao, Chong‐Wah Ngo, Xinmei Tian et al.

Year: 2019Citations: 217

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are local operations while ignoring the large-range dependency. Such drawback becomes even worse particularly for video reco...

Physical SciencesComputer ScienceComputer Vision and Pattern RecognitionOpen Access
Read Source

Camera Lens Super-Resolution

Verified

Chang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha et al.

Year: 2019Citations: 180

Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling. In this paper, we investigate SR from the perspective of camera lenses, named as CameraSR, which aims to alleviate the intrinsic tradeoff betwee...

Physical SciencesComputer ScienceComputer Vision and Pattern Recognition
Read Source

Camera Lens Super-Resolution

Verified

Chang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha et al.

Journal: arXiv (Cornell University)Year: 2019Citations: 9

Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling. In this paper, we investigate SR from the perspective of camera lenses, named as CameraSR, which aims to alleviate the intrinsic tradeoff betwee...

Physical SciencesComputer ScienceComputer Vision and Pattern RecognitionOpen Access
Read Source

Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks

Verified

Yonggang Zhang, Ya Li, Tongliang Liu, Xinmei Tian

Journal: Rare & Special e-Zone (The Hong Kong University of Science and Technology)Year: 2020Citations: 4

We study the problem of constructing black-box adversarial attacks, where no model information is revealed except for the feedback knowledge of the given inputs. To obtain sufficient knowledge for crafting adversarial examples, previous methods query the target model with inputs that are perturbed w...

Physical SciencesComputer ScienceComputer Networks and Communications
Read Source

Prognostic ability of the haemoglobin-to-red blood cell distribution width ratio in predicting in-hospital mortality: a retrospective, longitudinal, observational study among elderly patients with acute ischaemic stroke

Verified

Feiran Wei, Na Liu, Min Zhang, Yanhang Yin et al.

Journal: BMJ OpenYear: 2025Citations: 1

OBJECTIVE: To evaluate the prognostic ability of the haemoglobin-to-red blood cell distribution width ratio in predicting in-hospital mortality among elderly patients diagnosed with acute ischaemic stroke. DESIGN: Retrospective, longitudinal, observational study using a hospital-based database. SETT...

Health SciencesMedicineOncologyOpen Access
Read Source

Gaussian Temporal Awareness Networks for Action Localization

Verified

Fuchen Long, Ting Yao, Zhaofan Qiu, Xinmei Tian et al.

Journal: arXiv (Cornell University)Year: 2019

Temporally localizing actions in a video is a fundamental challenge in video understanding. Most existing approaches have often drawn inspiration from image object detection and extended the advances, e.g., SSD and Faster R-CNN, to produce temporal locations of an action in a 1D sequence. Neverthele...

Physical SciencesComputer ScienceComputer Vision and Pattern RecognitionOpen Access
Read Source
PreviousPage 1 of 1Next