Deformable Convolutional Networks
- Jifeng Dai, Haozhi Qi, Yichen Wei
- Computer ScienceIEEE International Conference on Computer Vision
- 17 March 2017
This work introduces two new modules to enhance the transformation modeling capability of CNNs, namely, deformable convolution and deformable RoI pooling, based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from the target tasks, without additional supervision.
Simple Baselines for Human Pose Estimation and Tracking
- Bin Xiao, Haiping Wu, Yichen Wei
- Computer ScienceEuropean Conference on Computer Vision
- 17 April 2018
This work provides simple and effective baseline methods for pose estimation that are helpful for inspiring and evaluating new ideas for the field and achieved on challenging benchmarks.
Saliency Optimization from Robust Background Detection
- Wangjiang Zhu, Shuang Liang, Yichen Wei, Jian Sun
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 23 June 2014
This work proposes a robust background measure, called boundary connectivity, which characterizes the spatial layout of image regions with respect to image boundaries and is much more robust and presents unique benefits that are absent in previous saliency measures.
Face Alignment by Explicit Shape Regression
- Xudong Cao, Yichen Wei, Fang Wen, Jian Sun
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 16 June 2012
A very efficient, highly accurate, “Explicit Shape Regression” approach for face alignment that significantly outperforms the state-of-the-art in terms of both accuracy and efficiency.
Face Alignment at 3000 FPS via Regressing Local Binary Features
- Shaoqing Ren, Xudong Cao, Yichen Wei, Jian Sun
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 23 June 2014
This paper presents a highly efficient, very accurate regression approach for face alignment that achieves the state-of-the-art results when tested on the current most challenging benchmarks.
Geodesic Saliency Using Background Priors
- Yichen Wei, Fang Wen, Wangjiang Zhu, Jian Sun
- Computer ScienceEuropean Conference on Computer Vision
- 7 October 2012
Evaluation on two databases validates that geodesic saliency achieves superior results and outperforms previous approaches by a large margin, in both accuracy and speed (2 ms per image), illustrating that appropriate prior exploitation is helpful for the ill-posed saliency detection problem.
Single Path One-Shot Neural Architecture Search with Uniform Sampling
- Zichao Guo, Xiangyu Zhang, Jian Sun
- Computer ScienceEuropean Conference on Computer Vision
- 31 March 2019
A Single Path One-Shot model is proposed to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated.
Flow-Guided Feature Aggregation for Video Object Detection
- Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, Yichen Wei
- Computer ScienceIEEE International Conference on Computer Vision
- 29 March 2017
This work presents flow-guided feature aggregation, an accurate and end-to-end learning framework for video object detection that improves the per-frame features by aggregation of nearby features along the motion paths, and thus improves the video recognition accuracy.
Deep Feature Flow for Video Recognition
- Xizhou Zhu, Yuwen Xiong, Jifeng Dai, Lu Yuan, Yichen Wei
- Computer ScienceComputer Vision and Pattern Recognition
- 23 November 2016
Deep feature flow is presented, a fast and accurate framework for video recognition that runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field and achieves significant speedup as flow computation is relatively fast.
Integral Human Pose Regression
- Xiao Sun, Bin Xiao, Shuang Liang, Yichen Wei
- Computer ScienceEuropean Conference on Computer Vision
- 22 November 2017
This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues and is differentiable, efficient, and compatible with any heat map based methods.
...
...