Share This Author
Video Segmentation by Tracking Many Figure-Ground Segments
- Fuxin Li, Taeyoung Kim, Ahmad Humayun, David Tsai, James M. Rehg
- Computer ScienceIEEE International Conference on Computer Vision
- 1 December 2013
An unsupervised video segmentation approach by simultaneously tracking multiple holistic figure-ground segments that outperforms state-of-the-art approaches in the dataset, showing its efficiency and robustness to challenges in different video sequences.
PointConv: Deep Convolutional Networks on 3D Point Clouds
- Wenxuan Wu, Zhongang Qi, Fuxin Li
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 17 November 2018
The dynamic filter is extended to a new convolution operation, named PointConv, which can be applied on point clouds to build deep convolutional networks and is able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds.
Multiple Hypothesis Tracking Revisited
- Chanho Kim, Fuxin Li, A. Ciptadi, James M. Rehg
- Computer ScienceIEEE International Conference on Computer Vision…
- 7 December 2015
It is demonstrated that a classical MHT implementation from the 90's can come surprisingly close to the performance of state-of-the-art methods on standard benchmark datasets, and it is shown that appearance models can be learned efficiently via a regularized least squares framework.
Open Set Learning with Counterfactual Images
- Lawrence Neal, M. Olson, Xiaoli Z. Fern, Weng-Keen Wong, Fuxin Li
- Computer ScienceECCV
- 8 September 2018
This work introduces a dataset augmentation technique that is based on generative adversarial networks that generates examples that are close to training set examples yet do not belong to any training category, and outperforms existing open set recognition algorithms on a selection of image classification tasks.
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation
A novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse- to-fine fashion, and shows great generalization ability on the KITTI Scene Flow 2015 dataset, outperforming all previous methods.
Multi-object Tracking with Neural Gating Using Bilinear LSTM
A novel recurrent network model, the Bilinear LSTM, is proposed in order to improve the learning of long-term appearance models via a recurrent network based on intuitions drawn from recursive least squares.
Object Recognition by Sequential Figure-Ground Ranking
- João Carreira, Fuxin Li, C. Sminchisescu
- Computer ScienceInternational Journal of Computer Vision
- 1 July 2012
We present an approach to visual object-class segmentation and recognition based on a pipeline that combines multiple figure-ground hypotheses with large object spatial support, generated by…
PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
This work proposes a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse- to-fine fashion, which shows great generalization ability on KITTI Scene Flow 2015 dataset, outperforming all previous methods.
Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
Improved 3D structure and temporally consistent semantic segmentation for difficult, large scale, forward moving monocular image sequences is demonstrated.
Latent structured models for human pose estimation
- Catalin Ionescu, Fuxin Li, C. Sminchisescu
- Computer ScienceInternational Conference on Computer Vision
- 6 November 2011
This work presents an approach for automatic 3D human pose reconstruction from monocular images, based on a discriminative formulation with latent segmentation inputs, and provides primal linear re-formulations based on Fourier kernel approximations in order to scale-up the non-linear latent structured prediction methodology.