102 citations · 570 across the 31 of their papers we have counts for
22 papers · 1 filter
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Jialin Yuan, Jay Patravali, Hung Nguyen +2
Unsupervised Video Object Segmentation (UVOS) aims at discovering objects and tracking them through videos. For accurate UVOS, we observe if one can locate precise segment proposal…
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
Ye Yu, Jialin Yuan, Gaurav Mittal +2
Video Object Segmentation (VOS) is fundamental to video understanding. Transformer-based methods show significant performance improvement on semi-supervised VOS. However, existing…
Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation
Jay Patravali, Gaurav Mittal, Ye Yu +2
We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D…
Space Time Recurrent Memory Network
Hung Nguyen, Chanho Kim, Fuxin Li
Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the featur…
Topology-Aware Segmentation Using Discrete Morse Theory
Xiaoling Hu, Yusu Wang, Li Fuxin +2
In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern. Topological correctness, such as vessel conne…
Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking
Chanho Kim, Li Fuxin, Mazen Alotaibi +1
In multi-object tracking, the tracker maintains in its memory the appearance and motion information for each object in the scene. This memory is utilized for finding matches betwee…
iGOS++: Integrated Gradient Optimized Saliency by Bilateral Perturbations
Saeed Khorram, Tyler Lawson, Fuxin Li
The black-box nature of the deep networks makes the explanation for "why" they make certain predictions extremely challenging. Saliency maps are one of the most widely-used local e…
Deep Variational Instance Segmentation
Jialin Yuan, Chao Chen, Li Fuxin
Instance Segmentation, which seeks to obtain both class and instance labels for each pixel in the input image, is a challenging task in computer vision. State-of-the-art algorithms…
PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
Wenxuan Wu, Zhiyuan Wang, Zhuwen Li +2
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion. Flow computed at the coarse level is upsampled and warped…
Visualizing Point Cloud Classifiers by Curvature Smoothing
Chen Ziwen, Wenxuan Wu, Zhongang Qi +1
Recently, several networks that operate directly on point clouds have been proposed. There is significant utility in understanding their mechanisms to classify point clouds, which…
Topology-Preserving Deep Image Segmentation
Xiaoling Hu, Li Fuxin, Dimitris Samaras +1
Segmentation algorithms are prone to make topological errors on fine-scale structures, e.g., broken connections. We propose a novel method that learns to segment with correct topol…
Visualizing Deep Networks by Optimizing with Integrated Gradients
Zhongang Qi, Saeed Khorram, Li Fuxin
Understanding and interpreting the decisions made by deep learning models is valuable in many domains. In computer vision, computing heatmaps from a deep network is a popular appro…
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
Xinyao Wang, Liefeng Bo, Li Fuxin
Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely studied…
PointConv: Deep Convolutional Networks on 3D Point Clouds
Wenxuan Wu, Zhongang Qi, Li Fuxin
Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we exte…
Purely Geometric Scene Association and Retrieval - A Case for Macro Scale 3D Geometry
Rahul Sawhney, Fuxin Li, Henrik I. Christensen +1
We address the problems of measuring geometric similarity between 3D scenes, represented through point clouds or range data frames, and associating them. Our approach leverages mac…
Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks
Neale Ratzlaff, Li Fuxin
Recent analysis of deep neural networks has revealed their vulnerability to carefully structured adversarial examples. Many effective algorithms exist to craft these adversarial ex…
Embedding Deep Networks into Visual Explanations
Zhongang Qi, Saeed Khorram, Fuxin Li
In this paper, we propose a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by learning a nonlinear embedding of a high-dime…
Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion
Peng Lei, Fuxin Li, Sinisa Todorovic
Using deep learning, this paper addresses the problem of joint object boundary detection and boundary motion estimation in videos, which we named boundary flow estimation. Boundary…
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
Xin Li, Fuxin Li
Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the…
A Continuous Optimization Approach for Efficient and Accurate Scene Flow
Zhaoyang Lv, Chris Beall, Pablo F. Alcantarilla +3
We propose a continuous optimization method for solving dense 3D scene flow problems from stereo imagery. As in recent work, we represent the dynamic 3D scene as a collection of ri…
GASP : Geometric Association with Surface Patches
Rahul Sawhney, Fuxin Li, Henrik I. Christensen
A fundamental challenge to sensory processing tasks in perception and robotics is the problem of obtaining data associations across views. We present a robust solution for ascertai…
Learning Random Kernel Approximations for Object Recognition
Eduard Gabriel Băzăvan, Fuxin Li, Cristian Sminchisescu
Approximations based on random Fourier features have recently emerged as an efficient and formally consistent methodology to design large-scale kernel machines. By expressing the k…