Search Results - "Fuxin, Li"
-
1
PointConv: Deep Convolutional Networks on 3D Point Clouds
Published in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2019)“…Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult…”
Get full text
Conference Proceeding -
2
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
Published in 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2019)“…Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap…”
Get full text
Conference Proceeding -
3
Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics
Published in 2017 IEEE International Conference on Computer Vision (ICCV) (01-10-2017)“…Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can…”
Get full text
Conference Proceeding -
4
Video Segmentation by Tracking Many Figure-Ground Segments
Published in 2013 IEEE International Conference on Computer Vision (01-12-2013)“…We propose an unsupervised video segmentation approach by simultaneously tracking multiple holistic figure-ground segments. Segment tracks are initialized from…”
Get full text
Conference Proceeding Journal Article -
5
Space–time recurrent memory network
Published in Computer vision and image understanding (01-04-2024)“…Transformers have recently been popular for learning and inference in the spatial–temporal domain. However, their performance relies on storing and applying…”
Get full text
Journal Article -
6
Cycle-Consistent Counterfactuals by Latent Transformations
Published in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2022)“…CounterFactual (CF) visual explanations try to find images similar to the query image that change the decision of a vision system to a specified outcome…”
Get full text
Conference Proceeding -
7
Multiple Hypothesis Tracking Revisited
Published in 2015 IEEE International Conference on Computer Vision (ICCV) (01-12-2015)“…This paper revisits the classical multiple hypotheses tracking (MHT) algorithm in a tracking-by-detection framework. The success of MHT largely depends on the…”
Get full text
Conference Proceeding Journal Article -
8
TASC:Topic-Adaptive Sentiment Classification on Dynamic Tweets
Published in IEEE transactions on knowledge and data engineering (01-06-2015)“…Sentiment classification is a topic-sensitive task, i.e., a classifier trained from one topic will perform worse on another. This is especially a problem for…”
Get full text
Journal Article -
9
PointConvFormer: Revenge of the Point-based Convolution
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2023)“…We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer…”
Get full text
Conference Proceeding -
10
Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking
Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2021)“…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…”
Get full text
Conference Proceeding -
11
Object Recognition by Sequential Figure-Ground Ranking
Published in International journal of computer vision (01-07-2012)“…We present an approach to visual object-class segmentation and recognition based on a pipeline that combines multiple figure-ground hypotheses with large…”
Get full text
Journal Article -
12
Adversarial Training on Point Clouds for Sim-to-Real 3D Object Detection
Published in IEEE robotics and automation letters (01-10-2021)“…In this work we address the problem of 3D object detection from point clouds in data-limited environments. Training with simulated data is a common approach in…”
Get full text
Journal Article -
13
Improving the Robustness of Point Convolution on k-Nearest Neighbor Neighborhoods with a Viewpoint-Invariant Coordinate Transform
Published in 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (01-01-2023)“…Recently, there is significant interest in performing convolution over irregularly sampled point clouds. Point clouds are very different from raster images, in…”
Get full text
Conference Proceeding -
14
Morphodynamics facilitate cancer cells to navigate 3D extracellular matrix
Published in Scientific reports (14-10-2021)“…Cell shape is linked to cell function. The significance of cell morphodynamics, namely the temporal fluctuation of cell shape, is much less understood. Here we…”
Get full text
Journal Article -
15
Latent structured models for human pose estimation
Published in 2011 International Conference on Computer Vision (01-11-2011)“…We present an approach for automatic 3D human pose reconstruction from monocular images, based on a discriminative formulation with latent segmentation inputs…”
Get full text
Conference Proceeding -
16
NopC/T/L Signal Crosstalk Gene GmPHT1-4
Published in International journal of molecular sciences (20-11-2023)“…Symbiotic nodulation between leguminous plants and rhizobia is a critical biological interaction. The type III secretion system (T3SS) employed by rhizobia…”
Get full text
Journal Article -
17
Medullary Thyroid Carcinoma With Elevated Serum CEA and Normal Serum Calcitonin After Surgery: A Case Report and Literature Review
Published in Frontiers in oncology (27-10-2020)“…Medullary thyroid carcinoma (MTC) is a relatively rare malignant tumor subtype originated the parafollicular C cells of the thyroid gland, producing tumor…”
Get full text
Journal Article -
18
Identification of a Six Gene Prognosis Signature for Papillary Thyroid Cancer Using Multi-Omics Methods and Bioinformatics Analysis
Published in Frontiers in oncology (18-03-2021)“…Papillary thyroid carcinoma (PTC) is the most common subtype of thyroid cancer. PTC is typically curable with an excellent survival rate; however, some…”
Get full text
Journal Article -
19
RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions
Published in 2014 IEEE Conference on Computer Vision and Pattern Recognition (01-06-2014)“…Popular figure-ground segmentation algorithms generate a pool of boundary-aligned segment proposals that can be used in subsequent object recognition engines…”
Get full text
Conference Proceeding -
20
Genome‐wide association study and network analysis of in vitro transformation in Populus trichocarpa support key roles of diverse phytohormone pathways and cross talk
Published in The New phytologist (01-06-2024)“…Summary Wide variation in amenability to transformation and regeneration (TR) among many plant species and genotypes presents a challenge to the use of genetic…”
Get full text
Journal Article