116 citations · 430 across the 65 of their papers we have counts for
65 papers
Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding
Fangzhou Lin, Qianwen Ge, Lingyu Xu +7
AI systems increasingly produce fluent, correct, end-to-end outcomes. Over time, this erodes users' ability to explain, verify, or intervene. We define this divergence as the Capab…
NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
Fangzhou Lin, Yuping Wang, Yuliang Guo +7
Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the…
TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting
Lingyu Jiang, Lingyu Xu, Peiran Li +14
We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice Learning (MCL)…
KANMixer: a minimal KAN-centered mixer for long-term time series forecasting
Lingyu Jiang, Dengzhe Hou, Yuping Wang +9
Long-term time series forecasting (LTSF) underpins critical applications from energy management to weather prediction, yet achieving reliable multi-step-ahead accuracy remains chal…
A Strong View-Free Baseline Approach for Single-View Image Guided Point Cloud Completion
Fangzhou Lin, Zilin Dai, Rigved Sanku +4
The single-view image guided point cloud completion (SVIPC) task aims to reconstruct a complete point cloud from a partial input with the help of a single-view image. While previou…
A Language Anchor-Guided Method for Robust Noisy Domain Generalization
Zilin Dai, Lehong Wang, Fangzhou Lin +5
Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninforma…
Hyperbolic Chamfer Distance for Point Cloud Completion and Beyond
Fangzhou Lin, Songlin Hou, Haotian Liu +4
Chamfer Distance (CD) is widely used as a metric to quantify difference between two point clouds. In point cloud completion, Chamfer Distance (CD) is typically used as a loss funct…
SPADE: Spectroscopic Photoacoustic Denoising using an Analytical and Data-free Enhancement Framework
Fangzhou Lin, Shang Gao, Yichuan Tang +6
Spectroscopic photoacoustic (sPA) imaging uses multiple wavelengths to differentiate chromophores based on their unique optical absorption spectra. This technique has been widely a…
Deep Loss Convexification for Learning Iterative Models
Ziming Zhang, Yuping Shao, Yiqing Zhang +3
Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality (e.g. saddle points), due to the nature of nonconvex opt…
Robust 3D Point Clouds Classification based on Declarative Defenders
Kaidong Li, Tianxiao Zhang, Cuncong Zhong +2
3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are uns…
Wildlife Product Trading in Online Social Networks: A Case Study on Ivory-Related Product Sales Promotion Posts
Guanyi Mou, Yun Yue, Kyumin Lee +1
Wildlife trafficking (WLT) has emerged as a global issue, with traffickers expanding their operations from offline to online platforms, utilizing e-commerce websites and social net…
Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance
Fangzhou Lin, Haotian Liu, Haoying Zhou +6
3D point clouds enhanced the robot's ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection…
Guiding the Last Centimeter: Novel Anatomy-Aware Probe Servoing for Standardized Imaging Plane Navigation in Robotic Lung Ultrasound
Xihan Ma, Mingjie Zeng, Jeffrey C. Hill +3
Navigating the ultrasound (US) probe to the standardized imaging plane (SIP) for image acquisition is a critical but operator-dependent task in conventional freehand diagnostic US.…
Understanding Hyperbolic Metric Learning through Hard Negative Sampling
Yun Yue, Fangzhou Lin, Guanyi Mou +1
In recent years, there has been a growing trend of incorporating hyperbolic geometry methods into computer vision. While these methods have achieved state-of-the-art performance on…
PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment
Yiqing Zhang, Xinming Huang, Ziming Zhang
The Lucas-Kanade (LK) method is a classic iterative homography estimation algorithm for image alignment, but often suffers from poor local optimality especially when image pairs ha…
Self-supervised Geometric Features Discovery via Interpretable Attentio for Vehicle Re-Identification and Beyond (Complete Version)
Ming Li, Xinming Huang, Ziming Zhang
To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requir…
Hyperbolic Contrastive Learning
Yun Yue, Fangzhou Lin, Kazunori D Yamada +1
Learning good image representations that are beneficial to downstream tasks is a challenging task in computer vision. As such, a wide variety of self-supervised learning approaches…
Simultaneous Estimation of Hand Configurations and Finger Joint Angles using Forearm Ultrasound
Keshav Bimbraw, Christopher J. Nycz, Matt Schueler +2
With the advancement in computing and robotics, it is necessary to develop fluent and intuitive methods for interacting with digital systems, augmented/virtual reality (AR/VR) inte…
EgoSpeed-Net: Forecasting Speed-Control in Driver Behavior from Egocentric Video Data
Yichen Ding, Ziming Zhang, Yanhua Li +1
Speed-control forecasting, a challenging problem in driver behavior analysis, aims to predict the future actions of a driver in controlling vehicle speed such as braking or acceler…
Robust Object Detection With Inaccurate Bounding Boxes
Chengxin Liu, Kewei Wang, Hao Lu +2
Learning accurate object detectors often requires large-scale training data with precise object bounding boxes. However, labeling such data is expensive and time-consuming. As the…
Auto-Encoding Adversarial Imitation Learning
Kaifeng Zhang, Rui Zhao, Ziming Zhang +1
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function. Adversarial Imit…
Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients
Kaidong Li, Ziming Zhang, Cuncong Zhong +1
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn…
CoFi: Coarse-to-Fine ICP for LiDAR Localization in an Efficient Long-lasting Point Cloud Map
Yecheng Lyu, Xinming Huang, Ziming Zhang
LiDAR odometry and localization has attracted increasing research interest in recent years. In the existing works, iterative closest point (ICP) is widely used since it is precise…
Don't Knock! Rowhammer at the Backdoor of DNN Models
M. Caner Tol, Saad Islam, Andrew J. Adiletta +2
State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on…