Search Results for author:
Found 12 papers, 8 papers with code
Enhanced Event-Based Video Reconstruction with Motion Compensation
To address this, we propose warping the input intensity frames and sparse codes to enhance reconstruction quality.
WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing
WiFi-based human sensing has exhibited remarkable potential to analyze user behaviors in a non-intrusive and device-free manner, benefiting applications as diverse as smart homes and healthcare.
First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures
In the backpropagation, we develop an error assignment method that propagates error from FS times to spikes through a Gaussian window, and then supervised learning for spikes is implemented through a surrogate gradient approach.
Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from Events
In this paper, we propose a light, simple model-based deep network for E2V reconstruction, explore the diversity for adjacent pixels in V2E generation, and finally build a video-to-events-to-video (V2E2V) architecture to validate how alternative event generation strategies improve video reconstruction.
Context-aware Style Learning and Content Recovery Networks for Neural Style Transfer
Neural text transfer aims to change the style of a text sequence while keeping its original content.
Locally varying distance transform for unsupervised visual anomaly detection
Unsupervised anomaly detection on image data is notoriously unstable.
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly
+3
Distance Based Image Classification: A solution to generative classification's conundrum?
We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues.
Shell Theory: A Statistical Model of Reality
The foundational assumption of machine learning is that the data under consideration is separable into classes; while intuitively reasonable, separability constraints have proven remarkably difficult to formulate mathematically.
Ranked #1 on
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly
on STL-10
(using extra training data)
Deep unsupervised anomaly detection
This paper proposes a novel method to detect anomalies in large datasets under a fully unsupervised setting.
Dual-SLAM: A framework for robust single camera navigation
As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle.
Dimensionality's Blessing: Clustering Images by Underlying Distribution
Many high dimensional vector distances tend to a constant.
PatchMatch-Based Automatic Lattice Detection for Near-Regular Textures
In this work, we investigate the problem of automatically inferring the lattice structure of near-regular textures (NRT) in real-world images.
