Search Results for author: Hongkai Wen

Found 21 papers, 11 papers with code

SignGraph: A Sign Sequence is Worth Graphs of Nodes

1 code implementation CVPR 2024 Shiwei Gan, Yafeng Yin, Zhiwei Jiang, Hongkai Wen, Lei Xie, Sanglu Lu

In fact sign language tasks need to focus on the correlation of different regions in one frame and the interaction of different regions among adjacent frames for identifying a sign sequence.

Fast Sampling Through The Reuse Of Attention Maps In Diffusion Models

no code implementations13 Dec 2023 Rosco Hunter, Łukasz Dudziak, Mohamed S. Abdelfattah, Abhinav Mehrotra, Sourav Bhattacharya, Hongkai Wen

Our specific reuse strategies are based on ODE theory, which implies that the later a map is reused, the smaller the distortion in the final image.

Image Generation Knowledge Distillation

How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor

no code implementations30 Nov 2023 Hrushikesh Loya, Łukasz Dudziak, Abhinav Mehrotra, Royson Lee, Javier Fernandez-Marques, Nicholas D. Lane, Hongkai Wen

Neural architecture search has proven to be a powerful approach to designing and refining neural networks, often boosting their performance and efficiency over manually-designed variations, but comes with computational overhead.

Image Classification Meta-Learning +1

Fusion of Radio and Camera Sensor Data for Accurate Indoor Positioning

no code implementations1 Feb 2023 Savvas Papaioannou, Hongkai Wen, Andrew Markham, Niki Trigoni

In this paper, we propose a novel positioning system, RAVEL (Radio And Vision Enhanced Localization), which fuses anonymous visual detections captured by widely available camera infrastructure, with radio readings (e. g. WiFi radio data).

Fleet Rebalancing for Expanding Shared e-Mobility Systems: A Multi-agent Deep Reinforcement Learning Approach

1 code implementation11 Nov 2022 Man Luo, Bowen Du, Wenzhe Zhang, Tianyou Song, Kun Li, HongMing Zhu, Mark Birkin, Hongkai Wen

This is particularly challenging in the context of expanding systems, because i) the range of the EVs is limited while charging time is typically long, which constrain the viable rebalancing operations; and ii) the EV stations in the system are dynamically changing, i. e., the legitimate targets for rebalancing operations can vary over time.

Multi-agent Reinforcement Learning

BLOX: Macro Neural Architecture Search Benchmark and Algorithms

1 code implementation13 Oct 2022 Thomas Chun Pong Chau, Łukasz Dudziak, Hongkai Wen, Nicholas Donald Lane, Mohamed S Abdelfattah

To provide a systematic study of the performance of NAS algorithms on a macro search space, we release Blox - a benchmark that consists of 91k unique models trained on the CIFAR-100 dataset.

Neural Architecture Search

High Speed Rotation Estimation with Dynamic Vision Sensors

no code implementations6 Sep 2022 Guangrong Zhao, Yiran Shen, Ning Chen, Pengfei Hu, Lei Liu, Hongkai Wen

By designing a series of signal processing algorithms bespoke for dynamic vision sensing on mobile devices, EV-Tach is able to extract the rotational speed accurately from the event stream produced by dynamic vision sensing on rotary targets.

Vocal Bursts Intensity Prediction

GeoPointGAN: Synthetic Spatial Data with Local Label Differential Privacy

1 code implementation18 May 2022 Teddy Cunningham, Konstantin Klemmer, Hongkai Wen, Hakan Ferhatosmanoglu

We introduce GeoPointGAN, a novel GAN-based solution for generating synthetic spatial point datasets with high utility and strong individual level privacy guarantees.

Management Privacy Preserving +1

Deployment Optimization for Shared e-Mobility Systems with Multi-agent Deep Neural Search

no code implementations3 Nov 2021 Man Luo, Bowen Du, Konstantin Klemmer, HongMing Zhu, Hongkai Wen

Shared e-mobility services have been widely tested and piloted in cities across the globe, and already woven into the fabric of modern urban planning.

Temporal Kernel Consistency for Blind Video Super-Resolution

no code implementations18 Aug 2021 Lichuan Xiang, Royson Lee, Mohamed S. Abdelfattah, Nicholas D. Lane, Hongkai Wen

Deep learning-based blind super-resolution (SR) methods have recently achieved unprecedented performance in upscaling frames with unknown degradation.

Blind Super-Resolution Video Super-Resolution

Zero-Cost Operation Scoring in Differentiable Architecture Search

1 code implementation12 Jun 2021 Lichuan Xiang, Łukasz Dudziak, Mohamed S. Abdelfattah, Thomas Chau, Nicholas D. Lane, Hongkai Wen

From this perspective, we introduce a novel \textit{perturbation-based zero-cost operation scoring} (Zero-Cost-PT) approach, which utilizes zero-cost proxies that were recently studied in multi-trial NAS but degrade significantly on larger search spaces, typical for differentiable NAS.

Neural Architecture Search

Journey Towards Tiny Perceptual Super-Resolution

2 code implementations ECCV 2020 Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane

Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks.

Neural Architecture Search Super-Resolution

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

no code implementations1 Mar 2020 Liang Du, Jingang Tan, xiangyang xue, Lili Chen, Hongkai Wen, Jianfeng Feng, Jiamao Li, Xiaolin Zhang

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation.

3D Semantic Instance Segmentation feature selection +2

Snoopy: Sniffing Your Smartwatch Passwords via Deep Sequence Learning

1 code implementation10 Dec 2019 Chris Xiaoxuan Lu, Bowen Du, Hongkai Wen, Sen Wang, Andrew Markham, Ivan Martinovic, Yiran Shen, Niki Trigoni

Demand for smartwatches has taken off in recent years with new models which can run independently from smartphones and provide more useful features, becoming first-class mobile platforms.

Autonomous Learning for Face Recognition in the Wild via Ambient Wireless Cues

1 code implementation14 Aug 2019 Chris Xiaoxuan Lu, Xuan Kan, Bowen Du, Changhao Chen, Hongkai Wen, Andrew Markham, Niki Trigoni, John Stankovic

Inspired by the fact that most people carry smart wireless devices with them, e. g. smartphones, we propose to use this wireless identifier as a supervisory label.

Face Recognition

Demand Prediction for Electric Vehicle Sharing

no code implementations10 Mar 2019 Man Luo, Hongkai Wen, Yi Luo, Bowen Du, Konstantin Klemmer, Hong-Ming Zhu

Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe.

Decision Making

Dense 3D Object Reconstruction from a Single Depth View

2 code implementations1 Feb 2018 Bo Yang, Stefano Rosa, Andrew Markham, Niki Trigoni, Hongkai Wen

Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid with a high resolution of 256^3 by recovering the occluded/missing regions.

3D Object Reconstruction Object

DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks

5 code implementations25 Sep 2017 Sen Wang, Ronald Clark, Hongkai Wen, Niki Trigoni

This paper presents a novel end-to-end framework for monocular VO by using deep Recurrent Convolutional Neural Networks (RCNNs).

Monocular Visual Odometry Motion Estimation

3D Object Reconstruction from a Single Depth View with Adversarial Learning

2 code implementations26 Aug 2017 Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni

In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.

3D Object Reconstruction Object

VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization

no code implementations CVPR 2017 Ronald Clark, Sen Wang, Andrew Markham, Niki Trigoni, Hongkai Wen

Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images.

Autonomous Driving Indoor Localization

VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem

no code implementations29 Jan 2017 Ronald Clark, Sen Wang, Hongkai Wen, Andrew Markham, Niki Trigoni

In this paper we present an on-manifold sequence-to-sequence learning approach to motion estimation using visual and inertial sensors.

Motion Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.