91 citations · 233 across the 12 of their papers we have counts for
12 papers
Smart Explorer: Recognizing Objects in Dense Clutter via Interactive Exploration
Zhenyu Wu, Ziwei Wang, Zibu Wei +2
Recognizing objects in dense clutter accurately plays an important role to a wide variety of robotic manipulation tasks including grasping, packing, rearranging and many others. Ho…
E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles
Zhenyu Hu, Zhenyu Wu, Pengcheng Pi +6
Unmanned Aerial Vehicles (UAVs) based video text spotting has been extensively used in civil and military domains. UAV's limited battery capacity motivates us to develop an energy-…
A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truth
Priya Narayanan, Xin Hu, Zhenyu Wu +9
Imagery collected from outdoor visual environments is often degraded due to the presence of dense smoke or haze. A key challenge for research in scene understanding in these degrad…
E^2TAD: An Energy-Efficient Tracking-based Action Detector
Xin Hu, Zhenyu Wu, Hao-Yu Miao +8
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays. It has high practical impacts…
Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study
Zhenyu Wu, Zhaowen Wang, Ye Yuan +3
Generative adversarial networks (GANs) nowadays are capable of producing images of incredible realism. One concern raised is whether the state-of-the-art GAN's learned distribution…
PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning
Yuli Zheng, Zhenyu Wu, Ye Yuan +2
Credit risk modeling has permeated our everyday life. Most banks and financial companies use this technique to model their clients' trustworthiness. While machine learning is incre…
MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis
Zhenyu Wu, Duc Hoang, Shih-Yao Lin +5
Estimating the 3D hand pose from a monocular RGB image is important but challenging. A solution is training on large-scale RGB hand images with accurate 3D hand keypoint annotation…
Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach
Zhenyu Wu, Karthik Suresh, Priya Narayanan +3
Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful. Despite the great success of the generic object detection methods trained…
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
Zhenyu Wu, Haotao Wang, Zhaowen Wang +2
We investigate privacy-preserving, video-based action recognition in deep learning, a problem with growing importance in smart camera applications. A novel adversarial training fra…
All-In-One Underwater Image Enhancement using Domain-Adversarial Learning
Pritish Uplavikar, Zhenyu Wu, Zhangyang Wang
Raw underwater images are degraded due to wavelength dependent light attenuation and scattering, limiting their applicability in vision systems. Another factor that makes enhancing…
Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
Zhenyu Wu, Zhangyang Wang, Zhaowen Wang +1
This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framew…
Deep -Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
Junru Wu, Yue Wang, Zhenyu Wu +3
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and…