127 citations · 409 across the 15 of their papers we have counts for
15 papers
Video Frame Interpolation via Structure-Motion based Iterative Fusion
Xi Li, Meng Cao, Yingying Tang +4
Video Frame Interpolation synthesizes non-existent images between adjacent frames, with the aim of providing a smooth and consistent visual experience. Two approaches for solving t…
Unsupervised segmentation via semantic-apparent feature fusion
Xi Li, Huimin Ma, Hongbing Ma +1
Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, wh…
Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class
Xi Li, Huimin Ma, Sheng Yi +1
Semantic segmentation tasks based on weakly supervised condition have been put forward to achieve a lightweight labeling process. For simple images that only include a few categori…
Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning
Xiang Wang, Sifei Liu, Huimin Ma +1
Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training. Recent methods have exploited classification networks to…
Semantic Head Enhanced Pedestrian Detection in a Crowd
Ruiqi Lu, Huimin Ma
Pedestrian detection in the crowd is a challenging task because of intra-class occlusion. More prior information is needed for the detector to be robust against it. Human head area…
WSOD with PSNet and Box Regression
Sheng Yi, Xi Li, Huimin Ma
Weakly supervised object detection(WSOD) task uses only image-level annotations to train object detection task. WSOD does not require time-consuming instance-level annotations, so…
Occluded Pedestrian Detection with Visible IoU and Box Sign Predictor
Ruiqi Lu, Huimin Ma
Training a robust classifier and an accurate box regressor are difficult for occluded pedestrian detection. Traditionally adopted Intersection over Union (IoU) measurement does not…
Pretrain Soft Q-Learning with Imperfect Demonstrations
Xiaoqin Zhang, Yunfei Li, Huimin Ma +1
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent…
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
Xiang Wang, Shaodi You, Xi Li +1
Weakly-supervised semantic segmentation under image tags supervision is a challenging task as it directly associates high-level semantic to low-level appearance. To bridge this gap…
Driving maneuvers prediction based on cognition-driven and data-driven method
Dong Zhou, Huimin Ma, Yuhan Dong
Advanced Driver Assistance Systems (ADAS) improve driving safety significantly. They alert drivers from unsafe traffic conditions when a dangerous maneuver appears. Traditional met…
Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations
Xiaoqin Zhang, Huimin Ma
Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is req…
Single Image Action Recognition using Semantic Body Part Actions
Zhichen Zhao, Huimin Ma, Shaodi You
In this paper, we propose a novel single image action recognition algorithm which is based on the idea of semantic body part actions. Unlike existing bottom up methods, we argue th…
Multi-View 3D Object Detection Network for Autonomous Driving
Xiaozhi Chen, Huimin Ma, Ji Wan +2
This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR poin…
Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection
Xiang Wang, Huimin Ma, Xiaozhi Chen +1
In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection. The proposed framework is aiming to address two limits of…
3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
Xiaozhi Chen, Kaustav Kundu, Yukun Zhu +3
The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method first aims at generating a set of high-quality 3D object proposals by expl…