Search Results for author:
Found 18 papers, 2 papers with code
Context-Aware Block Net for Small Object Detection
State-of-the-art object detectors usually progressively downsample the input image until it is represented by small feature maps, which loses the spatial information and compromises the representation of small objects.
Ranked #1 on
Traffic Sign Detection
on TT100K
Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition
Besides, these methods directly calculate the pair-wise global self-attention equally for all the joints in both the spatial and temporal dimensions, undervaluing the effect of discriminative local joints and the short-range temporal dynamics.
D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights
We present a trajectory prediction approach with respect to traffic lights, D2-TPred, which uses a spatial dynamic interaction graph (SDG) and a behavior dependency graph (BDG) to handle the problem of discontinuous dependency in the spatial-temporal space.
Multi-Agent Broad Reinforcement Learning for Intelligent Traffic Light Control
Existing approaches of MAS are largely based on Multi-Agent Deep Reinforcement Learning (MADRL).
Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition
Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task.
SSAGCN: Social Soft Attention Graph Convolution Network for Pedestrian Trajectory Prediction
In detail, when modeling social interaction, we propose a new \emph{social soft attention function}, which fully considers various interaction factors among pedestrians.
Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
Inspired by the habit of observing things by the human, we propose a new method by comparing the initial proposals and the extension ones to optimize those initial proposals.
User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning
This framework leverages user interactions to retouch and rank images for aesthetic assessment based on deep reinforcement learning (DRL), and generates personalized aesthetic distribution that is more in line with the aesthetic preferences of different users.
Emotional Contagion-Aware Deep Reinforcement Learning for Antagonistic Crowd Simulation
In this paper, we propose an Emotional contagion-aware Deep reinforcement learning model for Antagonistic Crowd Simulation (ACSED).
Agent-Based Campus Novel Coronavirus Infection and Control Simulation
Corona Virus Disease 2019 (COVID-19), due to its extremely high infectivity, has been spreading rapidly around the world and bringing huge influence to socioeconomic development as well as people's daily life.
Social and Information Networks Physics and Society Populations and Evolution
Probability Trajectory: One New Movement Description for Trajectory Prediction
Based on this unique description, we develop one novel trajectory prediction method, called social probability.
Personality-Aware Probabilistic Map for Trajectory Prediction of Pedestrians
We update this map dynamically based on the agents in the environment and prior trajectory of a pedestrian.
Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization
On ILSVRC 2016, the proposed method yields the Top-1 localization error of 48. 65\%, which outperforms previous results by 2. 75\%.
Abnormal Event Detection and Location for Dense Crowds using Repulsive Forces and Sparse Reconstruction
This paper proposes a method based on repulsive forces and sparse reconstruction for the detection and location of abnormal events in crowded scenes.
MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps.
USAR: an Interactive User-specific Aesthetic Ranking Framework for Images
When assessing whether an image is of high or low quality, it is indispensable to take personal preference into account.
Bi-directional Graph Structure Information Model for Multi-Person Pose Estimation
The first branch predicts the confidence maps of joints and uses a geometrical transform kernel to propagate information between neighboring joints at the confidence level.
Depth Information Guided Crowd Counting for Complex Crowd Scenes
DigCrowd first uses the depth information of an image to segment the scene into a far-view region and a near-view region.
