Search Results for author:
Found 20 papers, 5 papers with code
State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend
In this paper, we propose a state-space decomposition stochastic video prediction model that decomposes the overall video frame generation into deterministic appearance prediction and stochastic motion prediction.
Self-Attention Empowered Graph Convolutional Network for Structure Learning and Node Embedding
The proposed GCN-SA contains two enhancements corresponding to edges and node features.
Hierarchical Multi-Relational Graph Representation Learning for Large-Scale Prediction of Drug-Drug Interactions
Within the MVDSC, we utilize multiple DP features to construct graphs, where nodes represent DPs and edges denote different implicit correlations.
Relation-aware graph structure embedding with co-contrastive learning for drug-drug interaction prediction
To alleviate this issue, we propose a novel DDI prediction method based on relation-aware graph structure embedding with co-contrastive learning, RaGSECo.
Landmark Guided Active Exploration with State-specific Balance Coefficient
Goal-conditioned hierarchical reinforcement learning (GCHRL) decomposes long-horizon tasks into sub-tasks through a hierarchical framework and it has demonstrated promising results across a variety of domains.
Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes
For visual representation, a representation driven by a combination of the imageaugmented forward dynamics and the reward is acquired.
Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning
Knowledge Graph Question Answering (KGQA) aims to answer user-questions from a knowledge graph (KG) by identifying the reasoning relations between topic entity and answer.
GCN-SL: Graph Convolutional Network with Structure Learning for Disassortative Graphs
To solve the above-mentioned issue, we propose a graph convolutional network with structure learning (GCN-SL), and furthermore, the proposed approach can be applied to node classification.
Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances.
Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D
To makes the optimization easier, we further incorporate the epipolar geometry into the ICP based learning process for pose learning.
Trainable Class Prototypes for Few-Shot Learning
Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm.
GCN-SL: Graph Convolutional Networks with Structure Learning for Graphs under Heterophily
The proposed GCN-SL can aggregate feature representations from nearby nodes via re-connected adjacency matrix and is applied to graphs with various levels of homophily.
R-GSN: The Relation-based Graph Similar Network for Heterogeneous Graph
Heterogeneous graph is a kind of data structure widely existing in real life.
Few-Shot Image Classification via Contrastive Self-Supervised Learning
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required.
Ranked #10 on
Unsupervised Few-Shot Image Classification
on Mini-Imagenet 5-way (1-shot)
(using extra training data)
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Results of 33 object detection algorithms are presented.
Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus
Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch to acquire.
Flow Guided Short-term Trackers with Cascade Detection for Long-term Tracking
Object tracking has been studied for decades, but most of the existing works are focused on the short-term tracking.
Multiple Object Tracking with Motion and Appearance Cues
Due to better video quality and higher frame rate, the performance of multiple object tracking issues has been greatly improved in recent years.
3D Bounding Box Estimation for Autonomous Vehicles by Cascaded Geometric Constraints and Depurated 2D Detections Using 3D Results
In this paper, we propose a novel two stage 3D object detection method aimed at get the optimal solution of object location in 3D space based on regressing two additional 3D object properties by a deep convolutional neural network and combined with cascaded geometric constraints between the 2D and 3D boxes.
A Single-shot Object Detector with Feature Aggragation and Enhancement
To achieve it we introduce a pair of novel feature aggregation modules and two feature enhancement blocks, and integrate them into the original structure of SSD.
