Search Results for author:
Found 65 papers, 21 papers with code
Photon-Efficient 3D Imaging with A Non-Local Neural Network
Photon-efficient imaging has enabled a number of applications relying on single-photon sensors that can capture a 3D image with as few as one photon per pixel.
Entity-level Cross-modal Learning Improves Multi-modal Machine Translation
Inspired by the findings of (CITATION) that entities are most informative in the image, we propose an explicit entity-level cross-modal learning approach that aims to augment the entity representation.
Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation
Complex question answering over knowledge base remains as a challenging task because it involves reasoning over multiple pieces of information, including intermediate entities/relations and other constraints.
Privileged Prior Information Distillation for Image Matting
Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are semantically ambiguous, chromaless, or high transmittance.
Characterizing the Efficiency of Graph Neural Network Frameworks with a Magnifying Glass
In particular, unlike the traditional GNNs that are trained based on the entire graph in a full-batch manner, recent GNNs have been developed with different graph sampling techniques for mini-batch training of GNNs on large graphs.
P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving
Motion prediction is crucial in enabling safe motion planning for autonomous vehicles in interactive scenarios.
Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection
In this paper, we propose a risk-aware intelligent intersection system for autonomous vehicles (AVs) as well as human-driven vehicles (HVs).
VectorFlow: Combining Images and Vectors for Traffic Occupancy and Flow Prediction
Recently, the occupancy flow fields representation was proposed to represent joint future states of road agents through a combination of occupancy grid and flow, which supports efficient and consistent joint predictions.
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
Finally, we integrate configurable operators and DSMs into a unified search space and search with a Reinforcement Learning-based search algorithm to fully explore the optimal combination of the operators.
Ranked #12 on
Neural Architecture Search
on ImageNet
MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning
In this study, we propose Mixed and Masked Image Modeling (MixMIM), a simple but efficient MIM method that is applicable to various hierarchical Vision Transformers.
Ranked #1 on
Object Detection
on COCO 2017
(mAP metric)
Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis
A two-stage network is developed for novel view synthesis.
Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection
Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive.
M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction
Predicting future motions of road participants is an important task for driving autonomously in urban scenes.
HDR-NeRF: High Dynamic Range Neural Radiance Fields
The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper.
Trajectory Prediction with Linguistic Representations
Language allows humans to build mental models that interpret what is happening around them resulting in more accurate long-term predictions.
TIP: Task-Informed Motion Prediction for Intelligent Vehicles
When predicting trajectories of road agents, motion predictors usually approximate the future distribution by a limited number of samples.
A Generic Knowledge Based Medical Diagnosis Expert System
The proposed disease diagnosis system also uses a graphical user interface (GUI) to facilitate users to interact with the expert system.
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks.
Ranked #209 on
Image Classification
on ImageNet
HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Sampling
Modeling multi-modal high-level intent is important for ensuring diversity in trajectory prediction.
Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures
The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts.
Risk Conditioned Neural Motion Planning
In this paper, we propose an extension of soft actor critic model to estimate the execution risk of a plan through a risk critic and produce risk-bounded policies efficiently by adding an extra risk term in the loss function of the policy network.
Sea Ice Forecasting using Attention-based Ensemble LSTM
Accurately forecasting Arctic sea ice from subseasonal to seasonal scales has been a major scientific effort with fundamental challenges at play.
Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning.
PP-YOLOv2: A Practical Object Detector
To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged.
Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributed
In this paper, we propose Graph Neural Network models for both CS and ACS problems, i. e., Query Driven-GNN and Attributed Query Driven-GNN.
LSTM Based Sentiment Analysis for Cryptocurrency Prediction
Recent studies in big data analytics and natural language processing develop automatic techniques in analyzing sentiment in the social media information.
Single-photon imaging over 200 km
Long-range active imaging has widespread applications in remote sensing and target recognition.
LLA: Loss-aware Label Assignment for Dense Pedestrian Detection
A joint loss is then defined as the weighted summation of cls and reg losses as the assigning indicator.
A hybrid deep-learning approach for complex biochemical named entity recognition
In this approach, the MHATT mechanism aims to improve the recognition accuracy of abbreviations to efficiently deal with the problem of inconsistency in full-text labels.
Graph Neural Networks: Taxonomy, Advances and Trends
Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks.
TabTransformer: Tabular Data Modeling Using Contextual Embeddings
We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning.
Using Machine Learning to Automate Mammogram Images Analysis
Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate.
Budget Constrained Interactive Search for Multiple Targets
To address these two limitations, in this paper, we study a new problem of budget constrained interactive graph search for multiple targets called kBM-IGS-problem.
Image Classification
Product Categorization
Databases
Scenario-decomposition Solution Framework for Nonseparable Stochastic Control Problems
When stochastic control problems do not possess separability and/or monotonicity, the dynamic programming pioneered by Bellman in 1950s fails to work as a time-decomposition solution method.
Optimization and Control Systems and Control Systems and Control Portfolio Management
MitoEM Dataset: Large-scale 3D Mitochondria Instance Segmentation from EM Images
On MitoEM, we find existing instance segmentation methods often fail to correctly segment mitochondria with complex shapes or close contacts with other instances.
Ranked #2 on
3D Instance Segmentation
on MitoEM
(AP75-R-Test metric)
AIM 2020: Scene Relighting and Illumination Estimation Challenge
The first track considered one-to-one relighting; the objective was to relight an input photo of a scene with a different color temperature and illuminant orientation (i. e., light source position).
Hyperbolic Capsule Networks for Multi-Label Classification
Second, Hyperbolic Dynamic Routing (HDR) is introduced to aggregate hyperbolic capsules in a label-aware manner, so that the label-level discriminative information can be preserved along the depth of neural networks.
Fast Risk Assessment for Autonomous Vehicles Using Learned Models of Agent Futures
The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models for predictions of both agent positions and controls.
Delving into the Imbalance of Positive Proposals in Two-stage Object Detection
The first imbalance lies in the large number of low-quality RPN proposals, which makes the R-CNN module (i. e., post-classification layers) become highly biased towards the negative proposals in the early training stage.
NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing
To acquire the visible parts, a novel Paired-Box Model (PBM) is proposed to simultaneously predict the full and visible boxes of a pedestrian.
CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy
Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems.
PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression
PS-RCNN first detects slightly/none occluded objects by an R-CNN module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out.
Ranked #2 on
Object Detection
on WiderPerson
DSSLP: A Distributed Framework for Semi-supervised Link Prediction
Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure.
Building Footprint Generation by IntegratingConvolution Neural Network with Feature PairwiseConditional Random Field (FPCRF)
Due to the complexity of buildings, the accurate and reliable generation of the building footprint from remote sensing imagery is still a challenging task.
DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling
Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant systems.
Label-Specific Document Representation for Multi-Label Text Classification
Multi-label text classification (MLTC) aims to tag most relevant labels for the given document.
Ranked #1 on
Multi-Label Text Classification
on AAPD
Revised Progressive-Hedging-Algorithm Based Two-layer Solution Scheme for Bayesian Reinforcement Learning
Stochastic control with both inherent random system noise and lack of knowledge on system parameters constitutes the core and fundamental topic in reinforcement learning (RL), especially under non-episodic situations where online learning is much more demanding.
BERT-based Financial Sentiment Index and LSTM-based Stock Return Predictability
On the other hand, by combining with the other two commonly-used methods when it comes to building the sentiment index in the financial literature, i. e., the option-implied and the market-implied approaches, we propose a more general and comprehensive framework for the financial sentiment analysis, and further provide convincing outcomes for the predictability of individual stock return by combining LSTM (with a feature of a nonlinear mapping).
Fast Algorithm for K-Truss Discovery on Public-Private Graphs
In public-private graphs, users share one public graph and have their own private graphs.
Hyperbolic Interaction Model For Hierarchical Multi-Label Classification
The main reason is that the tree-likeness of the hyperbolic space matches the complexity of symbolic data with hierarchical structures.
Label-aware Document Representation via Hybrid Attention for Extreme Multi-Label Text Classification
Extreme multi-label text classification (XMTC) aims at tagging a document with most relevant labels from an extremely large-scale label set.
Ranked #1 on
Multi-Label Text Classification
on Amazon-12K
Semi-Unsupervised Lifelong Learning for Sentiment Classification: Less Manual Data Annotation and More Self-Studying
Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning.
Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Images
In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier.
CRAD: Clustering with Robust Autocuts and Depth
We develop a new density-based clustering algorithm named CRAD which is based on a new neighbor searching function with a robust data depth as the dissimilarity measure.
Online Risk-Bounded Motion Planning for Autonomous Vehicles in Dynamic Environments
In this work, we model the motion planning problem as a partially observable Markov decision process (POMDP) and propose an online system that combines an intent recognition algorithm and a POMDP solver to generate risk-bounded plans for the ego vehicle navigating with a number of dynamic agent vehicles.
Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections
In this paper, we propose a variational neural network approach that predicts future driver trajectory distributions for the vehicle based on multiple sensors.
Boost Blockchain Broadcast Propagation with Tree Routing
The research shows that the tree based routing can accelerate broadcast convergence time and reduce redundant traffic.
Distributed, Parallel, and Cluster Computing
Improve Blockchain Performance using Graph Data Structure and Parallel Mining
Blockchain technology is ushering in another break-out year, the challenge of blockchain still remains to be solved.
Cryptography and Security Distributed, Parallel, and Cluster Computing
Adversarial Attack on Graph Structured Data
Deep learning on graph structures has shown exciting results in various applications.
Deep Cross-media Knowledge Transfer
For achieving the goal, this paper proposes deep cross-media knowledge transfer (DCKT) approach, which transfers knowledge from a large-scale cross-media dataset to promote the model training on another small-scale cross-media dataset.
Multimedia
MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval
Transfer learning is for relieving the problem of insufficient training data, but it mainly focuses on knowledge transfer only from large-scale datasets as single-modal source domain to single-modal target domain.
Cross-modal Common Representation Learning by Hybrid Transfer Network
Knowledge in source domain cannot be directly transferred to both two different modalities in target domain, and the inherent cross-modal correlation contained in target domain provides key hints for cross-modal retrieval which should be preserved during transfer process.
Cross-media Similarity Metric Learning with Unified Deep Networks
Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework.
Cross-modal Deep Metric Learning with Multi-task Regularization
The quadruplet ranking loss can model the semantically similar and dissimilar constraints to preserve cross-modal relative similarity ranking information.
Information-theoretic interpretation of tuning curves for multiple motion directions
We have developed an efficient information-maximization method for computing the optimal shapes of tuning curves of sensory neurons by optimizing the parameters of the underlying feedforward network model.
