Search Results for author:
Found 28 papers, 5 papers with code
A Copy-Augmented Generative Model for Open-Domain Question Answering
Open-domain question answering is a challenging task with a wide variety of practical applications.
A Review on Machine Theory of Mind
Beliefs, desires, and intentions are the early abilities of infants and the foundation of human cognitive ability, as well as for machine with ToM.
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding
While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far.
Micro-Vibration Modes Reconstruction Based on Micro-Doppler Coincidence Imaging
To reconstruct the spatial distribution of micro vibrations, this paper proposes a new method based on a coincidence imaging system.
Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game
Game theory has been used to answer some of the basic questions about adversarial deep learning such as the existence of a classifier with optimal robustness and the existence of optimal adversarial samples for a given class of classifiers.
Improving Policy Optimization with Generalist-Specialist Learning
Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations.
Unified Line and Paragraph Detection by Graph Convolutional Networks
We formulate the task of detecting lines and paragraphs in a document into a unified two-level clustering problem.
Symmetry-Aware Neural Architecture for Embodied Visual Exploration
We then propose a network design for the actor and the critic to inherently attain these symmetries.
Symmetry-aware Neural Architecture for Embodied Visual Navigation
We then propose a network design for the actor and the critic to inherently attain these symmetries.
A Comprehensive Study on Learning-Based PE Malware Family Classification Methods
PE malware family classification has gained great attention and a large number of approaches have been proposed.
Task Guided Compositional Representation Learning for ZDA
To this end, we propose a method for task-guided ZDA (TG-ZDA) which employs multi-branch deep neural networks to learn feature representations exploiting their domain invariance and shareability properties.
GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback
To leverage the strength of text generation for information retrieval, in this article, we propose a novel approach which effectively integrates text generation models into PRF-based query expansion.
Person Re-Identification Using Heterogeneous Local Graph Attention Networks
Specifically, we first construct the completed local graph using local features, and we resort to the attention mechanism to aggregate the local features in the learning process of inter-local relation and intra-local relation so as to emphasize the importance of different local features.
Rotational dynamics of bottom-heavy rods in turbulence from experiments and numerical simulations
We successfully perform the three-dimensional tracking in a turbulent fluid flow of small asymmetrical particles that are neutrally-buoyant and bottom-heavy, i. e., they have a non-homogeneous mass distribution along their symmetry axis.
Fluid Dynamics
SE-ECGNet: A Multi-scale Deep Residual Network with Squeeze-and-Excitation Module for ECG Signal Classification
The classification of electrocardiogram (ECG) signals, which takes much time and suffers from a high rate of misjudgment, is recognized as an extremely challenging task for cardiologists.
Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
To further verify the scalability of our method, we propose a new large-scale multi-human dataset with 12 to 28 camera views.
Ranked #8 on
3D Multi-Person Pose Estimation
on Campus
Regret Bounds for Discounted MDPs
We give motivations and derive lower and upper bounds for such measures.
There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
In this work, we conduct an empirical study to evaluate the relationship between coverage, robustness and attack/defense metrics for DNN.
Pre-training as Batch Meta Reinforcement Learning with tiMe
Combining ideas from Batch RL and Meta RL, we propose tiMe, which learns distillation of multiple value functions and MDP embeddings from only existing data.
Multi-task Batch Reinforcement Learning with Metric Learning
To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards.
The Inductive Bias of Restricted f-GANs
Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood.
Falsification of Cyber-Physical Systems Using Deep Reinforcement Learning
With the rapid development of software and distributed computing, Cyber-Physical Systems (CPS) are widely adopted in many application areas, e. g., smart grid, autonomous automobile.
A vision based system for underwater docking
In the experiments, we first evaluate performance of the proposed detection module on UDID and its deformed variations.
Approximation and Convergence Properties of Generative Adversarial Learning
In this paper, we address these questions in a broad and unified setting by defining a notion of adversarial divergences that includes a number of recently proposed objective functions.
A Parallel algorithm for $\mathcal{X}$-Armed bandits
To deal with these large-scale data sets, we study a distributed setting of $\mathcal{X}$-armed bandits, where $m$ players collaborate to find the maximum of the unknown function.
Regret vs. Communication: Distributed Stochastic Multi-Armed Bandits and Beyond
When the time horizon is unknown, we measure the frequency of communication through a new notion called the density of the communication set, and give an exact characterization of the interplay between regret and communication.
Cross-View Action Recognition via a Continuous Virtual Path
In this paper, we propose a novel method for cross-view action recognition via a continuous virtual path which connects the source view and the target view.
