Search Results for author:
Found 106 papers, 32 papers with code
Learning to Reverse DNNs from AI Programs Automatically
With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern.
HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers
We analyze the performance of a set of baselines and show a correlation with a real-world evaluation.
Transformer Tracking with Cyclic Shifting Window Attention
Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism.
Detecting Topology Attacks against Graph Neural Networks
In this work, we study the victim node detection problem under topology attacks against GNNs.
CorrGAN: Input Transformation Technique Against Natural Corruptions
These DNNs are vulnerable to adversarial perturbations and corruptions.
Pan-cancer computational histopathology reveals tumor mutational burden status through weakly-supervised deep learning
In comparison with the state-of-the-art TMB prediction model from previous publications, our multiscale model achieved better performance over previously reported models.
Model Predictive Control for Fluid Human-to-Robot Handovers
However, how to responsively generate smooth motions to take an object from a human is still an open question.
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
To further understand such efficiency-oriented threats, we propose a new attack approach, NICGSlowDown, to evaluate the efficiency robustness of NICG models.
NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation
We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by simultaneously estimating the surface position and normal of the fluid front.
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers.
EREBA: Black-box Energy Testing of Adaptive Neural Networks
The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2, 000% compared to the original inputs.
NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing
We further develop a hybrid neural-rasterization rendering framework to support consumer-level VR headsets so that the aforementioned volumetric video viewing and editing, for the first time, can be conducted immersively in virtual 3D space.
Video-driven Neural Physically-based Facial Asset for Production
We then model the facial expression, geometry and physically-based textures using separate VAEs with a global MLP-based expression mapping across the latent spaces, to preserve characteristics across respective attributes while maintaining explicit controls over geometry and texture.
Artemis: Articulated Neural Pets with Appearance and Motion synthesis
Our ARTEMIS enables interactive motion control, real-time animation, and photo-realistic rendering of furry animals.
Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controller
Reinforcement learning has become a powerful tool to formulate controllers for legged robots.
JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning
To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration.
Efficient Exploration
Hierarchical Reinforcement Learning
+3
HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputs
The raw HumanNeRF can already produce reasonable rendering on sparse video inputs of unseen subjects and camera settings.
Hierarchical Neural Data Synthesis for Semantic Parsing
Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
Labels are costly and sometimes unreliable.
Ranked #3 on
Image Classification
on mini WebVision 1.0
Learning Perceptual Concepts by Bootstrapping from Human Queries
To address this challenge, we propose a new approach whereby the robot learns a low-dimensional variant of the concept and uses it to generate a larger data set for learning the concept in the high-dimensional space.
Learning Diverse Policies in MOBA Games via Macro-Goals
Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.
NODEAttack: Adversarial Attack on the Energy Consumption of Neural ODEs
Unlike the memory cost, the energy consumption of the Neural ODEs during inference can be adaptive because of the adaptive nature of the ODE solvers.
TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems
To further the understanding of such efficiency-oriented threats and raise the community’s concern on the efficiency robustness of NMT systems, we propose a new attack approach, TranSlowDown, to test the efficiency robustness of NMT systems.
Estimating Predictive Uncertainty Under Program Data Distribution Shift
Experiments show that program distribution shift does degrade the DL model performance to varying degrees and that existing uncertainty methods all present certain limitations in quantifying uncertainty on program dataset.
Boosting Offline Reinforcement Learning with Residual Generative Modeling
While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
GLIB: Towards Automated Test Oracle for Graphically-Rich Applications
We perform an evaluation of \texttt{GLIB} on 20 real-world game apps (with bug reports available) and the result shows that \texttt{GLIB} can achieve 100\% precision and 99. 5\% recall in detecting non-crashing bugs such as game GUI glitches.
SynthASR: Unlocking Synthetic Data for Speech Recognition
Our observations show that SynthASR holds great promise in training the state-of-the-art large-scale E2E ASR models for new applications while reducing the costs and dependency on production data.
Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
A natural language database interface (NLDB) can democratize data-driven insights for non-technical users.
A Globally Normalized Neural Model for Semantic Parsing
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing.
MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.
SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos
In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input.
Wide-Beam Array Antenna Power Gain Maximization via ADMM Framework
This paper proposes two algorithms to maximize the minimum array power gain in a wide-beam mainlobe by solving the power gain pattern synthesis (PGPS) problem with and without sidelobe constraints.
DexYCB: A Benchmark for Capturing Hand Grasping of Objects
We introduce DexYCB, a new dataset for capturing hand grasping of objects.
Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet
MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM).
F3SNet: A Four-Step Strategy for QIM Steganalysis of Compressed Speech Based on Hierarchical Attention Network
Traditional machine learning-based steganalysis methods on compressed speech have achieved great success in the field of communication security.
Cryptography and Security
AttackDist: Characterizing Zero-day Adversarial Samples by Counter Attack
We first theoretically clarify under which condition AttackDist can provide a certified detecting performance, then show that a potential application of AttackDist is distinguishing zero-day adversarial examples without knowing the mechanisms of new attacks.
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation
Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.
Continuous Copy-Paste for One-Stage Multi-Object Tracking and Segmentation
Current one-step multi-object tracking and segmentation (MOTS) methods lag behind recent two-step methods.
Optimizing Deeper Transformers on Small Datasets
This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.
Which Heroes to Pick? Learning to Draft in MOBA Games with Neural Networks and Tree Search
Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.
RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Features for Indoor Localization
Experimental results show that the proposed RaP-Net trained with OpenLORIS-Location dataset achieves excellent performance in the feature matching task and significantly outperforms state-of-the-arts feature algorithms in indoor localization.
Towards Playing Full MOBA Games with Deep Reinforcement Learning
However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.
Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings
Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.
Reactive Human-to-Robot Handovers of Arbitrary Objects
We demonstrate the generalizability, usability, and robustness of our approach on a novel benchmark set of 26 diverse household objects, a user study with naive users (N=6) handing over a subset of 15 objects, and a systematic evaluation examining different ways of handing objects.
Emergence of Chern insulating states in non-Magic angle twisted bilayer graphene
For {\theta}=1. 25{\deg}, we observe an emergence of topological insulating states at hole side with a sequence of Chern number |C|=4-|v|, where v is the number of electrons (holes) in moir\'e unite cell.
Mesoscale and Nanoscale Physics Materials Science
Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds
We demonstrate that our learned policy can be integrated into a tabletop 6D grasping system and a human-robot handover system to improve the grasping performance of unseen objects.
SpineParseNet: Spine Parsing for Volumetric MR Image by a Two-Stage Segmentation Framework with Semantic Image Representation
The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement.
DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features
For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically designed in most cases, and can be vulnerable in complex environments.
Loop Closure Detection
Simultaneous Localization and Mapping
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5. 4% higher MOTSA and 18 times faster over MOTSFusion) with the near real-time speed (22 FPS).
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+1
PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.
Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
In fact, due to the limitation of the receptive field, the 3 x 3 kernel has difficulty in covering the corresponding features at high/original resolution.
Human Grasp Classification for Reactive Human-to-Robot Handovers
In this paper, we propose an approach for human-to-robot handovers in which the robot meets the human halfway, by classifying the human's grasp of the object and quickly planning a trajectory accordingly to take the object from the human's hand according to their intent.
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes.
Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs).
Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents
Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient.
Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games.
Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM
We also design benchmarking metrics for lifelong SLAM, with which the robustness and accuracy of pose estimation are evaluated separately.
Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval
This paper applies BERT to ad hoc document retrieval on news articles, which requires addressing two challenges: relevance judgments in existing test collections are typically provided only at the document level, and documents often exceed the length that BERT was designed to handle.
Applying BERT to Document Retrieval with Birch
We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.
Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling
A core problem of information retrieval (IR) is relevance matching, which is to rank documents by relevance to a user{'}s query.
Incorporating Contextual and Syntactic Structures Improves Semantic Similarity Modeling
Semantic similarity modeling is central to many NLP problems such as natural language inference and question answering.
Our Neural Machine Translation Systems for WAT 2019
We use Transformer model through our work in this paper to explore and experience the powerful of the Transformer architecture relying on self-attention mechanism.
Multi-Stage Document Ranking with BERT
The advent of deep neural networks pre-trained via language modeling tasks has spurred a number of successful applications in natural language processing.
DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
Teleoperation offers the possibility of imparting robotic systems with sophisticated reasoning skills, intuition, and creativity to perform tasks.
Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability
In this work, after theoretically quantifying the estimation error bound and the manipulating risk bound of the Laplace mechanism, we propose two mechanisms improving the usefulness and soundness simultaneously: the weighted sampling mechanism and the additive mechanism.
End-to-End Neural Context Reconstruction in Chinese Dialogue
We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context.
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features
Consumers dissatisfied with the normal dispute resolution process provided by an e-commerce company{'}s customer service agents have the option of escalating their complaints by filing grievances with a government authority.
Document Expansion by Query Prediction
One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content. From the perspective of a question answering system, this might comprise questions the document can potentially answer.
Ranked #1 on
Passage Re-Ranking
on MS MARCO
Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia, yielding a large improvement over the previous state of the art on a standard benchmark dataset.
Ranked #2 on
Open-Domain Question Answering
on SQuAD1.1 dev
Simple Applications of BERT for Ad Hoc Document Retrieval
Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval.
Ranked #2 on
Ad-Hoc Information Retrieval
on TREC Robust04
(MAP metric)
End-to-End Open-Domain Question Answering with BERTserini
We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit.
Ranked #3 on
Open-Domain Question Answering
on SQuAD1.1 dev
A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings
Learning word embeddings has received a significant amount of attention recently.
Hierarchical Macro Strategy Model for MOBA Game AI
In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games.
Sequenced-Replacement Sampling for Deep Learning
We propose sequenced-replacement sampling (SRS) for training deep neural networks.
Visual Semantic Navigation using Scene Priors
Do we use the semantic/functional priors we have built over years to efficiently search and navigate?
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Recent research proposes syntax-based approaches to address the problem of generating programs from natural language specifications.
Towards End-to-End License Plate Detection and Recognition: A Large Dataset and Baseline
Most current license plate (LP) detection and recognition approaches are evaluated on a small and usually unrepresentative dataset since there are no publicly available large diverse datasets.
MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family.
Testing Untestable Neural Machine Translation: An Industrial Case
To fill the gap of lacking test oracle for in-vivo testing of an NMT system, in this paper, we propose a new approach for automatically identifying translation failures, without requiring reference translations for a translation task; our approach can directly serve as a test oracle for in-vivo testing.
Incorporating Latent Meanings of Morphological Compositions to Enhance Word Embeddings
Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models.
Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search
To our best knowledge, this paper presents the first substantial work tackling search over social media posts using neural ranking models.
3D Human Pose Estimation in the Wild by Adversarial Learning
Instead of defining hard-coded rules to constrain the pose estimation results, we design a novel multi-source discriminator to distinguish the predicted 3D poses from the ground-truth, which helps to enforce the pose estimator to generate anthropometrically valid poses even with images in the wild.
Ranked #17 on
3D Human Pose Estimation
on MPI-INF-3DHP
Robust 3D Human Motion Reconstruction Via Dynamic Template Construction
In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc.
A Roadmap for HEP Software and Computing R&D for the 2020s
Particle physics has an ambitious and broad experimental programme for the coming decades.
Computational Physics High Energy Physics - Experiment
Ray Space Features for Plenoptic Structure-From-Motion
In this paper, we explore using light fields captured by plenoptic cameras or camera arrays as inputs.
Recurrent Attention Network on Memory for Aspect Sentiment Analysis
We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review.
Identity-Aware Textual-Visual Matching with Latent Co-attention
The stage-2 CNN-LSTM network refines the matching results with a latent co-attention mechanism.
Learning Feature Pyramids for Human Pose Estimation
We investigate our method on two standard benchmarks for human pose estimation.
Ranked #5 on
Pose Estimation
on Leeds Sports Poses
Multi-Context Attention for Human Pose Estimation
We further combine the holistic attention model, which focuses on the global consistency of the full human body, and the body part attention model, which focuses on the detailed description for different body parts.
Ranked #7 on
Pose Estimation
on Leeds Sports Poses
Progressively Diffused Networks for Semantic Image Segmentation
This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application.
Personalized Classifier Ensemble Pruning Framework for Mobile Crowdsourcing
One of the fundamental issue in ensemble learning is the trade-off between classification accuracy and computational costs, which is the goal of ensemble pruning.
Improving Patent Translation using Bilingual Term Extraction and Re-tokenization for Chinese--Japanese
To improve the translation accuracy, we adjust and balance the granularity of segmentation results around terms for Chinese{--}Japanese patent corpus for training translation model.
End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation
In this paper, we propose a novel end-to-end framework for human pose estimation that combines DCNNs with the expressive deformable mixture of parts.
Multi-Task Recurrent Neural Network for Immediacy Prediction
In this paper, we propose to predict immediacy for interacting persons from still images.
Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis
We first conduct a comprehensive analysis to characterize DDAR, infer object depth from its AR, and model recoverable depth range, sensitivity, and error.
Ambient Occlusion via Compressive Visibility Estimation
This enables a sparsity-prior based solution for iteratively recovering the surface normal, the surface albedo, and the visibility function from a small number of images.
Data-Driven Scene Understanding with Adaptively Retrieved Exemplars
In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).
Clothing Co-Parsing by Joint Image Segmentation and Labeling
This paper aims at developing an integrated system of clothing co-parsing, in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations.
Learning Contour-Fragment-based Shape Model with And-Or Tree Representation
This paper proposes a simple yet effective method to learn the hierarchical object shape model consisting of local contour fragments, which represents a category of shapes in the form of an And-Or tree.
Discriminatively Trained And-Or Graph Models for Object Shape Detection
In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images.
