Search Results for author:
Found 80 papers, 19 papers with code
The AISP-SJTU Simultaneous Translation System for IWSLT 2022
This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task.
More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge
Despite achieving remarkable performance, previous knowledge-enhanced works usually only use a single-source homogeneous knowledge base of limited knowledge coverage.
Adversarial Attack against Cross-lingual Knowledge Graph Alignment
Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks.
PENet: A Joint Panoptic Edge Detection Network
In recent years, compact and efficient scene understanding representations have gained popularity in increasing situational awareness and autonomy of robotic systems.
Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment
To enable MedRPG to locate nuanced medical findings with better region-phrase correspondences, we further propose Tri-attention Context contrastive alignment (TaCo).
Faster Learning of Temporal Action Proposal via Sparse Multilevel Boundary Generator
Temporal action localization in videos presents significant challenges in the field of computer vision.
Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking
The increasing use of Machine Learning (ML) software can lead to unfair and unethical decisions, thus fairness bugs in software are becoming a growing concern.
Artificial Intelligence System for Detection and Screening of Cardiac Abnormalities using Electrocardiogram Images
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
Cost-minimization predictive energy management of a postal-delivery fuel cell electric vehicle with intelligent battery State-of-Charge Planner
Fuel cell electric vehicles have earned substantial attentions in recent decades due to their high-efficiency and zero-emission features, while the high operating costs remain the major barrier towards their large-scale commercialization.
Visual Fault Detection of Multi-scale Key Components in Freight Trains
Fault detection for key components in the braking system of freight trains is critical for ensuring railway transportation safety.
Multi-Job Intelligent Scheduling with Cross-Device Federated Learning
The system model enables a parallel training process of multiple jobs, with a cost model based on the data fairness and the training time of diverse devices during the parallel training process.
ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks.
Pixel-Aligned Non-parametric Hand Mesh Reconstruction
The decoder aggregate both local image features in pixels and geometric features in vertices.
Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraint
To tackle the challenge, we introduce an intermediate variable for grasp contact areas to constrain the grasp generation; in other words, we factorize the mapping into two sequential stages by assuming that grasping poses are fully constrained given contact maps: 1) we first learn contact map distributions to generate the potential contact maps for grasps; 2) then learn a mapping from the contact maps to the grasping poses.
Morig: Motion-aware rigging of character meshes from point clouds
We present MoRig, a method that automatically rigs character meshes driven by single-view point cloud streams capturing the motion of performing characters.
Rethinking Performance Gains in Image Dehazing Networks
Image dehazing is an active topic in low-level vision, and many image dehazing networks have been proposed with the rapid development of deep learning.
Ranked #1 on
Image Dehazing
on SOTS Outdoor
Modular Degradation Simulation and Restoration for Under-Display Camera
Together with a pixel-wise discriminator and supervised loss, we can train the generator to simulate the UDC imaging degradation process.
Learning Visibility for Robust Dense Human Body Estimation
An alternative approach is to estimate dense vertices of a predefined template body in the image space.
Skeleton-free Pose Transfer for Stylized 3D Characters
We present the first method that automatically transfers poses between stylized 3D characters without skeletal rigging.
Audio-driven Neural Gesture Reenactment with Video Motion Graphs
We present a method that reenacts a high-quality video with gestures matching a target speech audio.
Accelerated Federated Learning with Decoupled Adaptive Optimization
The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients.
Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothing
Theoretical analysis is conducted to derive that the Nemytskii operator is smooth and induces a Frechet differentiable smooth manifold.
Play It Cool: Dynamic Shifting Prevents Thermal Throttling
Machine learning (ML) has entered the mobile era where an enormous number of ML models are deployed on edge devices.
APES: Articulated Part Extraction from Sprite Sheets
Rigged puppets are one of the most prevalent representations to create 2D character animations.
A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains
In this paper, we propose a lightweight NMS-free framework to achieve real-time detection and high accuracy simultaneously.
Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection
To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target.
3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
(2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance.
Preserve Pre-trained Knowledge: Transfer Learning With Self-Distillation For Action Recognition
Video-based action recognition is one of the most popular topics in computer vision.
None Class Ranking Loss for Document-Level Relation Extraction
This ignores the context of entity pairs and the label correlations between the none class and pre-defined classes, leading to sub-optimal predictions.
Document-level Relation Extraction
Emotion Classification
+2
Human-Centered Prior-Guided and Task-Dependent Multi-Task Representation Learning for Action Recognition Pre-Training
Recently, much progress has been made for self-supervised action recognition.
FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server
Despite achieving remarkable performance, Federated Learning (FL) suffers from two critical challenges, i. e., limited computational resources and low training efficiency.
Lesion Localization in OCT by Semi-Supervised Object Detection
Over 300 million people worldwide are affected by various retinal diseases.
Multi-Robot Collaborative Perception with Graph Neural Networks
Multi-robot systems such as swarms of aerial robots are naturally suited to offer additional flexibility, resilience, and robustness in several tasks compared to a single robot by enabling cooperation among the agents.
Faithful Extreme Rescaling via Generative Prior Reciprocated Invertible Representations
This paper presents a Generative prior ReciprocAted Invertible rescaling Network (GRAIN) for generating faithful high-resolution (HR) images from low-resolution (LR) invertible images with an extreme upscaling factor (64x).
Efficient Device Scheduling with Multi-Job Federated Learning
However, the scheduling of devices for multiple jobs with FL remains a critical and open problem.
Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory
Despite achieving remarkable efficiency, traditional network pruning techniques often follow manually-crafted heuristics to generate pruned sparse networks.
Multi-Modal Multi-Instance Learning for Retinal Disease Recognition
We propose in this paper Multi-Modal Multi-Instance Learning (MM-MIL) for selectively fusing CFP and OCT modalities.
Virtual synchronous generator of PV generation without energy storage for frequency support in autonomous microgrid
PV generation reserve a part of the active power in accordance with the pre-defined power versus voltage curve.
Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
Mainstream lane marker detection methods are implemented by predicting the overall structure and deriving parametric curves through post-processing.
Ranked #3 on
Lane Detection
on TuSimple
Towards a Better Understanding of Linear Models for Recommendation
Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.
From Distributed Machine Learning to Federated Learning: A Survey
Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks.
Cross-lingual Entity Alignment with Adversarial Kernel Embedding and Adversarial Knowledge Translation
With the guidance of known aligned entities in the context of multiple random walks, an adversarial knowledge translation model is developed to fill and translate masked entities in pairwise random walks from two KGs.
Connected and Automated Vehicle Distributed Control for On-ramp Merging Scenario: A Virtual Rotation Approach
In this study, we propose a rotation-based connected automated vehicle (CAV) distributed cooperative control strategy for an on-ramp merging scenario.
CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge
In this paper, we present CogNet, a knowledge base (KB) dedicated to integrating three types of knowledge: (1) linguistic knowledge from FrameNet, which schematically describes situations, objects and events.
Infrastructure Assisted Constrained Connected Automated Vehicle Trajectory Optimization on Curved Roads: A Spatial Formulation on a Curvilinear Coordinate
This paper presents an infrastructure assisted constrained connected automated vehicles (CAVs) trajectory optimization method on curved roads.
Optimal Dynamic Futures Portfolios Under a Multiscale Central Tendency Ornstein-Uhlenbeck Model
We study the problem of dynamically trading multiple futures whose underlying asset price follows a multiscale central tendency Ornstein-Uhlenbeck (MCTOU) model.
Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection
However, universal language models may perform weakly in these fake news detection for lack of large-scale annotated data and sufficient semantic understanding of domain-specific knowledge.
Defect extremal surface as the holographic counterpart of Island formula
We propose defect extremal surface as the holographic counterpart of boundary quantum extremal surface.
High Energy Physics - Theory Strongly Correlated Electrons General Relativity and Quantum Cosmology Quantum Physics
Partially Connected Automated Vehicle Cooperative Control Strategy with a Deep Reinforcement Learning Approach
This paper proposes a cooperative strategy of connected and automated vehicles (CAVs) longitudinal control for partially connected and automated traffic environment based on deep reinforcement learning (DRL) algorithm, which enhances the string stability of mixed traffic, car following efficiency, and energy efficiency.
$K$-theoretic quasimap wall-crossing
In this paper, we prove a K-theoretic wall-crossing formula for $\epsilon$-stable quasimaps for all GIT targets in all genera.
Algebraic Geometry Mathematical Physics Mathematical Physics 14N35
Adversarial Attacks on Deep Graph Matching
Despite achieving remarkable performance, deep graph learning models, such as node classification and network embedding, suffer from harassment caused by small adversarial perturbations.
Manifold Partition Discriminant Analysis
We propose a novel algorithm for supervised dimensionality reduction named Manifold Partition Discriminant Analysis (MPDA).
Neural Latent Dependency Model for Sequence Labeling
One limitation of linear chain CRFs is their inability to model long-range dependencies between labels.
Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness
We collect and build a large-scale Chinese dataset aligned with the commonsense knowledge for dialogue generation.
A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction
Textual patterns (e. g., Country's president Person) are specified and/or generated for extracting factual information from unstructured data.
RigNet: Neural Rigging for Articulated Characters
We present RigNet, an end-to-end automated method for producing animation rigs from input character models.
MakeItTalk: Speaker-Aware Talking-Head Animation
We present a method that generates expressive talking heads from a single facial image with audio as the only input.
Multi-boundary entanglement in Chern-Simons theory with finite gauge groups
We study the multi-boundary entanglement structure of the states prepared in (1+1) and (2+1) dimensional Chern-Simons theory with finite discrete gauge group $G$.
High Energy Physics - Theory Mesoscale and Nanoscale Physics Quantum Physics
A Video Analysis Method on Wanfang Dataset via Deep Neural Network
To solve this problem, in this paper, we describe the new function for real-time multi-object detection in sports competition and pedestrians flow detection in public based on deep learning.
End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation
Video super-resolution aims at generating a high-resolution video from its low-resolution counterpart.
ETNet: Error Transition Network for Arbitrary Style Transfer
Numerous valuable efforts have been devoted to achieving arbitrary style transfer since the seminal work of Gatys et al.
Platoon trajectories generation: A unidirectional interconnected LSTM-based car following model
However, the traffic micro-simulation accuracy of car following models in a platoon level, especially during traffic oscillations, still needs to be enhanced.
Optimal Dynamic Futures Portfolio in a Regime-Switching Market Framework
We study the problem of dynamically trading futures in a regime-switching market.
Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets
We present a learning method for predicting animation skeletons for input 3D models of articulated characters.
SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings.
A Top-Down Approach for the Multiple Exercises and Valuation of Employee Stock Options
We propose a new framework to value employee stock options (ESOs) that captures multiple exercises of different quantities over time.
EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
Style transfer has been an important topic both in computer vision and graphics.
DeepMove: Learning Place Representations through Large Scale Movement Data
DeepMove is spatial and temporal context aware.
VisemeNet: Audio-Driven Animator-Centric Speech Animation
We present a novel deep-learning based approach to producing animator-centric speech motion curves that drive a JALI or standard FACS-based production face-rig, directly from input audio.
Graphics
Non-Stationary Texture Synthesis by Adversarial Expansion
We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar.
Full 3D Reconstruction of Transparent Objects
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades.
Triplet-Center Loss for Multi-View 3D Object Retrieval
Most existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with deep metric learning for 3D object retrieval is more or less neglected.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
A Large-scale Distributed Video Parsing and Evaluation Platform
Visual surveillance systems have become one of the largest data sources of Big Visual Data in real world.
A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories
Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene.
Cascaded Interactional Targeting Network for Egocentric Video Analysis
Firstly, a novel EM-like learning framework is proposed to train the pixel-level deep convolutional neural network (DCNN) by seamlessly integrating weakly supervised data (i. e., massive bounding box annotations) with a small set of strongly supervised data (i. e., fully annotated hand segmentation maps) to achieve state-of-the-art hand segmentation performance.
Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-Based Shrinkage
Facing to the challenges of trajectory clustering, e. g., large variations within a cluster and ambiguities across clusters, we first introduce an adaptive multi-kernel-based estimation process to estimate the `shrunk' positions and speeds of trajectories' points.
Interaction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition
Secondly, these object regions are matched and tracked across frames to form a large spatio-temporal graph based on the appearance matching and the dense motion trajectories through them.
Fine-grained Action Recognition
Human-Object Interaction Detection
+1
Structure Learning of Probabilistic Graphical Models: A Comprehensive Survey
Probabilistic graphical models combine the graph theory and probability theory to give a multivariate statistical modeling.
Regularized Distance Metric Learning:Theory and Algorithm
In this paper, we examine the generalization error of regularized distance metric learning.
