Search Results for author:
Found 103 papers, 44 papers with code
Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing
We present a novel differentiable point-based rendering framework for material and lighting decomposition from multi-view images, enabling editing, ray-tracing, and real-time relighting of the 3D point cloud.
L(M)V-IQL: Multiple Intention Inverse Reinforcement Learning for Animal Behavior Characterization
In advancing the understanding of decision-making processes, mathematical models, particularly Inverse Reinforcement Learning (IRL), have proven instrumental in reconstructing animal's multiple intentions amidst complex behaviors.
Alignment and Outer Shell Isotropy for Hyperbolic Graph Contrastive Learning
We show that in the hyperbolic space one has to address the leaf- and height-level uniformity which are related to properties of trees, whereas in the ambient space of the hyperbolic manifold, these notions translate into imposing an isotropic ring density towards boundaries of Poincar\'e ball.
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence.
PaintHuman: Towards High-fidelity Text-to-3D Human Texturing via Denoised Score Distillation
We first propose a novel score function, Denoised Score Distillation (DSD), which directly modifies the SDS by introducing negative gradient components to iteratively correct the gradient direction and generate high-quality textures.
Tracking Anything in Heart All at Once
Myocardial motion tracking stands as an essential clinical tool in the prevention and detection of Cardiovascular Diseases (CVDs), the foremost cause of death globally.
Data-driven Forced Oscillation Localization using Inferred Impulse Responses
Poorly damped oscillations pose threats to the stability and reliability of interconnected power systems.
RHINO: Regularizing the Hash-based Implicit Neural Representation
This connection ensures a seamless backpropagation of gradients from the network's output back to the input coordinates, thereby enhancing regularization.
Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail
Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance.
WebArena: A Realistic Web Environment for Building Autonomous Agents
Building upon our environment, we release a set of benchmark tasks focusing on evaluating the functional correctness of task completions.
Topology-aware Piecewise Linearization of the AC Power Flow through Generative Modeling
Effective power flow modeling critically affects the ability to efficiently solve large-scale grid optimization problems, especially those with topology-related decision variables.
Interpretable Neural Embeddings with Sparse Self-Representation
Many methods employ sparse representation to learn interpretable word embeddings for better interpretability.
Cascade Subspace Clustering for Outlier Detection
A suitable Markov Chain can be defined on the self-representation and it allows us to recognize the difference between inliers and outliers.
AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation
Unlike previous approaches that can only synthesize avatars based on simple text descriptions, our method enables the creation of personalized avatars from casually captured face or body images, while still supporting text-based model generation and editing.
COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements
To study the contextual dynamics of offensiveness, we train models to generate COBRA explanations, with and without access to the context.
Hierarchical Prompting Assists Large Language Model on Web Navigation
Large language models (LLMs) struggle on processing complicated observations in interactive decision making tasks.
High-Fidelity 3D Face Generation from Natural Language Descriptions
Synthesizing high-quality 3D face models from natural language descriptions is very valuable for many applications, including avatar creation, virtual reality, and telepresence.
Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement
In this paper, we propose a novel prototype-based label propagation to solve these issues.
NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination
Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images.
From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection
Unlike current deep keypoint detectors that are trained to recognize limited number of body parts, few-shot keypoint detection (FSKD) attempts to localize any keypoints, including novel or base keypoints, depending on the reference samples.
Disorder-invariant Implicit Neural Representation
However, the expressive power of INR is limited by the spectral bias in the network training.
CelebV-Text: A Large-Scale Facial Text-Video Dataset
This paper presents CelebV-Text, a large-scale, diverse, and high-quality dataset of facial text-video pairs, to facilitate research on facial text-to-video generation tasks.
Optimal Power System Topology Control Under Uncertain Wildfire Risk
Wildfires pose a significant threat to the safe and reliable operation of electric power systems.
Computational Language Acquisition with Theory of Mind
We also find some evidence that increasing task difficulty in the training process results in more fluent and precise utterances in evaluation.
RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs
We propose a robust and accurate non-parametric method for single-view 3D face reconstruction (SVFR).
EXCALIBUR: Encouraging and Evaluating Embodied Exploration
Humans constantly explore and learn about their environment out of curiosity, gather information, and update their models of the world.
Wind Power Scenario Generation Using Graph Convolutional Generative Adversarial Network
Generating wind power scenarios is very important for studying the impacts of multiple wind farms that are interconnected to the grid.
Spectral Feature Augmentation for Graph Contrastive Learning and Beyond
Although augmentations (e. g., perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible, complementary yet not well researched strategy.
DINER: Disorder-Invariant Implicit Neural Representation
Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems.
Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue
We provide empirical comparisons of metrics, analysis of three models, and make suggestions for how the field might best progress.
Dynamic Response Recovery Using Ambient Synchrophasor Data: A Synthetic Texas Interconnection Case Study
Wide-area dynamic studies are of paramount importance to ensure the stability and reliability of power grids.
CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields.
Ranked #1 on
Unconditional Video Generation
on CelebV-HQ
An Unsupervised Deep-Learning Method for Bone Age Assessment
In this paper, based on the convolutional auto-encoder with constraints (CCAE), an unsupervised deep-learning model proposed in the classification of the fingerprint, we propose this model for the classification of the bone age and baptize it BA-CCAE.
COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
In this paper, we show that the node embedding obtained via the graph augmentations is highly biased, somewhat limiting contrastive models from learning discriminative features for downstream tasks.
Topology-aware Graph Neural Networks for Learning Feasible and Adaptive ac-OPF Solutions
We develop a new topology-informed graph neural network (GNN) approach for predicting the optimal solutions of real-time ac-OPF problem.
Migrating Face Swap to Mobile Devices: A lightweight Framework and A Supervised Training Solution
In this work, we propose MobileFSGAN, a novel lightweight GAN for face swap that can run on mobile devices with much fewer parameters while achieving competitive performance.
Epipolar Focus Spectrum: A Novel Light Field Representation and Application in Dense-view Reconstruction
Existing light field representations, such as epipolar plane image (EPI) and sub-aperture images, do not consider the structural characteristics across the views, so they usually require additional disparity and spatial structure cues for follow-up tasks.
Ensemble Spectral Prediction (ESP) Model for Metabolite Annotation
We show that annotation performance, for ESP and other models, is a strong function of the number of molecules in the candidate set and their similarity to the target molecule.
SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification
Compared with the existing literature, our WNFG of EEG signals achieves up to 10 times of redundant edge reduction, and our approach achieves up to 97 times of model pruning without loss of classification accuracy.
Graph-adaptive Rectified Linear Unit for Graph Neural Networks
However, in the updating stage, all nodes share the same updating function.
Contrastive Laplacian Eigenmaps
Starting from a GAN-inspired contrastive formulation, we show that the Jensen-Shannon divergence underlying many contrastive graph embedding models fails under disjoint positive and negative distributions, which may naturally emerge during sampling in the contrastive setting.
Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Function
By fitting a 3D morphable model from multi-view images, the features of multiple images are extracted and aggregated in the mesh-attached UV space, which makes the implicit function more effective in recovering detailed facial shape.
EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning
We present an unsupErvised discriminAnt Subspace lEarning (EASE) that improves transductive few-shot learning performance by learning a linear projection onto a subspace built from features of the support set and the unlabeled query set in the test time.
MoFaNeRF: Morphable Facial Neural Radiance Field
To the best of our knowledge, our work is the first facial parametric model built upon a neural radiance field that can be used in fitting, generation and manipulation.
Scalable Learning for Optimal Load Shedding Under Power Grid Emergency Operations
Effective and timely responses to unexpected contingencies are crucial for enhancing the resilience of power grids.
Appliance Level Short-term Load Forecasting via Recurrent Neural Network
Accurate load forecasting is critical for electricity market operations and other real-time decision-making tasks in power systems.
FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction
By training on FaceScape data, a novel algorithm is proposed to predict elaborate riggable 3D face models from a single image input.
On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure
We study the problem of control policy design for decentralized state-feedback linear quadratic control with a partially nested information structure, when the system model is unknown.
Risk-Aware Learning for Scalable Voltage Optimization in Distribution Grids
Real-time coordination of distributed energy resources (DERs) is crucial for regulating the voltage profile in distribution grids.
Few-shot graph link prediction with domain adaptation
In this work, we propose an adversarial training based modification to the current state-of-the-arts link prediction method to solve this problem.
Dependency Induction Through the Lens of Visual Perception
Our experiments find that concreteness is a strong indicator for learning dependency grammars, improving the direct attachment score (DAS) by over 50\% as compared to state-of-the-art models trained on pure text.
REFINE: Random RangE FInder for Network Embedding
Moreover, we design a simple but efficient spectral filter for network enhancement to obtain higher-order information for node representation.
CIGLI: Conditional Image Generation from Language & Image
Instead of generating an image based on text as in text-image generation, this task requires the generation of an image from a textual description and an image prompt.
Data-driven Modeling for Distribution Grids Under Partial Observability
Accurately modeling power distribution grids is crucial for designing effective monitoring and decision making algorithms.
Efficient Representation for Electric Vehicle Charging Station Operations using Reinforcement Learning
Effectively operating electrical vehicle charging station (EVCS) is crucial for enabling the rapid transition of electrified transportation.
Detailed Avatar Recovery from Single Image
In this paper, we propose a novel learning-based framework that combines the robustness of the parametric model with the flexibility of free-form 3D deformation.
Graph Convolutional Network with Generalized Factorized Bilinear Aggregation
Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are still using linear transformations and a simple pooling step.
Few-shot Language Coordination by Modeling Theory of Mind
Positive results from our experiments hint at the importance of explicitly modeling communication as a socio-pragmatic progress.
Graph Neural Networks for Learning Real-Time Prices in Electricity Market
Solving the optimal power flow (OPF) problem in real-time electricity market improves the efficiency and reliability in the integration of low-carbon energy resources into the power grids.
Inferring power system dynamics from synchrophasor data using Gaussian processes
Synchrophasor data provide unprecedented opportunities for inferring power system dynamics, such as estimating voltage angles, frequencies, and accelerations along with power injection at all buses.
A Dynamic Response Recovery Framework Using Ambient Synchrophasor Data
Wide-area dynamic studies are of paramount importance to ensure the stability and reliability of power grids.
Enhancing the Spatio-temporal Observability of Grid-Edge Resources in Distribution Grids
The load recovery solutions can be utilized to identify the EV charging events at each load node and to infer the total behind-the-meter PV output.
Deep Anti-aliasing of Whole Focal Stack Using Slice Spectrum
Based on these two observations, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack.
Simple Spectral Graph Convolution
Our spectral analysis shows that our simple spectral graph convolution used in S^2GC is a low-pass filter which partitions networks into a few large parts.
Ranked #1 on
Node Clustering
on Wiki
Imbalance Robust Softmax for Deep Embeeding Learning
IR-Softmax can generalise to any softmax and its variants (which are discriminative for open-set problem) by directly setting the weights as their class centers, naturally solving the data imbalance problem.
Lets Play Music: Audio-driven Performance Video Generation
We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip.
AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
However, due to the lack of Deepfakes datasets with large variance in appearance, which can be hardly produced by recent identity swapping methods, the detection algorithm may fail in this situation.
Multi-agent Trajectory Prediction with Fuzzy Query Attention
Trajectory prediction for scenes with multiple agents and entities is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning.
Using Graph Neural Networks for Mass Spectrometry Prediction
We compare our results to NEIMS, a neural network model that utilizes molecular fingerprints as inputs.
The Return of Lexical Dependencies: Neural Lexicalized PCFGs
In this paper we demonstrate that $\textit{context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies}$.
Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses
In this paper, we propose a novel approach to convert given speech audio to a photo-realistic speaking video of a specific person, where the output video has synchronized, realistic, and expressive rich body dynamics.
Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
For this scheme, we propose a novel privacy-preserving architecture where two parties can collaboratively train a deep learning model efficiently while preserving the privacy of each party's data.
Self-Supervised Human Depth Estimation from Monocular Videos
Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data.
FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and propose a novel algorithm that is able to predict elaborate riggable 3D face models from a single image input.
SAPIEN: A SimulAted Part-based Interactive ENvironment
To achieve this task, a simulated environment with physically realistic simulation, sufficient articulated objects, and transferability to the real robot is indispensable.
Deep Audio-Visual Learning: A Survey
Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully.
EnsemFDet: An Ensemble Approach to Fraud Detection based on Bipartite Graph
Existing fraud detection methods try to identify unexpected dense subgraphs and treat related nodes as suspicious.
S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes
Grasping is among the most fundamental and long-lasting problems in robotics study.
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
We present FewRel 2. 0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances?
Learned Point Cloud Geometry Compression
This paper presents a novel end-to-end Learned Point Cloud Geometry Compression (a. k. a., Learned-PCGC) framework, to efficiently compress the point cloud geometry (PCG) using deep neural networks (DNN) based variational autoencoders (VAE).
Quantifying Similarity between Relations with Fact Distribution
We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases.
Ekar: An Explainable Method for Knowledge Aware Recommendation
Recently, a variety of methods have been developed for this problem, which generally try to learn effective representations of users and items and then match items to users according to their representations.
Ranked #1 on
Recommendation Systems
on Last.FM
Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies
Under a further strict saddle points assumption, this result establishes convergence to essentially locally-optimal policies of the underlying problem, and thus bridges the gap in existing literature on the convergence of PG methods.
Doc2hash: Learning Discrete Latent variables for Documents Retrieval
However, the discrete stochastic layer is usually incompatible with the backpropagation in the training stage, and thus causes a gradient flow problem because of non-differentiable operators.
Neural Finite-State Transducers: Beyond Rational Relations
We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings.
Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
This paper presents a novel framework to recover detailed human body shapes from a single image.
Breaking the Spatio-Angular Trade-off for Light Field Super-Resolution via LSTM Modelling on Epipolar Plane Images
We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.
Graph Neural Networks with Generated Parameters for Relation Extraction
Recently, progress has been made towards improving relational reasoning in machine learning field.
Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms.
Ranked #6 on
Multi-Person Pose Estimation
on OCHuman
Language Modeling with Sparse Product of Sememe Experts
Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words.
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers.
Put It Back: Entity Typing with Language Model Enhancement
Entity typing aims to classify semantic types of an entity mention in a specific context.
Cross-lingual Lexical Sememe Prediction
We propose a novel framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction.
Incorporating Chinese Characters of Words for Lexical Sememe Prediction
However, existing methods of lexical sememe prediction typically rely on the external context of words to represent the meaning, which usually fails to deal with low-frequency and out-of-vocabulary words.
Dense Light Field Reconstruction From Sparse Sampling Using Residual Network
A light field records numerous light rays from a real-world scene.
View Extrapolation of Human Body from a Single Image
We study how to synthesize novel views of human body from a single image.
Barotropic instability of shear flows
The second one is to write the linearized fluid equation in a Hamiltonian form and then use an instability index theory for general Hamiltonian PDEs.
Analysis of PDEs
Light Field Segmentation From Super-pixel Graph Representation
The large volume of input data and the redundancy of light field make it an open challenge.
4D Light Field Superpixel and Segmentation
Superpixel segmentation of 2D image has been widely used in many computer vision tasks.
Iterative Entity Alignment via Joint Knowledge Embeddings
During this process, we can align entities according to their semantic distance in this joint semantic space.
Occlusion-Model Guided Anti-Occlusion Depth Estimation in Light Field
Occlusion is one of the most challenging problems in depth estimation.
Decentralized learning for wireless communications and networking
This chapter deals with decentralized learning algorithms for in-network processing of graph-valued data.
