Search Results for author:
Found 121 papers, 40 papers with code
Tell2Design: A Dataset for Language-Guided Floor Plan Generation
We make multiple contributions to initiate research on this task.
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.
RigNet: Neural Rigging for Articulated Characters
We present RigNet, an end-to-end automated method for producing animation rigs from input character models.
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.
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.
LRM: Large Reconstruction Model for Single Image to 3D
We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds.
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.
Skeleton-free Pose Transfer for Stylized 3D Characters
We present the first method that automatically transfers poses between stylized 3D characters without skeletal rigging.
LLM Inference Unveiled: Survey and Roofline Model Insights
Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques.
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 #2 on
Image Dehazing
on RS-Haze
A Survey on Multimodal Large Language Models for Autonomous Driving
We first introduce the background of Multimodal Large Language Models (MLLMs), the multimodal models development using LLMs, and the history of autonomous driving.
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.
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.
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.
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.
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.
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.
DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing
In this study, we utilize the DINOv2 model as the backbone network for trimming and fine-tuning to extract robust image features.
SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
Context information, such as road maps and surrounding agents' states, provides crucial geometric and semantic information for motion behavior prediction.
UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization
Our approach introduces a Temporal Feature Abnormal Attention (TFAA) module based on temporal feature reconstruction to enhance the detection of temporal differences.
Ranked #1 on
Temporal Forgery Localization
on LAV-DF
Neural Texture Synthesis With Guided Correspondence
More importantly, the Guided Correspondence loss can function as a general textural loss in, e. g., training generative networks for real-time controlled synthesis and inversion-based single-image editing.
Learning Navigational Visual Representations with Semantic Map Supervision
Being able to perceive the semantics and the spatial structure of the environment is essential for visual navigation of a household robot.
Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization
This paper proposes a Parameter-efficient prompt Tuning approach with Adaptive Optimization, i. e., FedPepTAO, to enable efficient and effective FL of LLMs.
Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion
To address the above issues, we propose Diffuse3D which employs a pre-trained diffusion model for global synthesis, while amending the model to activate depth-aware inference.
APES: Articulated Part Extraction from Sprite Sheets
Rigged puppets are one of the most prevalent representations to create 2D character animations.
Generating Non-Stationary Textures using Self-Rectification
This paper addresses the challenge of example-based non-stationary texture synthesis.
Deformable One-shot Face Stylization via DINO Semantic Guidance
This paper addresses the complex issue of one-shot face stylization, focusing on the simultaneous consideration of appearance and structure, where previous methods have fallen short.
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
+3
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).
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.
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.
Cyclic Learning: Bridging Image-level Labels and Nuclei Instance Segmentation
Experiments on three datasets demonstrate the good generality of our method, which outperforms other image-level weakly supervised methods for nuclei instance segmentation, and achieves comparable performance to fully-supervised methods.
Zero-shot Nuclei Detection via Visual-Language Pre-trained Models
Foremost, our work demonstrates that the VLPM pre-trained on natural image-text pairs exhibits astonishing potential for downstream tasks in the medical field as well.
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.
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.
DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesis
To address this, we develop a generalist model that shares architecture and parameters across centers to utilize the shared knowledge.
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.
Full 3D Reconstruction of Transparent Objects
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades.
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.
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.
DeepMove: Learning Place Representations through Large Scale Movement Data
DeepMove is spatial and temporal context aware.
EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer
Style transfer has been an important topic both in computer vision and graphics.
Regularized Distance Metric Learning:Theory and Algorithm
In this paper, we examine the generalization error of regularized distance metric learning.
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
+2
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.
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.
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.
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.
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.
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
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
Neural Latent Dependency Model for Sequence Labeling
One limitation of linear chain CRFs is their inability to model long-range dependencies between labels.
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).
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.
Optimal Dynamic Futures Portfolio in a Regime-Switching Market Framework
We study the problem of dynamically trading futures in a regime-switching market.
$K$-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
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.
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
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.
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.
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.
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.
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.
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.
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.
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 #2 on
Lane Detection
on TuSimple
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.
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.
Adversarial Attack against Cross-lingual Knowledge Graph Alignment
Recent literatures have shown that knowledge graph (KG) learning models are highly vulnerable to adversarial attacks.
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.
Efficient Device Scheduling with Multi-Job Federated Learning
However, the scheduling of devices for multiple jobs with FL remains a critical and open problem.
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.
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.
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.
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.
The AISP-SJTU Simultaneous Translation System for IWSLT 2022
This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task.
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.
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.
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.
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.
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.
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.
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.
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.
Pixel-Aligned Non-parametric Hand Mesh Reconstruction
The decoder aggregate both local image features in pixels and geometric features in vertices.
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.
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.
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.
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.
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.
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.
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).
L0-norm constraint normalized subband adaptive filtering algorithm: Performance development and AEC application
Limited by fixed step-size and sparsity penalty factor, the conventional sparsity-aware normalized subband adaptive filtering (NSAF) type algorithms suffer from trade-off requirements of high filtering accurateness and quicker convergence behavior for sparse system identification.
Single-View View Synthesis with Self-Rectified Pseudo-Stereo
In this way, the challenging novel view synthesis process is decoupled into two simpler problems of stereo synthesis and 3D reconstruction.
On building machine learning pipelines for Android malware detection: a procedural survey of practices, challenges and opportunities
In this paper, we address this problem with a review of 42 highly-cited papers, spanning a decade of research (from 2011 to 2021).
A Survey on Cross-Architectural IoT Malware Threat Hunting
In recent years, the increase in non-Windows malware threats had turned the focus of the cybersecurity community.
Efficient Visual Fault Detection for Freight Train Braking System via Heterogeneous Self Distillation in the Wild
Efficient visual fault detection of freight trains is a critical part of ensuring the safe operation of railways under the restricted hardware environment.
Fast algorithms for k-submodular maximization subject to a matroid constraint
In this paper, we apply a Threshold-Decreasing Algorithm to maximize $k$-submodular functions under a matroid constraint, which reduces the query complexity of the algorithm compared to the greedy algorithm with little loss in approximation ratio.
GRIP: Generating Interaction Poses Using Latent Consistency and Spatial Cues
In contrast, we introduce GRIP, a learning-based method that takes, as input, the 3D motion of the body and the object, and synthesizes realistic motion for both hands before, during, and after object interaction.
Graph-Based Interaction-Aware Multimodal 2D Vehicle Trajectory Prediction using Diffusion Graph Convolutional Networks
Within this framework, vehicles' motions are conceptualized as nodes in a time-varying graph, and the traffic interactions are represented by a dynamic adjacency matrix.
ContactGen: Generative Contact Modeling for Grasp Generation
This paper presents a novel object-centric contact representation ContactGen for hand-object interaction.
Visual Environment Assessment for Safe Autonomous Quadrotor Landing
Autonomous identification and evaluation of safe landing zones are of paramount importance for ensuring the safety and effectiveness of aerial robots in the event of system failures, low battery, or the successful completion of specific tasks.
Deep Learning for Vascular Segmentation and Applications in Phase Contrast Tomography Imaging
Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed.
Sequencing-enabled Hierarchical Cooperative CAV On-ramp Merging Control with Enhanced Stability and Feasibility
Subsequently, the lower-level control employs a longitudinal distributed model predictive control (MPC) supplemented by a virtual car-following (CF) concept to ensure asymptotic local stability, l_2 norm string stability, and safety.
Spatial-wise Dynamic Distillation for MLP-like Efficient Visual Fault Detection of Freight Trains
Existing modeling shortcomings of spatial invariance and pooling layers in conventional CNNs often ignore the neglect of crucial global information, resulting in error localization for fault objection tasks of freight trains.
Beyond 1D and oversimplified kinematics: A generic analytical framework for surrogate safety measures
This paper presents a generic analytical framework tailored for surrogate safety measures (SSMs) that is versatile across various highway geometries, capable of encompassing vehicle dynamics of differing dimensionality and fidelity, and suitable for dynamic, real-world environments.
A Generic Stochastic Hybrid Car-following Model Based on Approximate Bayesian Computation
However, the CF behavior of human drivers is highly stochastic and nonlinear.
AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices
First, we propose an asynchronous FL system model with an efficient model aggregation method for improving the FL convergence.
In-Hand 3D Object Reconstruction from a Monocular RGB Video
We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of $52\%$ on HO3D and $20\%$ on HOD.
Jump Cut Smoothing for Talking Heads
We leverage the appearance of the subject from the other source frames in the video, fusing it with a mid-level representation driven by DensePose keypoints and face landmarks.
ActAnywhere: Subject-Aware Video Background Generation
Generating video background that tailors to foreground subject motion is an important problem for the movie industry and visual effects community.
Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM
We present Human-LRM, a diffusion-guided feed-forward model that predicts the implicit field of a human from a single image.
Overview of Sensing Attacks on Autonomous Vehicle Technologies and Impact on Traffic Flow
While perception systems in Connected and Autonomous Vehicles (CAVs), which encompass both communication technologies and advanced sensors, promise to significantly reduce human driving errors, they also expose CAVs to various cyberattacks.
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
With the emergence of text-to-video (T2V) diffusion models, its temporal counterpart, motion customization, has not yet been well investigated.
A Survey of Lottery Ticket Hypothesis
The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i. e., winning tickets) that can achieve even better performance than the original model when trained in isolation.
CTSM: Combining Trait and State Emotions for Empathetic Response Model
Specifically, to sufficiently perceive emotions in dialogue, we first construct and encode trait and state emotion embeddings, and then we further enhance emotional perception capability through an emotion guidance module that guides emotion representation.
MedRG: Medical Report Grounding with Multi-modal Large Language Model
Medical Report Grounding is pivotal in identifying the most relevant regions in medical images based on a given phrase query, a critical aspect in medical image analysis and radiological diagnosis.
