Search Results for author:
Found 61 papers, 28 papers with code
ActPerFL: Active Personalized Federated Learning
Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training.
Action-Attentive Deep Reinforcement Learning for Autonomous Alignment of Beamlines
Synchrotron radiation sources play a crucial role in fields such as materials science, biology, and chemistry.
MARS: Unleashing the Power of Variance Reduction for Training Large Models
Despite the development of numerous variance reduction algorithms in the past decade aimed at accelerating stochastic optimization in both convex and nonconvex settings, variance reduction has not found widespread success in training deep neural networks or large language models.
UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation
In this work we design a Unified Voxelization framework for explicit learning of scene representations, dubbed UniVoxel, which allows for efficient modeling of the geometry, materials and illumination jointly, thereby accelerating the inverse rendering significantly.
DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
To address this limitation, we propose an agent model capable of generating counterfactual images that prompt different decisions when plugged into a black box model.
Graph Neural Thompson Sampling
We formally formulate the problem as an instance of graph action bandit.
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
In this work, we introduce Direct3D, a native 3D generative model scalable to in-the-wild input images, without requiring a multiview diffusion model or SDS optimization.
GMPC: Geometric Model Predictive Control for Wheeled Mobile Robot Trajectory Tracking
The configuration of most robotic systems lies in continuous transformation groups.
Direct Shooting Method for Numerical Optimal Control: A Modified Transcription Approach
Direct shooting is an efficient method to solve numerical optimal control.
Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature.
Enhance Reasoning for Large Language Models in the Game Werewolf
This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents.
Re-thinking Data Availability Attacks Against Deep Neural Networks
In this paper we re-examine the existing availability attack methods and propose a novel two-stage min-max-min optimization paradigm to generate robust unlearnable noise.
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps
We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task.
Dynamic Multimodal Information Bottleneck for Multimodality Classification
Specifically, our information bottleneck module serves to filter out the task-irrelevant information and noises in the fused feature, and we further introduce a sufficiency loss to prevent dropping of task-relevant information, thus explicitly preserving the sufficiency of prediction information in the distilled feature.
Exploring Decision-based Black-box Attacks on Face Forgery Detection
Further, the fake faces by our method can pass face forgery detection and face recognition, which exposes the security problems of face forgery detectors.
Locate and Verify: A Two-Stream Network for Improved Deepfake Detection
Deepfake has taken the world by storm, triggering a trust crisis.
Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detection
To address this challenge, this paper introduces a novel multi-scale cross-restoration framework for ECG anomaly detection and localization that considers both local and global ECG characteristics.
Autonomy 2.0: The Quest for Economies of Scale
With the advancement of robotics and AI technologies in the past decade, we have now entered the age of autonomous machines.
Query-Efficient Decision-based Black-Box Patch Attack
In this work, we first explore the decision-based patch attack.
Online Map Vectorization for Autonomous Driving: A Rasterization Perspective
However, current map vectorization methods often exhibit deviations, and the existing evaluation metric for map vectorization lacks sufficient sensitivity to detect these deviations.
Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
However, the vanilla Euclidean space is not efficient for modeling important motion characteristics such as the joint-wise angular acceleration, which reveals the driving force behind the motion.
Ranked #16 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Re-thinking Data Availablity Attacks Against Deep Neural Networks
The unauthorized use of personal data for commercial purposes and the clandestine acquisition of private data for training machine learning models continue to raise concerns.
Towards Generalizable Data Protection With Transferable Unlearnable Examples
One of the crucial factors contributing to this success has been the access to an abundance of high-quality data for constructing machine learning models.
Delving into the Adversarial Robustness of Federated Learning
In this work, we propose a novel algorithm called Decision Boundary based Federated Adversarial Training (DBFAT), which consists of two components (local re-weighting and global regularization) to improve both accuracy and robustness of FL systems.
Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition
Dynamic Facial Expression Recognition (DFER) is a rapidly developing field that focuses on recognizing facial expressions in video format.
Ranked #11 on
Dynamic Facial Expression Recognition
on FERV39k
Dynamic Facial Expression Recognition
Facial Expression Recognition
Graph Federated Learning with Hidden Representation Sharing
On the other hand, due to the increasing demands for the protection of clients' data privacy, Federated Learning (FL) has been widely adopted: FL requires models to be trained in a multi-client system and restricts sharing of raw data among clients.
Towards Efficient Dynamic Uplink Scheduling over Multiple Unknown Channels
To alleviate the challenge, we reformulate the problem as a variant of the restless multi-armed bandit (RMAB) problem and leverage Whittle's index theory to design an index-based scheduling policy algorithm.
Who is Gambling? Finding Cryptocurrency Gamblers Using Multi-modal Retrieval Methods
Meanwhile, decentralized applications have also attracted intense attention from the online gambling community, with more and more decentralized gambling platforms created through the help of smart contracts.
Shape Matters: Deformable Patch Attack
Though deep neural networks (DNNs) have demonstrated excellent performance in computer vision, they are susceptible and vulnerable to carefully crafted adversarial examples which can mislead DNNs to incorrect outputs.
Federated Learning with Label Distribution Skew via Logits Calibration
Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance.
Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations
In this work we design a novel knowledge distillation framework to guide the learning of the object detector and thereby restrain the overfitting in both the pre-training stage on base classes and fine-tuning stage on novel classes.
Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection
Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and transferred implicitly from base classes with abundant samples to novel classes with limited samples via such a two-stage training strategy.
NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition
To deal with this issue, we advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs by constructing non-flat lattices.
Ranked #9 on
Chinese Named Entity Recognition
on Resume NER
Chinese Named Entity Recognition
named-entity-recognition
+2
Copy Motion From One to Another: Fake Motion Video Generation
3) To enhance texture details, we encode facial features with geometric guidance and employ local GANs to refine the face, feet, and hands.
Self-Aware Personalized Federated Learning
In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned.
Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation
State-of-the-art methods strive to incorporate additional visual evidences from neighboring frames (supporting frames) to facilitate the pose estimation of the current frame (key frame).
Towards Practical Certifiable Patch Defense with Vision Transformer
To move towards a practical certifiable patch defense, we introduce Vision Transformer (ViT) into the framework of Derandomized Smoothing (DS).
Residual Bootstrap Exploration for Stochastic Linear Bandit
We propose a new bootstrap-based online algorithm for stochastic linear bandit problems.
Federated Learning Challenges and Opportunities: An Outlook
Federated learning (FL) has been developed as a promising framework to leverage the resources of edge devices, enhance customers' privacy, comply with regulations, and reduce development costs.
Dual Learning Music Composition and Dance Choreography
Music and dance have always co-existed as pillars of human activities, contributing immensely to the cultural, social, and entertainment functions in virtually all societies.
Motion Prediction via Joint Dependency Modeling in Phase Space
In this paper, we introduce a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics.
Detecting Camouflaged Object in Frequency Domain
We first design a novel frequency enhancement module (FEM) to dig clues of camouflaged objects in the frequency domain.
Towards Efficient Data Free Black-Box Adversarial Attack
The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate.
Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results.
DENSE: Data-Free One-Shot Federated Learning
One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.
Music-to-Dance Generation with Optimal Transport
We introduce an optimal transport distance for evaluating the authenticity of the generated dance distribution and a Gromov-Wasserstein distance to measure the correspondence between the dance distribution and the input music.
Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game
The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.
MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition
This paper presents a novel Multi-metadata Embedding based Cross-Transformer (MECT) to improve the performance of Chinese NER by fusing the structural information of Chinese characters.
Aggregated Multi-GANs for Controlled 3D Human Motion Prediction
Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways.
Deep Dual Consecutive Network for Human Pose Estimation
Multi-frame human pose estimation in complicated situations is challenging.
Ranked #1 on
Multi-Person Pose Estimation
on PoseTrack2017
(using extra training data)
Motion Prediction Using Trajectory Cues
Predicting human motion from a historical pose sequence is at the core of many applications in computer vision.
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.
Convolution with even-sized kernels and symmetric padding
Compact convolutional neural networks gain efficiency mainly through depthwise convolutions, expanded channels and complex topologies, which contrarily aggravate the training process.
Robust and Efficient Graph Correspondence Transfer for Person Re-identification
To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID.
Graph Correspondence Transfer for Person Re-identification
In this paper, we propose a graph correspondence transfer (GCT) approach for person re-identification.
L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs).
Training and Inference with Integers in Deep Neural Networks
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics.
Slim Embedding Layers for Recurrent Neural Language Models
When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models.
Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts
Current state-of-the-art systems for visual content analysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples.
A unified model of short-range and long-range motion perception
The human vision system is able to effortlessly perceive both short-range and long-range motion patterns in complex dynamic scenes.
Model selection and velocity estimation using novel priors for motion patterns
Psychophysical experiments show that humans are better at perceiving rotation and expansion than translation.
