Search Results for author:
Found 148 papers, 36 papers with code
The USTC-NELSLIP Offline Speech Translation Systems for IWSLT 2022
This paper describes USTC-NELSLIP’s submissions to the IWSLT 2022 Offline Speech Translation task, including speech translation of talks from English to German, English to Chinese and English to Japanese.
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks
Previous works on word-level attacks widely use word importance ranking (WIR) methods and complex search methods, including greedy search and heuristic algorithms, to find optimal substitutions.
Leveraging Reinforcement Learning and Koopman Theory for Enhanced Model Predictive Control Performance
This study presents an innovative approach to Model Predictive Control (MPC) by leveraging the powerful combination of Koopman theory and Deep Reinforcement Learning (DRL).
How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
In this work, we focus on two representative tasks in the category of regular language recognition, known as `even pairs' and `parity check', the aim of which is to determine whether the occurrences of certain subsequences in a given sequence are even.
Benchmark of Segmentation Techniques for Pelvic Fracture in CT and X-ray: Summary of the PENGWIN 2024 Challenge
The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance.
Exploiting Temporal State Space Sharing for Video Semantic Segmentation
Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes.
DomainCQA: Crafting Expert-Level QA from Domain-Specific Charts
Chart Question Answering (CQA) benchmarks are essential for evaluating the capability of Multimodal Large Language Models (MLLMs) to interpret visual data.
A Shared Low-Rank Adaptation Approach to Personalized RLHF
Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models.
Transformer-based Wireless Symbol Detection Over Fading Channels
Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts without model update.
CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts
We introduce CHOrD, a novel framework for scalable synthesis of 3D indoor scenes, designed to create house-scale, collision-free, and hierarchically structured indoor digital twins.
HisTrackMap: Global Vectorized High-Definition Map Construction via History Map Tracking
Thirdly, we propose a global perspective metric to evaluate the quality of temporal geometry construction in HD maps, filling the gap in current metrics for assessing global geometric perception results.
Adaptive Reinforcement Learning for State Avoidance in Discrete Event Systems
Reinforcement learning (RL) has emerged as a potent paradigm for autonomous decision-making in complex environments.
Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks
To address this, we investigate how to use existing explanation datasets for self-rationalization and evaluate models' out-of-distribution (OOD) performance.
Singing Voice Conversion with Accompaniment Using Self-Supervised Representation-Based Melody Features
Melody preservation is crucial in singing voice conversion (SVC).
Paper Copilot: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
The rapid growth of submissions to top-tier Artificial Intelligence (AI) and Machine Learning (ML) conferences has prompted many venues to transition from closed to open review platforms.
Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function
Recent advancements in data-driven weather forecasting models have delivered deterministic models that outperform the leading operational forecast systems based on traditional, physics-based models.
AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement
Based on a masked generative model, AnyEnhance is capable of handling both speech and singing voices, supporting a wide range of enhancement tasks including denoising, dereverberation, declipping, super-resolution, and target speaker extraction, all simultaneously and without fine-tuning.
Average Reward Reinforcement Learning for Wireless Radio Resource Management
In this paper, we address a crucial but often overlooked issue in applying reinforcement learning (RL) to radio resource management (RRM) in wireless communications: the mismatch between the discounted reward RL formulation and the undiscounted goal of wireless network optimization.
Chirpy3D: Creative Fine-grained 3D Object Fabrication via Part Sampling
This allows smooth interpolation and flexible recombination of parts to generate entirely new objects with species-specific details.
MarsSQE: Stereo Quality Enhancement for Martian Images Using Bi-level Cross-view Attention
In this paper, we present a novel stereo quality enhancement approach for Martian images, named MarsSQE.
RFPPO: Motion Dynamic RRT based Fluid Field - PPO for Dynamic TF/TA Routing Planning
Existing local dynamic route planning algorithms, when directly applied to terrain following/terrain avoidance, or dynamic obstacle avoidance for large and medium-sized fixed-wing aircraft, fail to simultaneously meet the requirements of real-time performance, long-distance planning, and the dynamic constraints of large and medium-sized aircraft.
Acquisition of Spatially-Varying Reflectance and Surface Normals via Polarized Reflectance Fields
Accurately measuring the geometry and spatially-varying reflectance of real-world objects is a complex task due to their intricate shapes formed by concave features, hollow engravings and diverse surfaces, resulting in inter-reflection and occlusion when photographed.
FedDW: Distilling Weights through Consistency Optimization in Heterogeneous Federated Learning
Federated Learning (FL) is an innovative distributed machine learning paradigm that enables neural network training across devices without centralizing data.
Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
However, existing works exhibit significant variations in training schemes and RL optimization objectives, and some methods are only applicable to diffusion models.
Pretrained Reversible Generation as Unsupervised Visual Representation Learning
Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored.
Decision Feedback In-Context Symbol Detection over Block-Fading Channels
Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts \textit{without model update}.
Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
Specifically, when the nominal model admits a low-rank structure, we propose a new algorithm, featuring a novel dataset distillation and a lower confidence bound (LCB) design for robust values under different types of the uncertainty set.
Learning Optimal Combination Patterns for Lightweight Stereo Image Super-Resolution
RWBlock empowers LSNB with the capability to explore various combination patterns of pairwise NAFBlocks by adaptive re-weighting of feature.
On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery
An intriguing property of the Transformer is its ability to perform in-context learning (ICL), where the Transformer can solve different inference tasks without parameter updating based on the contextual information provided by the corresponding input-output demonstration pairs.
On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
While transformers have demonstrated impressive capacities for in-context learning (ICL) in practice, theoretical understanding of the underlying mechanism enabling transformers to perform ICL is still in its infant stage.
Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
Large Language Models (LLMs) rely on the contextual information embedded in examples/demonstrations to perform in-context learning (ICL).
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years.
MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements.
Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation
We propose a label-adaptive learning approach: first, we fine-tune a model to learn veracity prediction with annotated labels (step-1 model).
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
We study the problems of differentially private federated online prediction from experts against both stochastic adversaries and oblivious adversaries.
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Our analysis technique involves the development of novel properties on the attention gradient and further in-depth analysis of how these properties contribute to the convergence of the training process.
Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences
Building on this task, we propose a novel PBRL method, Multi-Type Preference Learning (MTPL), which allows simultaneous learning from equal preferences while leveraging existing methods for learning from explicit preferences.
RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling under Continuous Representation
In this work, we verify for the first time that the parameter estimation performance of current mainstream methods will significantly decrease when the testing diffusion directions and the training diffusion directions are inconsistent.
Localized Gaussian Splatting Editing with Contextual Awareness
In the second Texture Enhancement step, we introduce a novel Depth-guided Inpainting Score Distillation Sampling (DI-SDS), which enhances geometry and texture details with the inpainting diffusion prior, beyond the scope of the 3D-aware diffusion prior knowledge in the first coarse step.
DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models
Specifically, we have developed Spatial Perturbation Learning (SPL) by exploiting the fixed and perturbation-sensitive nature of the image encoder in personalized generation.
Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging
This study illustrates the relative strengths and weaknesses of these competing paradigms using the GEM (Global Environmental Multiscale) and GraphCast models to represent physics-based and AI-based approaches, respectively.
Oracle Bone Inscriptions Multi-modal Dataset
Oracle bone inscriptions(OBI) is the earliest developed writing system in China, bearing invaluable written exemplifications of early Shang history and paleography.
Graph in Graph Neural Network
Given a set of graphs or a data sample whose components can be represented by a set of graphs (called multi-graph data sample), our GIG network starts with a GIG sample generation (GSG) module which encodes the input as a \textbf{GIG sample}, where each GIG vertex includes a graph.
GM-DF: Generalized Multi-Scenario Deepfake Detection
In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets.
TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems
Temporal relation extraction (TRE) aims to grasp the evolution of events or actions, and thus shape the workflow of associated tasks, so it holds promise in helping understand task requests initiated by requesters in crowdsourcing systems.
SYM3D: Learning Symmetric Triplanes for Better 3D-Awareness of GANs
Despite the growing success of 3D-aware GANs, which can be trained on 2D images to generate high-quality 3D assets, they still rely on multi-view images with camera annotations to synthesize sufficient details from all viewing directions.
Federated Representation Learning in the Under-Parameterized Regime
In this paper, we make the initial efforts to investigate FRL in the under-parameterized regime, where the FL model is insufficient to express the variations in all ground-truth models.
RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts
Therefore, we present a Prompt-Based Contrastive learning framework for TD (PBCT), which incorporates a prompt-based trigger detector to overcome dependence.
Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping
By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity.
Emphasizing Crucial Features for Efficient Image Restoration
SFAM consists of two modules: the spatial domain attention module (SDAM) and the frequency domain attention module (FDAM).
AMCEN: An Attention Masking-based Contrastive Event Network for Two-stage Temporal Knowledge Graph Reasoning
To achieve more accurate TKG reasoning, we propose an attention masking-based contrastive event network (AMCEN) with local-global temporal patterns for the two-stage prediction of future events.
DeepMpMRI: Tensor-decomposition Regularized Learning for Fast and High-Fidelity Multi-Parametric Microstructural MR Imaging
Deep learning has emerged as a promising approach for learning the nonlinear mapping between diffusion-weighted MR images and tissue parameters, which enables automatic and deep understanding of the brain microstructures.
ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze
Monte Carlo Tree Search (MCTS)-based algorithms, such as MuZero and its derivatives, have achieved widespread success in various decision-making domains.
CSR-dMRI: Continuous Super-Resolution of Diffusion MRI with Anatomical Structure-assisted Implicit Neural Representation Learning
The first is the latent feature extractor, which primarily extracts latent space feature maps from LR dMRI and anatomical images while learning structural prior information from the anatomical images.
Visualizing Routes with AI-Discovered Street-View Patterns
Third, we integrate these discovered patterns into driving route planners with new visualization techniques.
A Codesign of Scheduling and Parallelization for Large Model Training in Heterogeneous Clusters
The exponentially enlarged scheduling space and ever-changing optimal parallelism plan from adaptive parallelism together result in the contradiction between low-overhead and accurate performance data acquisition for efficient cluster scheduling.
Multiview Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks
In conclusion, the proposed model can effectively improve the clustering ac-curacy of HSI.
Efficient Prompt Optimization Through the Lens of Best Arm Identification
TRIPLE is built on a novel connection established between prompt optimization and fixed-budget best arm identification (BAI-FB) in multi-armed bandits (MAB); thus, it is capable of leveraging the rich toolbox from BAI-FB systematically and also incorporating unique characteristics of prompt optimization.
Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment
The final prediction of the equivalent entity is derived from the LLM's output.
Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generation
Variational Autoencoders (VAEs) constitute a crucial component of neural symbolic music generation, among which some works have yielded outstanding results and attracted considerable attention.
AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-Preserving Model-based Deep Learning
Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI).
Simultaneous q-Space Sampling Optimization and Reconstruction for Fast and High-fidelity Diffusion Magnetic Resonance Imaging
Diffusion Magnetic Resonance Imaging (dMRI) plays a crucial role in the noninvasive investigation of tissue microstructural properties and structural connectivity in the \textit{in vivo} human brain.
Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
In this paper, we consider federated reinforcement learning for tabular episodic Markov Decision Processes (MDP) where, under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal policy without sharing their raw data.
DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
The rendering view is then manipulated with a novel conditional control module that interprets the camera pose by watching a condition image of a crossed subject from the same view.
Advancing RAN Slicing with Offline Reinforcement Learning
Dynamic radio resource management (RRM) in wireless networks presents significant challenges, particularly in the context of Radio Access Network (RAN) slicing.
A New Approach to Intuitionistic Fuzzy Decision Making Based on Projection Technology and Cosine Similarity Measure
The objective of the presented pa-per is to develop a MADM method and medical diagnosis method under IFS using the projection technology and cosine similarity measure.
Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets
We observe that the performance of offline RL for the RRM problem depends critically on the behavior policy used for data collection, and further propose a novel offline RL solution that leverages heterogeneous datasets collected by different behavior policies.
Learning Discriminative Features for Crowd Counting
Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations.
Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
To this end, we posit a joint model class for tasks and use the notion of $\eta$-bracketing number to quantify its complexity; this number also serves as a general metric to capture the similarity of tasks and thus determines the benefit of multi-task over single-task RL.
DED: Diagnostic Evidence Distillation for acne severity grading on face images
In this study, we propose an acne diagnosis method, Diagnostic Evidence Distillation (DED), that suitably adapts the characteristics of acne diagnosis and can be applied to diagnose under different acne criteria.
Ranked #1 on
Acne Severity Grading
on ACNE04
(Accuracy metric)
A 3M-Hybrid Model for the Restoration of Unique Giant Murals: A Case Study on the Murals of Yongle Palace
Here, a 3M-Hybrid model is proposed to address these challenges.
PMET: Precise Model Editing in a Transformer
To achieve more precise model editing, we analyze hidden states of MHSA and FFN, finding that MHSA encodes certain general knowledge extraction patterns.
Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
In this work, we propose a model-free stage-based Q-learning algorithm and show that it achieves the same sample complexity as the best model-based algorithm, and hence for the first time demonstrate that model-free algorithms can enjoy the same optimality in the $H$ dependence as model-based algorithms.
ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning.
Ranked #1 on
Action Classification
on Kinetics-700-2020
TimePool: Visually Answer "Which and When" Questions On Univariate Time Series
When exploring time series datasets, analysts often pose "which and when" questions.
Tolerating Annotation Displacement in Dense Object Counting via Point Annotation Probability Map
To improve the robustness to annotation displacement, we design an effective transport cost function based on GGD.
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
The general sequential decision-making problem, which includes Markov decision processes (MDPs) and partially observable MDPs (POMDPs) as special cases, aims at maximizing a cumulative reward by making a sequence of decisions based on a history of observations and actions over time.
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
Then, a novel HetPEVI algorithm is proposed, which simultaneously considers the sample uncertainties from a finite number of data samples per data source and the source uncertainties due to a finite number of available data sources.
Differentially Private Wireless Federated Learning Using Orthogonal Sequences
A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels.
The Age of Synthetic Realities: Challenges and Opportunities
Synthetic realities are digital creations or augmentations that are contextually generated through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data to construct new narratives or realities, regardless of the intent to deceive.
Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints
This paper investigates conservative exploration in reinforcement learning where the performance of the learning agent is guaranteed to be above a certain threshold throughout the learning process.
Federated Linear Contextual Bandits with User-level Differential Privacy
This paper studies federated linear contextual bandits under the notion of user-level differential privacy (DP).
Non-stationary Reinforcement Learning under General Function Approximation
To the best of our knowledge, this is the first dynamic regret analysis in non-stationary MDPs with general function approximation.
A Mountain-Shaped Single-Stage Network for Accurate Image Restoration
Image restoration is the task of aiming to obtain a high-quality image from a corrupt input image, such as deblurring and deraining.
Ranked #2 on
Image Deblurring
on HIDE (trained on GOPRO)
Reward Teaching for Federated Multi-armed Bandits
Rigorous analyses demonstrate that when facing clients with UCB1, TWL outperforms TAL in terms of the dependencies on sub-optimality gaps thanks to its adaptive design.
Unicom: Universal and Compact Representation Learning for Image Retrieval
To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes.
Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
Extensive experiments showcase the quality and efficiency of our PBR face skin shader, indicating the effectiveness of our proposed lighting and material representations.
Block-regularized 5$\times$2 Cross-validated McNemar's Test for Comparing Two Classification Algorithms
In contrast, a cross-validation (CV) method repeats the HO method in multiple times and produces a stable estimation.
Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs
In this work, we first provide the first known sample complexity lower bound that holds for any algorithm under low-rank MDPs.
Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction
Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction.
ConMAE: Contour Guided MAE for Unsupervised Vehicle Re-Identification
With the large-scale and dynamic road environment, the paradigm of supervised vehicle re-identification shows limited scalability because of the heavy reliance on large-scale annotated datasets.
Self-Supervised Learning
Unsupervised Vehicle Re-Identification
+1
Determinate Node Selection for Semi-supervised Classification Oriented Graph Convolutional Networks
Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data.
Acne Severity Grading on Face Images via Extraction and Guidance of Prior Knowledge
Acne Vulgaris seriously affects people’s daily life.
Ranked #2 on
Acne Severity Grading
on ACNE04
(Accuracy metric)
Few-shot Learning for Multi-modal Social Media Event Filtering
To the best of our knowledge, this dataset is the first of its kind in event filtering that focuses on protests in multi-modal social media data, with most of the text in Portuguese.
FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection
Our model consists of a hybrid network of convolution and transformer blocks to learn per-AU features and to model AU co-occurrences.
Exploring Graph-aware Multi-View Fusion for Rumor Detection on Social Media
Automatic detecting rumors on social media has become a challenging task.
Span-based joint entity and relation extraction augmented with sequence tagging mechanism
On the one hand, the core architecture enables our model to learn token-level label information via the sequence tagging mechanism and then uses the information in the span-based joint extraction; on the other hand, it establishes a bi-directional information interaction between NER and RE.
Joint Entity and Relation Extraction
named-entity-recognition
+3
Random Orthogonalization for Federated Learning in Massive MIMO Systems
We propose a novel communication design, termed random orthogonalization, for federated learning (FL) in a massive multiple-input and multiple-output (MIMO) wireless system.
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL
In particular, we consider the scenario where a safe baseline policy is known beforehand, and propose a unified Safe reWard-frEe ExploraTion (SWEET) framework.
Unified BERT for Few-shot Natural Language Understanding
Even as pre-trained language models share a semantic encoder, natural language understanding suffers from a diversity of output schemas.
Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
Thus, CNN could locate and estimate crowds accurately in low-density regions, while it is hard to properly perceive the densities in high-density regions.
Provable Benefit of Multitask Representation Learning in Reinforcement Learning
To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask RL for both upstream and downstream tasks.
Knowledge Distillation Meets Open-Set Semi-Supervised Learning
The key idea is that we leverage the teacher's classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions.
Transformer-based Cross-Modal Recipe Embeddings with Large Batch Training
In this paper, we present a cross-modal recipe retrieval framework, Transformer-based Network for Large Batch Training (TNLBT), which is inspired by ACME~(Adversarial Cross-Modal Embedding) and H-T~(Hierarchical Transformer).
Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
Ranked #1 on
Face Recognition
on MFR
On Federated Learning with Energy Harvesting Clients
Catering to the proliferation of Internet of Things devices and distributed machine learning at the edge, we propose an energy harvesting federated learning (EHFL) framework in this paper.
Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis
This paper proposes a Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion.
Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing
However, the improvement is still limited by two issues: 1) It is difficult to perfectly map all faces to a shared feature space.
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization
In this paper, we propose BEACON -- Batched Exploration with Adaptive COmmunicatioN -- that closes this gap.
Federated Linear Contextual Bandits
This paper presents a novel federated linear contextual bandits model, where individual clients face different $K$-armed stochastic bandits coupled through common global parameters.
Explainable Fact-checking through Question Answering
Misleading or false information has been creating chaos in some places around the world.
Scalable Fact-checking with Human-in-the-Loop
Researchers have been investigating automated solutions for fact-checking in a variety of fronts.
Deep-learning-based Hyperspectral imaging through a RGB camera
Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection.
Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting
More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity.
Variational Prototype Learning for Deep Face Recognition
Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.
Multi-Spectrally Constrained Transceiver Design against Signal-Dependent Interference
This paper focuses on the joint synthesis of constant envelope transmit signal and receive filter aimed at optimizing radar performance in signal-dependent interference and spectrally contested-congested environments.
Document Layout Analysis via Dynamic Residual Feature Fusion
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval.
Pre-training strategies and datasets for facial representation learning
Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e. g. face recognition, facial landmark localization etc.)
Ranked #2 on
Facial Expression Recognition (FER)
on BP4D
Robust Kalman filter-based dynamic state estimation of natural gas pipeline networks
To obtain the accurate transient states of the big scale natural gas pipeline networks under the bad data and non-zero mean noises conditions, a robust Kalman filter-based dynamic state estimation method is proposed using the linearized gas pipeline transient flow equations in this paper.
Federated Multi-armed Bandits with Personalization
A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with personalization.
Experimental demonstration of superresolution of partially coherent light sources using parity sorting
Analyses based on quantum metrology have shown that the ability to localize the positions of two incoherent point sources can be significantly enhanced through the use of mode sorting.
Optics Quantum Physics
Magnetic field generation from bubble collisions during first-order phase transition
We study the magnetic fields generation from the cosmological first-order electroweak phase transition.
Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology High Energy Physics - Theory
Knowledge distillation via softmax regression representation learning
We advocate for a method that optimizes the output feature of the penultimate layer of the student network and hence is directly related to representation learning.
OrgMining 2.0: A Novel Framework for Organizational Model Mining from Event Logs
We demonstrate the feasibility of this framework by proposing an approach underpinned by the framework for organizational model discovery, and also conduct experiments on real-life event logs to discover and evaluate organizational models.
DARE: AI-based Diver Action Recognition System using Multi-Channel CNNs for AUV Supervision
With the growth of sensing, control and robotic technologies, autonomous underwater vehicles (AUVs) have become useful assistants to human divers for performing various underwater operations.
Adaptive 3D Face Reconstruction from a Single Image
3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses.
Training Binary Neural Networks with Real-to-Binary Convolutions
This paper shows how to train binary networks to within a few percent points ($\sim 3-5 \%$) of the full precision counterpart.
Knowledge distillation via adaptive instance normalization
To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from the teacher to the student.
Stochastic Linear Contextual Bandits with Diverse Contexts
In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits.
Decentralized Multi-player Multi-armed Bandits with No Collision Information
The decentralized stochastic multi-player multi-armed bandit (MP-MAB) problem, where the collision information is not available to the players, is studied in this paper.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
A Real-Time Deep Network for Crowd Counting
Automatic analysis of highly crowded people has attracted extensive attention from computer vision research.
Cascaded Detail-Preserving Networks for Super-Resolution of Document Images
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results.
Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition
Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements.
Edge-Aware Deep Image Deblurring
In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring.
Fast Video Crowd Counting with a Temporal Aware Network
Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting.
Online Learning with Diverse User Preferences
We aim to show that when the user preferences are sufficiently diverse and each arm can be optimal for certain users, the O(log T) regret incurred by exploring the sub-optimal arms under the standard stochastic MAB setting can be reduced to a constant.
Adaptive Scenario Discovery for Crowd Counting
Crowd counting, i. e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications.
Runtime Analysis for Self-adaptive Mutation Rates
We propose and analyze a self-adaptive version of the $(1,\lambda)$ evolutionary algorithm in which the current mutation rate is part of the individual and thus also subject to mutation.
To learn image super-resolution, use a GAN to learn how to do image degradation first
This paper is on image and face super-resolution.
Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT
Although neural machine translation(NMT) yields promising translation performance, it unfortunately suffers from over- and under-translation is- sues [Tu et al., 2016], of which studies have become research hotspots in NMT.
Optimal Parameter Choices via Precise Black-Box Analysis
It has been observed that some working principles of evolutionary algorithms, in particular, the influence of the parameters, cannot be understood from results on the asymptotic order of the runtime, but only from more precise results.
Cost-Aware Learning and Optimization for Opportunistic Spectrum Access
Our objective is to understand how the costs and reward of the actions would affect the optimal behavior of the user in both offline and online settings, and design the corresponding opportunistic spectrum access strategies to maximize the expected cumulative net reward (i. e., reward-minus-cost).
Attention Regularized Sequence-to-Sequence Learning for E2E NLG Challenge
This paper describes our system used for the end-to-end (E2E) natural language generation (NLG) challenge.
Ranked #8 on
Data-to-Text Generation
on E2E NLG Challenge
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability.
Ranked #1 on
Face Verification
on Labeled Faces in the Wild
(using extra training data)
The (1+$λ$) Evolutionary Algorithm with Self-Adjusting Mutation Rate
We propose a new way to self-adjust the mutation rate in population-based evolutionary algorithms in discrete search spaces.
Adaptive Compressive Tracking via Online Vector Boosting Feature Selection
Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency, but it cannot well deal with the large scale target appearance variations due to its data-independent random projection matrix that results in less discriminative features.
