Search Results for author:
Found 51 papers, 12 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.
Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL
We then particularize the SWEET framework to the tabular and the low-rank MDP settings, and develop algorithms coined Tabular-SWEET and Low-rank-SWEET, respectively.
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 crowd accurately in low-density regions, while it is hard to properly perceive density 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.
Duck swarm algorithm: a novel swarm intelligence algorithm
A swarm intelligence-based optimization algorithm, named Duck Swarm Algorithm (DSA), is proposed in this paper.
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.
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.
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 #1 on
Arousal Estimation
on AffectNet
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.
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
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
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 #7 on
Data-to-Text Generation
on E2E NLG Challenge
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.
