Search Results for author:
Found 72 papers, 12 papers with code
SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses.
Fast Estimations of Hitting Time of Elitist Evolutionary Algorithms from Fitness Levels
In this method, an EA is modeled as a Markov chain on a digraph.
BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval
Dance and music are closely related forms of expression, with mutual retrieval between dance videos and music being a fundamental task in various fields like education, art, and sports.
STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation
Scene Graph Generation is a critical enabler of environmental comprehension for autonomous robotic systems.
Drift Analysis with Fitness Levels for Elitist Evolutionary Algorithms
An open question regarding the fitness level method is what are the tightest lower and upper time bounds that can be constructed based on transition probabilities between fitness levels.
SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
To enhance the visual accuracy of generated lip movement while reducing the dependence on labeled data, we propose a novel framework SelfTalk, by involving self-supervision in a cross-modals network system to learn 3D talking faces.
Backdoor Attacks with Input-unique Triggers in NLP
Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels.
SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation
In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image.
FuRPE: Learning Full-body Reconstruction from Part Experts
These novel elements of FuRPE not only serve to further refine the model but also to reduce potential biases that may arise from inaccuracies in pseudo labels, thereby optimizing the network's training process and enhancing the robustness of the model.
GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Large-scale Place Recognition
Large-scale place recognition is a fundamental but challenging task, which plays an increasingly important role in autonomous driving and robotics.
Human Pose Driven Object Effects Recommendation
In this paper, we research the new topic of object effects recommendation in micro-video platforms, which is a challenging but important task for many practical applications such as advertisement insertion.
MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment
In specific, we split the point clouds into sub-models to represent local geometry distortions such as point shift and down-sampling.
Ranked #1 on
Point Cloud Quality Assessment
on SJTU-PCQA
Calcium oscillation on homogeneous and heterogeneous networks of ryanodine receptor
The synchronization of RyRs is found important to generate a global calcium oscillation.
Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers
However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the domain gap.
Deep Neural Network for Blind Visual Quality Assessment of 4K Content
In this paper, we propose a deep learning-based BIQA model for 4K content, which on one hand can recognize true and pseudo 4K content and on the other hand can evaluate their perceptual visual quality.
Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important.
Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image
Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications.
BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing
Extensive experiments on various GNN models and large graph datasets show that BGL significantly outperforms existing GNN training systems by 20. 68x on average.
ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation
ACR-Pose consists of a Reconstructor and a Discriminator.
Influence of Binomial Crossover on Approximation Error of Evolutionary Algorithms
Although differential evolution (DE) algorithms perform well on a large variety of complicated optimization problems, only a few theoretical studies are focused on the working principle of DE algorithms.
An MRC Framework for Semantic Role Labeling
We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense.
Ranked #1 on
Semantic Role Labeling
on CoNLL 2005
RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network
Third, we apply these kernels to previous point cloud features to generate new features, which is the well-known SO(3) mapping process.
Improving Entity Linking through Semantic Reinforced Entity Embeddings
We propose a simple yet effective method, FGS2EE, to inject fine-grained semantic information into entity embeddings to reduce the distinctiveness and facilitate the learning of contextual commonality.
Nonlinear signal transduction network with multistate
At short time scale, the second open state is essential to reproduce the quasi-bistable regime, which emerges at a critical strength of connection for all three states involved in the fast processes and disappears at another critical point.
Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview
Therefore, this study presents a comprehensive review of recent progress in object pose detection and tracking that belongs to the deep learning technical route.
SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM).
Ranked #2 on
3D Place Recognition
on Oxford RobotCar Dataset
Functional annotation of creeping bentgrass protein sequences based on convolutional neural network
Conclusions: The prediction model based on convolutional neural network was successfully applied to select good candidates of the proteins with functions relevant to the ISR mechanism from the protein sequences which cannot be annotated by database alignment.
Revisiting Local Descriptor for Improved Few-Shot Classification
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images.
Significant Inverse Magnetocaloric Effect induced by Quantum Criticality
Strong fluctuations in the low-$T$ quantum critical regime can give rise to a large thermal entropy change and thus significant cooling effect when approaching the QCP.
Strongly Correlated Electrons
$P_{cs}(4459)$ and other possible molecular states from $Ξ_{c}^{(*)}\bar{D}^{(*)}$ and $Ξ'_c\bar{D}^{(*)}$ interactions
Two states with spin parities $1/2^-$ and $3/2^-$ are predicted near the $\Xi'_c\bar{D}$, $\Xi_c\bar{D}$, and $\Xi_c^*\bar{D}$ thresholds, respectively.
High Energy Physics - Phenomenology
Dirac semimetal PdTe2 temperature-dependent quasiparticle dynamics and electron-phonon coupling
Two distinct carrier and coherent phonons relaxation processes were identified in the 5 K - 300 K range.
Materials Science Superconductivity
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
Unsupervised Summarization by Jointly Extracting Sentences and Keywords
We present RepRank, an unsupervised graph-based ranking model for extractive multi-document summarization in which the similarity between words, sentences, and word-to-sentence can be estimated by the distances between their vector representations in a unified vector space.
Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference
One of the major challenges in coreference resolution is how to make use of entity-level features defined over clusters of mentions rather than mention pairs.
Possible molecular states from the $NΔ$ interaction
It has a relatively small binding energy compared with the $d^*(2380)$ and a width close to the width of the $\Delta$ baryon, which suggests that it may be a dibaryon in a molecular state picture.
Nuclear Theory High Energy Physics - Phenomenology
DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors
Recently, two attention methods are proposed via combining with Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) network, which can capture the dependencies of sensing signals in both spatial and temporal domains simultaneously.
Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices
For deep learning, improvements in performance have to heavily rely on increasing model size or capacity to scale to larger and larger datasets, which inevitably leads to the increase of operations.
Memory-Augmented Relation Network for Few-Shot Learning
Metric-based few-shot learning methods concentrate on learning transferable feature embedding that generalizes well from seen categories to unseen categories under the supervision of limited number of labelled instances.
Layer-wise training convolutional neural networks with smaller filters for human activity recognition using wearable sensors
A set of lower-dimensional filters is used as Lego bricks to be stacked for conventional filters, which does not rely on any special network structure.
Incorporating Multiple Cluster Centers for Multi-Label Learning
In this article, we propose to leverage the data augmentation technique to improve the performance of multi-label learning.
Sequential Weakly Labeled Multi-Activity Localization and Recognition on Wearable Sensors using Recurrent Attention Networks
Recently, several attention mechanisms are proposed to handle the weakly labeled human activity data, which do not require accurate data annotation.
Exploitation and Exploration Analysis of Elitist Evolutionary Algorithms: A Case Study
Known as two cornerstones of problem solving by search, exploitation and exploration are extensively discussed for implementation and application of evolutionary algorithms (EAs).
Conditionally Learn to Pay Attention for Sequential Visual Task
Sequential visual task usually requires to pay attention to its current interested object conditional on its previous observations.
Unlimited Budget Analysis of Randomised Search Heuristics
Run time and solution quality are two popular measures of the performance of these algorithms.
Error Analysis of Elitist Randomized Search Heuristics
When globally optimal solutions of complicated optimization problems cannot be located by evolutionary algorithms (EAs) in polynomial expected running time, the hitting time/running time analysis is not flexible enough to accommodate the requirement of theoretical study, because sometimes we have no idea on what approximation ratio is available in polynomial expected running time.
Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process.
Average Convergence Rate of Evolutionary Algorithms II: Continuous Optimization
But for hard functions such as the deceptive function, the ACR of both the (1+1) adaptive random univariate search and evolutionary programming is exponential.
A Theoretical Framework of Approximation Error Analysis of Evolutionary Algorithms
In the empirical study of evolutionary algorithms, the solution quality is evaluated by either the fitness value or approximation error.
A Blended Deep Learning Approach for Predicting User Intended Actions
In this work, we focus on pre- dicting attrition, which is one of typical user intended actions.
Multiobjective Optimization Differential Evolution Enhanced with Principle Component Analysis for Constrained Optimization
PMODE and HECO-PDE are compared with the algorithms from the IEEE CEC 2018 competition and another recent MOEA for constrained optimisation.
An Analytic Expression of Relative Approximation Error for a Class of Evolutionary Algorithms
In this paper, an analytic expression for calculating the relative approximation error is presented for a class of evolutionary algorithms, that is, (1+1) strictly elitist evolution algorithms.
Multi-objective Differential Evolution with Helper Functions for Constrained Optimization
This paper proposes a new multi-objective method for solving constrained optimization problems.
Average Convergence Rate of Evolutionary Algorithms
The calculation of the average convergence rate is very simple and it is applicable for most evolutionary algorithms on both continuous and discrete optimization.
Analysis of Solution Quality of a Multiobjective Optimization-based Evolutionary Algorithm for Knapsack Problem
Multi-objective optimisation is regarded as one of the most promising ways for dealing with constrained optimisation problems in evolutionary optimisation.
Adaptive Stochastic Gradient Descent on the Grassmannian for Robust Low-Rank Subspace Recovery and Clustering
In this paper, we present GASG21 (Grassmannian Adaptive Stochastic Gradient for $L_{2, 1}$ norm minimization), an adaptive stochastic gradient algorithm to robustly recover the low-rank subspace from a large matrix.
Performance Analysis on Evolutionary Algorithms for the Minimum Label Spanning Tree Problem
We also show that GSEMO achieves a $(2ln(n))$-approximation ratio for the MLST problem in expected polynomial time of $n$ and $k$.
A Theoretical Assessment of Solution Quality in Evolutionary Algorithms for the Knapsack Problem
Nonetheless, few rigorous investigations address the quality of solutions that evolutionary algorithms may produce for the knapsack problem.
A Novel Genetic Algorithm using Helper Objectives for the 0-1 Knapsack Problem
On the other hand, genetic algorithms are well suited for solving the knapsack problem and they find reasonably good solutions quickly.
A Unified Markov Chain Approach to Analysing Randomised Search Heuristics
The convergence, convergence rate and expected hitting time play fundamental roles in the analysis of randomised search heuristics.
Average Drift Analysis and Population Scalability
Population scalability is the ratio of the expected hitting time between a benchmark algorithm and an algorithm using a larger population size.
Iterative Grassmannian Optimization for Robust Image Alignment
t-GRASTA iteratively performs incremental gradient descent constrained to the Grassmann manifold of subspaces in order to simultaneously estimate a decomposition of a collection of images into a low-rank subspace, a sparse part of occlusions and foreground objects, and a transformation such as rotation or translation of the image.
A Further Generalization of the Finite-Population Geiringer-like Theorem for POMDPs to Allow Recombination Over Arbitrary Set Covers
Recently a finite population version of Geiringer theorem with nonhomologous recombination has been adopted to the setting of Monte-Carlo tree search to cope with randomness and incomplete information by exploiting the entrinsic similarities within the state space of the problem.
Geiringer Theorems: From Population Genetics to Computational Intelligence, Memory Evolutive Systems and Hebbian Learning
The classical Geiringer theorem addresses the limiting frequency of occurrence of various alleles after repeated application of crossover.
Combining Drift Analysis and Generalized Schema Theory to Design Efficient Hybrid and/or Mixed Strategy EAs
Hybrid and mixed strategy EAs have become rather popular for tackling various complex and NP-hard optimization problems.
Mixed Strategy May Outperform Pure Strategy: An Initial Study
In mixed strategy meta-heuristics, each time one search strategy is chosen from a strategy pool with a probability and then is applied.
On the Easiest and Hardest Fitness Functions
The aim of this paper is to answer the following research questions: Given a fitness function class, which functions are the easiest with respect to an evolutionary algorithm?
A Polynomial Time Approximation Scheme for a Single Machine Scheduling Problem Using a Hybrid Evolutionary Algorithm
Nowadays hybrid evolutionary algorithms, i. e, heuristic search algorithms combining several mutation operators some of which are meant to implement stochastically a well known technique designed for the specific problem in question while some others playing the role of random search, have become rather popular for tackling various NP-hard optimization problems.
Pure Strategy or Mixed Strategy?
Mixed strategy EAs aim to integrate several mutation operators into a single algorithm.
Online Robust Subspace Tracking from Partial Information
This paper presents GRASTA (Grassmannian Robust Adaptive Subspace Tracking Algorithm), an efficient and robust online algorithm for tracking subspaces from highly incomplete information.
Novel Analysis of Population Scalability in Evolutionary Algorithms
(1) We demonstrate rigorously that for elitist EAs with identical global mutation, using a lager population size always increases the average rate of convergence to the optimal set; and yet, sometimes, the expected number of generations needed to find an optimal solution (measured by either the maximal value or the average value) may increase, rather than decrease.
