Search Results for author:
Found 64 papers, 16 papers with code
Facke: a Survey on Generative Models for Face Swapping
In this work, we investigate into the performance of mainstream neural generative models on the very task of swapping faces.
Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Prediction
The previous deep video compression approaches only use the single scale motion compensation strategy and rarely adopt the mode prediction technique from the traditional standards like H. 264/H. 265 for both motion and residual compression.
Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor
In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor (Kapralov and Panigrahy, 2010) for smoothed online convex optimization (SOCO), in which the learner needs to minimize not only the hitting cost but also the switching cost.
Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification
In order to mitigate the impact of large modality discrepancy existing in heterogeneous images, previous methods attempt to apply generative adversarial network (GAN) to generate the modality-consisitent data.
NeuMan: Neural Human Radiance Field from a Single Video
Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences.
Optimal Algorithms for Stochastic Multi-Level Compositional Optimization
To address this limitation, we propose a Stochastic Multi-level Variance Reduction method (SMVR), which achieves the optimal sample complexity of $\mathcal{O}\left(1 / \epsilon^{3}\right)$ to find an $\epsilon$-stationary point for non-convex objectives.
Vertical Federated Edge Learning with Distributed Integrated Sensing and Communication
This letter studies a vertical federated edge learning (FEEL) system for collaborative objects/human motion recognition by exploiting the distributed integrated sensing and communication (ISAC).
LSVC: A Learning-Based Stereo Video Compression Framework
In this work, we propose the first end-to-end optimized framework for compressing automotive stereo videos (i. e., stereo videos from autonomous driving applications) from both left and right views.
Fast Data-Driven Adaptation of Radar Detection via Meta-Learning
One approach is based on transfer learning: it first pre-trains a detector such that it works well on data collected in previously observed environments, and then it adapts the pre-trained detector to the specific current environment.
Online Meta Adaptation for Variable-Rate Learned Image Compression
This work addresses two major issues of end-to-end learned image compression (LIC) based on deep neural networks: variable-rate learning where separate networks are required to generate compressed images with varying qualities, and the train-test mismatch between differentiable approximate quantization and true hard quantization.
A Two-stage Pricing Strategy Considering Learning Effects and Word-of-Mouth
This paper proposes a two-stage pricing strategy for nondurable (such as typical electronics) products, where retail price is cut down at certain time points of the product lifecycle.
Reinforcement Learning for Process Control with Application in Semiconductor Manufacturing
Process control is widely discussed in the manufacturing process, especially for semiconductor manufacturing.
A Survey of Knowledge Enhanced Pre-trained Models
Pre-trained models learn informative representations on large-scale training data through a self-supervised or supervised learning method, which has achieved promising performance in natural language processing (NLP), computer vision (CV), and cross-modal fields after fine-tuning.
Machine learning based iterative learning control for non-repetitive time-varying systems
A machine learning (ML) based nominal model update mechanism, which utilizes the linear regression technique to update the nominal model at each ILC trial only using the current trial information, is proposed for non-repetitive TVSs in order to enhance the ILC performance.
Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.
Substitutional Neural Image Compression
The key idea is to replace the image to be compressed with a substitutional one that outperforms the original one in a desired way.
Multi-agent consensus with heterogeneous time-varying input and communication delays in digraphs
First, for all agents whose state matrix has no eigenvalues with positive real parts, a communication-delay-related observer, which is used to construct the controller, is designed for followers to estimate the leader's state information.
An Iteratively Reweighted Method for Sparse Optimization on Nonconvex $\ell_{p}$ Ball
Specifically, if the current iterate is in the interior of the feasible set, then the weighted $\ell_{1}$ ball is formed by linearizing the $\ell_{p}$ norm at the current iterate.
Multi-hierarchical Convolutional Network for Efficient Remote Photoplethysmograph Signal and Heart Rate Estimation from Face Video Clips
Heart beat rhythm and heart rate (HR) are important physiological parameters of the human body.
COTR: Correspondence Transformer for Matching Across Images
We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other.
Ranked #1 on
Dense Pixel Correspondence Estimation
on ETH3D
Dense Pixel Correspondence Estimation
Optical Flow Estimation
Joint Design of Radar Waveform and Detector via End-to-end Learning with Waveform Constraints
In the second approach, the transmitter and detector are trained simultaneously.
Revisiting Smoothed Online Learning
Moreover, when the hitting cost is both convex and $\lambda$-quadratic growth, we reduce the competitive ratio to $1 + \frac{2}{\sqrt{\lambda}}$ by minimizing the weighted sum of the hitting cost and the switching cost.
TransReID: Transformer-based Object Re-Identification
Extracting robust feature representation is one of the key challenges in object re-identification (ReID).
Ranked #1 on
Person Re-Identification
on Market-1501-C
Predictive Relay Selection: A Cooperative Diversity Scheme Using Deep Learning
In this paper, we propose a novel cooperative multi-relay transmission scheme for mobile terminals to exploit spatial diversity.
Information Theory Signal Processing Information Theory
A Simple Cooperative Diversity Method Based on Deep-Learning-Aided Relay Selection
Opportunistic relay selection (ORS) has been recognized as a simple but efficient method for mobile nodes to achieve cooperative diversity in slow fading channels.
The Road Towards 6G: A Comprehensive Survey
As of today, the fifth generation (5G) mobile communication system has been rolled out in many countries and the number of 5G subscribers already reaches a very large scale.
Implementation of OpenAirInterface-based real-world channel measurement for evaluating wireless transmission algorithms
The results from the measurement are then trained and tested on the channel prediction algorithm.
An Abstracted Survey on 6G: Drivers, Requirements, Efforts, and Enablers
As of today, 5G mobile systems have been already widely rolled out, it is the right time for academia and industry to explore the next generation mobile communication system beyond 5G.
Networking and Internet Architecture
1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
A pipeline for fair comparison of graph neural networks in node classification tasks
We introduce a standard, reproducible benchmark to which the same training settings can be applied for node classification.
DeRF: Decomposed Radiance Fields
Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering.
SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view.
3D Depth Estimation
3D Multi-Person Pose Estimation (absolute)
+2
ArchNet: Data Hiding Model in Distributed Machine Learning System
Specifically, our design can improve the accuracy on MNIST up to 97. 26% compared with RC4. The accuracies on the datasets encrypted by ArchNet are 97. 26%, 84. 15% and 79. 80%, and they are 97. 31%, 82. 31% and 80. 22% on the original datasets, which shows that the encrypted accuracy of ArchNet has the same performance as the base model.
Multi-Domain Learning and Identity Mining for Vehicle Re-Identification
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
Survey of Privacy-Preserving Collaborative Filtering
Collaborative filtering recommendation systems provide recommendations to users based on their own past preferences, as well as those of other users who share similar interests.
Improving Uyghur ASR systems with decoders using morpheme-based language models
The experimental results show that the decoding based on the static and fully composed graph reduces state-of-the-art Word Error Rate (WER) on the clean and noiseless speech test task in THUYG-20 to 14. 24%.
Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification
Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem.
End-to-end Learning of Waveform Generation and Detection for Radar Systems
An end-to-end learning approach is proposed for the joint design of transmitted waveform and detector in a radar system.
Signal Processing
SUDA-Alibaba at MRP 2019: Graph-Based Models with BERT
Our final submission ranks the third on the overall MRP evaluation metric, the first on EDS and the second on UCCA.
Stripe-based and Attribute-aware Network: A Two-Branch Deep Model for Vehicle Re-identification
Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security.
Optimizing Through Learned Errors for Accurate Sports Field Registration
We propose an optimization-based framework to register sports field templates onto broadcast videos.
Adaptive Bayesian SLOPE -- High-dimensional Model Selection with Missing Values
We consider the problem of variable selection in high-dimensional settings with missing observations among the covariates.
Methodology Applications Computation
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds.
A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
The present study collects and evaluates these effective training tricks in person ReID.
Ranked #37 on
Person Re-Identification
on DukeMTMC-reID
Analytical Derivatives for Differentiable Renderer: 3D Pose Estimation by Silhouette Consistency
The experimental results also show that the proposed differentiable renderer is of higher accuracy and efficiency compared with previous method of differentiable renderer.
A Dual-level Model Predictive Control Scheme for Multi-timescale Dynamical Systems--Extended Version
So far, many control algorithms have been developed for singularly perturbed systems.
HLT@SUDA at SemEval-2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing
The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.
Ranked #1 on
UCCA Parsing
on SemEval 2019 Task 1
A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation
The prevalent approaches of Chinese word segmentation task almost rely on the Bi-LSTM neural network.
ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views
Hence, we collect and annotate the ShopSign dataset to advance research in Chinese scene text detection and recognition.
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
In the literature, some effective training tricks are briefly appeared in several papers or source codes.
Ranked #2 on
Person Re-Identification
on UAV-Human
STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification
Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID.
An End-to-End Network for Panoptic Segmentation
Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic.
HLT@SUDA at SemEval 2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing
The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery.
Improve Object Detection by Data Enhancement based on Generative Adversarial Nets
The accuracy of the object detection model depends on whether the anchor boxes effectively trained.
A Novel Self-Intersection Penalty Term for Statistical Body Shape Models and Its Applications in 3D Pose Estimation
To calculate the partial derivatives with respect to the coordinates of the vertices, we employed detection rays to divide vertices of statistical body shape models into different groups depending on whether the vertex is in the region of self-intersection.
Linearized Multi-Sampling for Differentiable Image Transformation
We propose a novel image sampling method for differentiable image transformation in deep neural networks.
SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.
Distributing and Obfuscating Firewalls via Oblivious Bloom Filter Evaluation
In this paper, we develop an innovative distributed architecture to obliviously manage and evaluate firewalls to prevent both insider and external attacks oriented to the firewalls.
Cryptography and Security
SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously.
DFNet: Semantic Segmentation on Panoramic Images with Dynamic Loss Weights and Residual Fusion Block
We propose the DFNet and make two main contributions, one is dynamic loss weights, and the other is residual fusion block (RFB).
Stochastic Approximation EM for Logistic Regression with Missing Values
We propose a complete approach, including the estimation of parameters and their variance, derivation of confidence intervals, a model selection procedure, and a method for prediction on test sets with missing values.
Methodology
VH-HFCN based Parking Slot and Lane Markings Segmentation on Panoramic Surround View
At the same time, we proposed a highly fused convolutional network (HFCN) based segmentation method for parking slot and lane markings based on the PSV dataset.
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.
Ranked #1 on
Person Re-Identification
on CUHK-SYSU
A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets
Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area.
