Search Results for author:
Found 256 papers, 89 papers with code
CORN: Correlation-driven Non parametric Learning Approach for Portfolio Selection
Machine learning techniques have been adopted to select portfolios from financial markets in some emerging intelligent business applications.
PAMR: Passive aggressive mean reversion strategy for portfolio selection
This article proposes a novel online portfolio selection strategy named “Passive Aggressive Mean Reversion” (PAMR).
On-Line Portfolio Selection with Moving Average Reversion
Online portfolio selection has attracted increasing interests in machine learning and AI communities recently.
An Adaptive Successive Cancellation List Decoder for Polar Codes with Cyclic Redundancy Check
In this letter, we propose an adaptive SC (Successive Cancellation)-List decoder for polar codes with CRC.
Information Theory Information Theory
Online Portfolio Selection: A Survey
This article aims to provide a timely and comprehensive survey for both machine learning and data mining researchers in academia and quantitative portfolio managers in the financial industry to help them understand the state-of-the-art and facilitate their research and practical applications.
Robust Median Reversion Strategy for On-Line Portfolio Selection
Online portfolio selection has been attracting increasing interests from artificial intelligence community in recent decades.
Stochastic Patching Process
Due to constraints of partition strategy, existing models may cause unnecessary dissections in sparse regions when fitting data in dense regions.
Improving Efficiency of SVM k-fold Cross-validation by Alpha Seeding
The k-fold cross-validation is commonly used to evaluate the effectiveness of SVMs with the selected hyper-parameters.
Mechanism Design in Social Networks
The challenge to the seller is to design a mechanism to incentivize the buyers, who are aware of the auction, to further propagate the information to their neighbors so that more buyers will participate in the auction and hence, the seller will be able to make a higher revenue.
Computer Science and Game Theory
The Power of Waiting for More than One Response in Minimizing the Age-of-Information
Interestingly, we find that under this new Pull model, replication schemes capture a novel tradeoff between different levels of information freshness and different response times across the servers, which can be exploited to minimize the expected AoI at the user's side.
Networking and Internet Architecture
Improved Consistent Weighted Sampling Revisited
Min-Hash is a popular technique for efficiently estimating the Jaccard similarity of binary sets.
Data Structures and Algorithms
A multi-branch convolutional neural network for detecting double JPEG compression
In this paper, we present a CNN solution by using raw DCT (discrete cosine transformation) coefficients from JPEG images as input.
Model-Free Information Extraction in Enriched Nonlinear Phase-Space
We benchmark the astonishing accuracy of our method on three diverse and challenging problems in: biology, medicine, and engineering.
Transition-Based Chinese AMR Parsing
This paper presents the first AMR parser built on the Chinese AMR bank.
Robust Fuzzy-Learning For Partially Overlapping Channels Allocation In UAV Communication Networks
This allows the system to achieve a smoother and more robust performance by optimizing in an alternate space.
Scene Learning: Deep Convolutional Networks For Wind Power Prediction by Embedding Turbines into Grid Space
There have been a lot of researches based on the time series of the wind power or speed, but In fact, these time series cannot express the temporal and spatial changes of wind, which fundamentally hinders the advance of wind power prediction.
Customer Sharing in Economic Networks with Costs
To tackle this problem, we develop a novel mechanism called customer sharing mechanism (CSM) which incentivizes all sellers to share each other's sale information to their private customer groups.
A Study of Deep Feature Fusion based Methods for Classifying Multi-lead ECG
An automatic classification method has been studied to effectively detect and recognize Electrocardiogram (ECG).
Detection of Deep Network Generated Images Using Disparities in Color Components
In this paper, we address the problem of detecting deep network generated (DNG) images by analyzing the disparities in color components between real scene images and DNG images.
Multimedia
Predicting Lung Nodule Malignancies by Combining Deep Convolutional Neural Network and Handcrafted Features
The fusion algorithm takes full advantage of the handcrafted features and the highest level CNN features learned at the output layer.
A Review for Weighted MinHash Algorithms
In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme).
Data Structures and Algorithms
Affinity Derivation and Graph Merge for Instance Segmentation
We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance.
High-dimensional Metric Combining for Non-coherent Molecular Signal Detection
If the channel is unknown, we cannot easily achieve traditional coherent channel estimation and cancellation, and the impact of ISI will be more severe.
Sequential Bayesian Detection of Spike Activities from Fluorescence Observations
Extracting and detecting spike activities from the fluorescence observations is an important step in understanding how neuron systems work.
Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping
Different from existing methods, the proposed method disentangles the attributes of an object into ``shape'' and ``appearance'' which are modeled separately by the mixture weights and the mixture components.
Learn a Prior for RHEA for Better Online Planning
In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network.
Selling Multiple Items via Social Networks
We consider a market where a seller sells multiple units of a commodity in a social network.
Rectangular Bounding Process
Stochastic partition models divide a multi-dimensional space into a number of rectangular regions, such that the data within each region exhibit certain types of homogeneity.
Binary Space Partitioning Forests
The Binary Space Partitioning~(BSP)-Tree process is proposed to produce flexible 2-D partition structures which are originally used as a Bayesian nonparametric prior for relational modelling.
The Binary Space Partitioning-Tree Process
The Mondrian process represents an elegant and powerful approach for space partition modelling.
Text Guided Person Image Synthesis
This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.
Question Guided Modular Routing Networks for Visual Question Answering
Particularly, The QGMRN is composed of visual, textual and routing network.
Diffusion and Auction on Graphs
Auction is the common paradigm for resource allocation which is a fundamental problem in human society.
DA-RefineNet:A Dual Input Whole Slide Image Segmentation Algorithm Based on Attention
Automatic medical image segmentation has wide applications for disease diagnosing.
Spatiotemporal graph routing for skeleton-based action recognition
With the representation effectiveness, skeleton-based human action recognition has received considerable research attention, and has a wide range of real applications.
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short).
Ranked #1 on
Visual Question Answering (VQA)
on VCR (Q-A) dev
Scalable Deep Generative Relational Models with High-Order Node Dependence
We propose a probabilistic framework for modelling and exploring the latent structure of relational data.
Ultra-Fast Accurate AoA Estimation via Automotive Massive-MIMO Radar
Massive multiple-input multiple-output (MIMO) radar, enabled by millimeter-wave virtual MIMO techniques, provides great promises to the high-resolution automotive sensing and target detection in unmanned ground/aerial vehicles (UGA/UAV).
Scalable Deep Generative Relational Model with High-Order Node Dependence
In this work, we propose a probabilistic framework for relational data modelling and latent structure exploring.
Reinforcement learning for bandwidth estimation and congestion control in real-time communications
Bandwidth estimation and congestion control for real-time communications (i. e., audio and video conferencing) remains a difficult problem, despite many years of research.
Waiting but not Aging: Optimizing Information Freshness Under the Pull Model
Interestingly, we find that under this new Pull model, replication schemes capture a novel tradeoff between different values of the AoI across the servers (due to the random updating processes) and different response times across the servers, which can be exploited to minimize the expected AoI at the user's side.
Outlier Detection Ensemble with Embedded Feature Selection
Existing methods usually perform feature selection and outlier scoring separately, which would select feature subsets that may not optimally serve for outlier detection, leading to unsatisfying performance.
Adjustable robust optimization in enabling optimal day-ahead economic dispatch of CCHP-MG considering uncertainties of wind-solar power and electric vehicle
At present, electric vehicles (EVs), small-scale wind power, and solar power have been increasingly integrated into modern power system via the combined cooling heating and power based microgrid (CCHP-MG).
Recurrent Dirichlet Belief Networks for Interpretable Dynamic Relational Data Modelling
In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data.
Smoothing Graphons for Modelling Exchangeable Relational Data
We initially propose the Integrated Smoothing Graphon (ISG) which introduces one smoothing parameter to the SBM graphon to generate continuous relational intensity values.
Bayesian Nonparametric Space Partitions: A Survey
Bayesian nonparametric space partition (BNSP) models provide a variety of strategies for partitioning a $D$-dimensional space into a set of blocks.
Online Binary Space Partitioning Forests
The Binary Space Partitioning-Tree~(BSP-Tree) process was recently proposed as an efficient strategy for space partitioning tasks.
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning
This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs.
Event-based Robotic Grasping Detection with Neuromorphic Vision Sensor and Event-Stream Dataset
Based on the Event-Stream dataset, we develop a deep neural network for grasping detection which consider the angle learning problem as classification instead of regression.
Integration of Automatic Sentence Segmentation and Lexical Analysis of Ancient Chinese based on BiLSTM-CRF Model
The basic tasks of ancient Chinese information processing include automatic sentence segmentation, word segmentation, part-of-speech tagging and named entity recognition.
Construct a Sense-Frame Aligned Predicate Lexicon for Chinese AMR Corpus
The existing lexicons blur senses and frames of predicates, which needs to be refined to meet the tasks like word sense disambiguation and event extraction.
NodeSketch: Highly-Efficient Graph Embeddings via Recursive Sketching
Embeddings have become a key paradigm to learn graph represen-tations and facilitate downstream graph analysis tasks.
Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation
Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood.
Graph Layer Security: Encrypting Information via Common Networked Physics
Leveraging this, we propose for the first time, graph layer security (GLS), by exploiting the dependency in physical dynamics among network nodes for information encryption and decryption.
Dual-stream Maximum Self-attention Multi-instance Learning
Recently, MIL models fully parameterized by neural networks have become popular due to the high flexibility and superior performance.
W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network
To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation.
Epoch-evolving Gaussian Process Guided Learning
In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution.
Multitask Non-Autoregressive Model for Human Motion Prediction
Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem.
A New Perspective on Stabilizing GANs training: Direct Adversarial Training
Quite a number of methods have been proposed to stabilize the training of GANs, the focuses of which were respectively put on the loss functions, regularization and normalization technologies, training algorithms, and model architectures.
A Systematic Survey of Regularization and Normalization in GANs
Although a handful number of regularization and normalization methods have been proposed for GANs, to the best of our knowledge, there exists no comprehensive survey that primarily focuses on objectives and development of these methods, apart from some in-comprehensive and limited scope studies.
Improving Resistance to Adversarial Deformations by Regularizing Gradients
Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications.
An Automatic Cost Learning Framework for Image Steganography Using Deep Reinforcement Learning
In SPAR-RL, an agent utilizes a policy network which decomposes the embedding process into pixel-wise actions and aims at maximizing the total rewards from a simulated steganalytic environment, while the environment employs an environment network for pixel-wise reward assignment.
Deformable DETR: Deformable Transformers for End-to-End Object Detection
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance.
Ranked #6 on
2D Object Detection
on SARDet-100K
POND: Pessimistic-Optimistic oNline Dispatching
This paper considers constrained online dispatching with unknown arrival, reward and constraint distributions.
Performance Analysis and Optimization for the MAC Protocol in UAV-based IoT Network
A modified three-dimensional Markov chain model adopting the quitting probability and cluster division is developed for the performance analysis.
Information Theory Information Theory
MRP 2020: The Second Shared Task on Cross-Framework and Cross-Lingual Meaning Representation Parsing
Extending a similar setup from the previous year, five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the English training and evaluation data for the task, packaged in a uniform graph abstraction and serialization; for four of these representation frameworks, additional training and evaluation data was provided for one additional language per framework.
On Performance of Multiscale Sparse Fast Fourier Transform Algorithm
The sFFT algorithms decrease the runtime and sampling complexity by taking advantage of the signal inherent characteristics that a large number of signals are sparse in the frequency domain(e. g., sensors, video data, audio, medical image, etc.).
On Performance of Sparse Fast Fourier Transform Algorithms Using the Aliasing Filter
In the second part, we make two categories of experiments for computing the signals of different SNR, different N, different K by a standard testing platform and record the run time, percentage of the signal sampled and L0, L1, L2 error both in the exactly sparse case and general sparse case.
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning
We propose a MIL-based method for WSI classification and tumor detection that does not require localized annotations.
Boosting CNN-based primary quantization matrix estimation of double JPEG images via a classification-like architecture
The method is based on a Convolutional Neural Network (CNN) that is trained to solve the estimation as a standard regression problem.
Model-free Neural Counterfactual Regret Minimization with Bootstrap Learning
Experimental results show that Neural ReCFR-B is competitive with the state-of-the-art neural CFR algorithms at a much lower training cost.
Incentive Mechanism Design for ROI-constrained Auto-bidding
Auto-bidding plays an important role in online advertising and has become a crucial tool for advertisers and advertising platforms to meet their performance objectives and optimize the efficiency of ad delivery.
Computer Science and Game Theory
DR 21 South Filament: a Parsec-sized Dense Gas Accretion Flow onto the DR 21 Massive Young Cluster
DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex.
Astrophysics of Galaxies
Empirical Evaluation of Typical Sparse Fast Fourier Transform Algorithms
Computing the Sparse Fast Fourier Transform(sFFT) of a K-sparse signal of size N has emerged as a critical topic for a long time.
Efficient Learning-based Scheduling for Information Freshness in Wireless Networks
Here, UCB estimates balance the tradeoff between exploration and exploitation in learning and are critical for yielding a small cumulative regret.
Self-supervised Visual-LiDAR Odometry with Flip Consistency
To this end, we design a self-supervised visual-lidar odometry (Self-VLO) framework.
Image Steganography based on Iteratively Adversarial Samples of A Synchronized-directions Sub-image
In this paper, we present a novel steganography scheme denoted as ITE-SYN (based on ITEratively adversarial perturbations onto a SYNchronized-directions sub-image), by which security data is embedded with synchronizing modification directions to enhance security and then iteratively increased perturbations are added onto a sub-image to reduce loss with cover class label of the target CNN classifier.
Infant Cry Classification with Graph Convolutional Networks
We propose an approach of graph convolutional networks for robust infant cry classification.
A Generic Object Re-identification System for Short Videos
Short video applications like TikTok and Kwai have been a great hit recently.
An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints
Thus, the overall computational complexity of our algorithm is similar to that of the linear UCB for unconstrained stochastic linear bandits.
Serial-parallel Multi-Scale Feature Fusion for Anatomy-Oriented Hand Joint Detection
Accurate hand joints detection from images is a fundamental topic which is essential for many applications in computer vision and human computer interaction.
PENet: Towards Precise and Efficient Image Guided Depth Completion
More specifically, one branch inputs a color image and a sparse depth map to predict a dense depth map.
Ranked #3 on
Depth Completion
on KITTI Depth Completion
Knowledge-Guided Object Discovery with Acquired Deep Impressions
The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation.
Exploring The Effect of High-frequency Components in GANs Training
Generative Adversarial Networks (GANs) have the ability to generate images that are visually indistinguishable from real images.
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
In this paper we aim to solve the latter one by proposing a deep latent variable model, in which multiple Gaussian processes are employed as priors of latent variables to separately learn underlying abstract concepts from RPMs; thus the proposed model is interpretable in terms of concept-specific latent variables.
MCTSteg: A Monte Carlo Tree Search-based Reinforcement Learning Framework for Universal Non-additive Steganography
Recent research has shown that non-additive image steganographic frameworks effectively improve security performance through adjusting distortion distribution.
Non-contact PPG Signal and Heart Rate Estimation with Multi-hierarchical Convolutional Network
Heartbeat rhythm and heart rate (HR) are important physiological parameters of the human body.
Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning
Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks.
Ranked #1 on
SMAC+
on Off_Superhard_parallel
Sparse online relative similarity learning
This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity.
Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics
The performance of deep reinforcement learning methods prone to degenerate when applied to environments with non-stationary dynamics.
Improving Cost Learning for JPEG Steganography by Exploiting JPEG Domain Knowledge
To address the issue, in this paper we extend an existing automatic cost learning scheme to JPEG, where the proposed scheme called JEC-RL (JPEG Embedding Cost with Reinforcement Learning) is explicitly designed to tailor the JPEG DCT structure.
Hashing-Accelerated Graph Neural Networks for Link Prediction
Networks are ubiquitous in the real world.
Bilateral Personalized Dialogue Generation with Contrastive Learning
Generating personalized responses is one of the major challenges in natural human-robot interaction.
Scene Text Telescope: Text-Focused Scene Image Super-Resolution
Image super-resolution, which is often regarded as a preprocessing procedure of scene text recognition, aims to recover the realistic features from a low-resolution text image.
Image Super-Resolution
Optical Character Recognition (OCR)
+2
Zero-Shot Chinese Character Recognition with Stroke-Level Decomposition
Inspired by the fact that humans can generalize to know how to write characters unseen before if they have learned stroke orders of some characters, we propose a stroke-based method by decomposing each character into a sequence of strokes, which are the most basic units of Chinese characters.
Self-Adversarial Training incorporating Forgery Attention for Image Forgery Localization
In this paper, we propose a self-adversarial training strategy and a reliable coarse-to-fine network that utilizes a self-attention mechanism to localize forged regions in forgery images.
Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing Images
In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations.
BezierSeg: Parametric Shape Representation for Fast Object Segmentation in Medical Images
Pixel-wise classification is a popular approach to segmenting the region of interest.
DuCN: Dual-children Network for Medical Diagnosis and Similar Case Recommendation towards COVID-19
Our proposed network contains two stages: the first one is a lung region segmentation step and is used to exclude irrelevant factors, and the second is a detection and recommendation stage.
More but Correct: Generating Diversified and Entity-revised Medical Response
Medical Dialogue Generation (MDG) is intended to build a medical dialogue system for intelligent consultation, which can communicate with patients in real-time, thereby improving the efficiency of clinical diagnosis with broad application prospects.
SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning
Ten learning-based surgical tasks are built in the platform, which are common in the real autonomous surgical execution.
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.
Deep Contextual Video Compression
In this paper, we propose a deep contextual video compression framework to enable a paradigm shift from predictive coding to conditional coding.
Stereo Dense Scene Reconstruction and Accurate Localization for Learning-Based Navigation of Laparoscope in Minimally Invasive Surgery
Then, we develop a dense visual reconstruction algorithm to represent the scene by surfels, estimate the laparoscope poses and fuse the depth maps into a unified reference coordinate for tissue reconstruction.
Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent
Follow-the-Regularized-Lead (FTRL) and Online Mirror Descent (OMD) are regret minimization algorithms for Online Convex Optimization (OCO), they are mathematically elegant but less practical in solving Extensive-Form Games (EFGs).
RelationRS: Relationship Representation Network for Object Detection in Aerial Images
To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution.
Enhancing Backdoor Attacks with Multi-Level MMD Regularization
Then, ML-MMDR, a difference reduction method that adds multi-level MMD regularization into the loss, is proposed, and its effectiveness is testified on three typical difference-based defense methods.
Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
The most common solution for this is to compute an approximate risk by replacing the 0-1 loss with a surrogate one.
Temporal Context Mining for Learned Video Compression
From the stored propagated features, we propose to learn multi-scale temporal contexts, and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder.
SimCLAD: A Simple Framework for Contrastive Learning of Acronym Disambiguation
In this paper, we propose a Simple framework for Contrastive Learning of Acronym Disambiguation (SimCLAD) method to better understand the acronym meanings.
PSG: Prompt-based Sequence Generation for Acronym Extraction
In this paper, we propose a Prompt-based Sequence Generation (PSG) method for the acronym extraction task.
Continuous-time edge modelling using non-parametric point processes
The mutually-exciting Hawkes process (ME-HP) is a natural choice to model reciprocity, which is an important attribute of continuous-time edge (dyadic) data.
MT-TransUNet: Mediating Multi-Task Tokens in Transformers for Skin Lesion Segmentation and Classification
However, these approaches formulated skin cancer diagnosis as a simple classification task, dismissing the potential benefit from lesion segmentation.
Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
When observing a visual scene that contains multiple objects from multiple viewpoints, humans are able to perceive the scene in a compositional way from each viewpoint, while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold.
ADBCMM : Acronym Disambiguation by Building Counterfactuals and Multilingual Mixing
To address the above issue, this paper proposes an new method for acronym disambiguation, named as ADBCMM, which can significantly improve the performance of low-resource languages by building counterfactuals and multilingual mixing.
Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution
However, the recognition of low-resolution scene text images remains a challenge.
Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization
Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators.
Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
The experimental results indicate that the performance of baselines on CTR datasets is not as good as that on English datasets due to the characteristics of Chinese texts that are quite different from the Latin alphabet.
PROMPT: Learning Dynamic Resource Allocation Policies for Network Applications
A growing number of service providers are exploring methods to improve server utilization and reduce power consumption by co-scheduling high-priority latency-critical workloads with best-effort workloads.
A Higher-Order Semantic Dependency Parser
Higher-order features bring significant accuracy gains in semantic dependency parsing.
Compositional Scene Representation Learning via Reconstruction: A Survey
In this survey, we first outline the current progress on reconstruction-based compositional scene representation learning with deep neural networks, including development history and categorizations of existing methods from the perspectives of the modeling of visual scenes and the inference of scene representations; then provide benchmarks, including an open source toolbox to reproduce the benchmark experiments, of representative methods that consider the most extensively studied problem setting and form the foundation for other methods; and finally discuss the limitations of existing methods and future directions of this research topic.
Remote blood pressure measurement via spatiotemporal mapping of a short-time facial video
Blood pressure (BP) monitoring is vital in daily healthcare, especially for cardiovascular diseases.
Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video
However, due to the weak correlations and huge gaps of the semantic features between the textual question and visual answer, existing methods adopting visual span predictor perform poorly in the TAGV task.
Multi-Unit Diffusion Auctions with Intermediaries
This paper studies multi-unit auctions powered by intermediaries, where each intermediary owns a private set of unit-demand buyers and all intermediaries are networked with each other.
Neural Compression-Based Feature Learning for Video Restoration
The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the current frame.
Prompt-based System for Personality and Interpersonal Reactivity Prediction
This paper describes our proposed method for the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Personality Prediction (PER) and Reactivity Index Prediction (IRI).
Towards Better Chinese-centric Neural Machine Translation for Low-resource Languages
The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries.
A Comprehensive Survey on Data-Efficient GANs in Image Generation
Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis.
LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs
The medical conversational system can relieve the burden of doctors and improve the efficiency of healthcare, especially during the pandemic.
Data-Efficient Backdoor Attacks
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks.
Hierarchical Locality Sensitive Hashing for Structured Data: A Survey
Data similarity (or distance) computation is a fundamental research topic which fosters a variety of similarity-based machine learning and data mining applications.
One-shot Federated Learning without Server-side Training
Federated Learning (FL) has recently made significant progress as a new machine learning paradigm for privacy protection.
Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios.
Dog nose print matching with dual global descriptor based on Contrastive Learning
These methods generally extract the global features as descriptor to represent the original image.
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition
We propose a normalized distortion threshold to evaluate the sensitivity of each involved convolutional layer of the base model to guide STD-NET to compress target network in an efficient and unsupervised approach, and obtain two network structures of different shapes with low computation cost and similar performance compared with the original one.
Adversarial Reconfigurable Intelligent Surface Against Physical Layer Key Generation
The development of reconfigurable intelligent surfaces (RIS) has recently advanced the research of physical layer security (PLS).
Cross-domain Federated Object Detection
Federated learning can enable multi-party collaborative learning without leaking client data.
Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation
To fully leverage the visual information for both scene understanding and dialogue generation, we propose the scene-aware prompt for the MDUG task.
Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
Besides estimating the probability distribution, our entropy model also generates the quantization step at spatial-channel-wise.
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
Since data augmentation strategies have largely alleviated the training instability, how to further improve the generative performance of DE-GANs becomes a hotspot.
Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction
Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted.
Clear Memory-Augmented Auto-Encoder for Surface Defect Detection
At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds.
Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis
We connect Fourier amplitude and phase with Gram matrices and a content reconstruction loss in style transfer, respectively.
Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process
However, making full use of the abundant information available from LFIs, such as 2D array of sub-views and the disparity map of each sub-view, for effective rain removal is still a challenging problem.
Compositional Law Parsing with Latent Random Functions
The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks.
TODE-Trans: Transparent Object Depth Estimation with Transformer
We observe that the global characteristics of the transformer make it easier to extract contextual information to perform depth estimation of transparent areas.
Domain-Unified Prompt Representations for Source-Free Domain Generalization
The proposed scheme generates diverse prompts from a domain bank that contains many more diverse domains than existing DG datasets.
Domain Discrepancy Aware Distillation for Model Aggregation in Federated Learning
In this paper, we first analyze the generalization bound of the aggregation model produced from knowledge distillation for the client domains, and then describe two challenges, server-to-client discrepancy and client-to-client discrepancy, brought to the aggregation model by the domain discrepancies.
Learning to Locate Visual Answer in Video Corpus Using Question
We introduce a new task, named video corpus visual answer localization (VCVAL), which aims to locate the visual answer in a large collection of untrimmed instructional videos using a natural language question.
Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction
This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence.
Slippage-robust Gaze Tracking for Near-eye Display
In recent years, head-mounted near-eye display devices have become the key hardware foundation for virtual reality and augmented reality.
Visual Answer Localization with Cross-modal Mutual Knowledge Transfer
In this paper, we propose a cross-modal mutual knowledge transfer span localization (MutualSL) method to reduce the knowledge deviation.
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning
In this paper, we propose a federated adaptive prompt tuning algorithm, FedAPT, for multi-domain collaborative image classification with powerful foundation models, like CLIP.
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #2 on
Semantic Segmentation
on ADE20K
(using extra training data)
Compositional Scene Modeling with Global Object-Centric Representations
Inspired by such an ability of humans, this paper proposes a compositional scene modeling method to infer global representations of canonical images of objects without any supervision.
Chinese Character Recognition with Radical-Structured Stroke Trees
In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way.
Artificial Text Detection with Multiple Training Strategies
As the deep learning rapidly promote, the artificial texts created by generative models are commonly used in news and social media.
Adversarial Example Defense via Perturbation Grading Strategy
In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.
Large Language Models are Better Reasoners with Self-Verification
By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score.
Test-time Personalizable Forecasting of 3D Human Poses
Current motion forecasting approaches typically train a deep end-to-end model from the source domain data, and then apply it directly to target subjects.
Motion Information Propagation for Neural Video Compression
Meanwhile, besides assisting frame coding at the current time step, the feature from context generation will be propagated as motion condition when coding the subsequent motion latent.
Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging
As to the orthographic projection problem, we propose a novel Viewing Direction-aided Positional Encoding (VDPE) strategy.
Time-Conditioned Generative Modeling of Object-Centric Representations for Video Decomposition and Prediction
To reconstruct the complete shape of an object accurately, we enhance the disentanglement between the latent representations of objects and views, where the latent representations of time-conditioned views are jointly inferred with a Transformer and then are input to a sequential extension of Slot Attention to learn object-centric representations.
Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection
In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal.
Kainate receptor modulation by NETO2
Glutamate-gated kainate receptors (KARs) are ubiquitous in the central nervous system of vertebrates, mediate synaptic transmission on post-synapse, and modulate transmitter release on pre-synapse.
EVC: Towards Real-Time Neural Image Compression with Mask Decay
Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder.
Energy Efficient Computation Offloading in Aerial Edge Networks With Multi-Agent Cooperation
With the high flexibility of supporting resource-intensive and time-sensitive applications, unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) is proposed as an innovational paradigm to support the mobile users (MUs).
Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot
Task automation of surgical robot has the potentials to improve surgical efficiency.
Neural Video Compression with Diverse Contexts
Better yet, our codec has surpassed the under-developing next generation traditional codec/ECM in both RGB and YUV420 colorspaces, in terms of PSNR.
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.
Uncertainty-aware U-Net for Medical Landmark Detection
To estimate the uncertainty, we propose a module named Pyramid Covariance Predictor to predict the covariance matrices of the target Gaussian distributions, which determine the distributions of landmarks and represent the uncertainty of landmark annotation.
Weakly-Supervised Text Instance Segmentation
Text segmentation is a challenging vision task with many downstream applications.
Mechanism Design for Ad Auctions with Display Prices
In this paper, we study ad auctions with display prices from the perspective of mechanism design, in which advertisers are asked to submit both the costs and prices of their products.
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
Our work highlights the potential of seamlessly unifying explicit rule learning via CoNNs and implicit pattern learning in LMs, paving the way for true symbolic comprehension capabilities.
FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI).
DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback
Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration.
RAPID: Enabling Fast Online Policy Learning in Dynamic Public Cloud Environments
Resource sharing between multiple workloads has become a prominent practice among cloud service providers, motivated by demand for improved resource utilization and reduced cost of ownership.
Meta-Auxiliary Learning for Adaptive Human Pose Prediction
Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans.
Frequency Decomposition to Tap the Potential of Single Domain for Generalization
Then, a new method that learns through multiple frequency domains is proposed.
Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model
Specifically, we first extract prototypes from the labeled data on the server and send them to the clients.
Large Language Models Need Holistically Thought in Medical Conversational QA
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care.
Collaborative Chinese Text Recognition with Personalized Federated Learning
In Chinese text recognition, to compensate for the insufficient local data and improve the performance of local few-shot character recognition, it is often necessary for one organization to collect a large amount of data from similar organizations.
Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis
The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently.
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions.
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data.
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
This paper presents a Proxy attack-Free Strategy (PFS) designed to identify efficient poisoning samples based on individual similarity and ensemble diversity, effectively addressing the mentioned concern.
Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions
We provide a gradient backpropagation highway for low-rank adapters which eliminates the need for expensive backpropagation through the frozen pre-trained model, resulting in substantial savings of training memory and training time.
OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning
The results demonstrate the shortcomings of state-of-the-art methods for learning meaningful representations from real-world data, despite their impressive performance on complex synthesis datasets.
Prototypes as Explanation for Time Series Anomaly Detection
Detecting abnormal patterns that deviate from a certain regular repeating pattern in time series is essential in many big data applications.
GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts
In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts.
Payload-Independent Direct Cost Learning for Image Steganography
This framework directly learns universal costs that can be applied to any payload.
