Search Results for author:
Found 339 papers, 112 papers with code
SQLFlow: A Bridge between SQL and Machine Learning
Previous database systems extended their SQL dialect to support ML.
Towards Fast, Accurate and Stable 3D Dense Face Alignment
Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously.
Ranked #1 on
3D Face Reconstruction
on Florence
(Mean NME metric)
InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language
Different from existing interactive systems that rely on pure language, by incorporating pointing instructions, the proposed iGPT significantly improves the efficiency of communication between users and chatbots, as well as the accuracy of chatbots in vision-centric tasks, especially in complicated visual scenarios where the number of objects is greater than 2.
CogDL: A Comprehensive Library for Graph Deep Learning
In CogDL, we propose a unified design for the training and evaluation of GNN models for various graph tasks, making it unique among existing graph learning libraries.
MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices
We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices.
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
We introduce MobileVLM V2, a family of significantly improved vision language models upon MobileVLM, which proves that a delicate orchestration of novel architectural design, an improved training scheme tailored for mobile VLMs, and rich high-quality dataset curation can substantially benefit VLMs' performance.
ABD-Net: Attentive but Diverse Person Re-Identification
Attention mechanism has been shown to be effective for person re-identification (Re-ID).
Ranked #16 on
Person Re-Identification
on Market-1501-C
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score.
Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition
Benchmarking our model on one of the most popular unconstrained face recognition datasets IJB-C additionally verifies the promising generalizability of AIM in recognizing faces in the wild.
Ranked #1 on
Age-Invariant Face Recognition
on MORPH Album2
AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss
Here we present a self-supervised representation learning method, namely AAG, which is featured by an auxiliary augmentation strategy and GNT-Xent loss.
ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
Aspect category sentiment analysis (ACSA) and review rating prediction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities.
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity.
Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
To address this issue, we propose a novel semantic-aware knowledge-guided framework (SKF) that can assist a low-light enhancement model in learning rich and diverse priors encapsulated in a semantic segmentation model.
Ranked #3 on
Low-Light Image Enhancement
on LOLv2
Reinforcement Learning for Relation Classification from Noisy Data
In this paper, we propose a novel model for relation classification at the sentence level from noisy data.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
LaFIn: Generative Landmark Guided Face Inpainting
It is challenging to inpaint face images in the wild, due to the large variation of appearance, such as different poses, expressions and occlusions.
Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness
The capability of Large Language Models (LLMs) like ChatGPT to comprehend user intent and provide reasonable responses has made them extremely popular lately.
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
First, it can exploit pixel alignment and feature alignment jointly.
Cross-Modality Person Re-identification
Generative Adversarial Network
+2
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
Deep learning-based methods have achieved remarkable performance for image dehazing.
Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning
To bridge this gap, we present the Graph Robustness Benchmark (GRB) with the goal of providing a scalable, unified, modular, and reproducible evaluation for the adversarial robustness of GML models.
Time-Series Event Prediction with Evolutionary State Graph
In this paper, we present evolutionary state graph, a dynamic graph structure designed to systematically represent the evolving relations (edges) among states (nodes) along time.
Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction.
Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition
With estimated scene depth, our method is capable of re-rendering hazy images with different thicknesses which further benefits the training of the dehazing network.
Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
We propose a novel framework that achieves remarkable matching performance with acceptable model complexity.
GraphLLM: Boosting Graph Reasoning Ability of Large Language Model
This synergy equips LLMs with the ability to proficiently interpret and reason on graph data, harnessing the superior expressive power of graph learning models.
GIKT: A Graph-based Interaction Model for Knowledge Tracing
With the rapid development in online education, knowledge tracing (KT) has become a fundamental problem which traces students' knowledge status and predicts their performance on new questions.
Ranked #7 on
Knowledge Tracing
on EdNet
Fast Single Image Reflection Suppression via Convex Optimization
Removing undesired reflections from images taken through the glass is of great importance in computer vision.
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks.
TI-CNN: Convolutional Neural Networks for Fake News Detection
By projecting the explicit and latent features into a unified feature space, TI-CNN is trained with both the text and image information simultaneously.
Improving Knowledge Tracing via Pre-training Question Embeddings
Knowledge tracing (KT) defines the task of predicting whether students can correctly answer questions based on their historical response.
Ranked #3 on
Knowledge Tracing
on EdNet
A Deep Learning Approach to Grasping the Invisible
The target-oriented motion critic, which maps both visual observations and target information to the expected future rewards of pushing and grasping motion primitives, is learned via deep Q-learning.
In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation
This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels.
ReshapeGAN: Object Reshaping by Providing A Single Reference Image
We present the tailored models of the proposed ReshapeGAN for all the problem settings, and have them tested on 8 kinds of reshaping tasks with 13 different datasets, demonstrating the ability of ReshapeGAN on generating convincing and superior results for object reshaping.
From Zero-Shot Learning to Cold-Start Recommendation
This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR.
Transformer-based Transform Coding
Neural data compression based on nonlinear transform coding has made great progress over the last few years, mainly due to improvements in prior models, quantization methods and nonlinear transforms.
DropMessage: Unifying Random Dropping for Graph Neural Networks
First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models.
GAKE: Graph Aware Knowledge Embedding
Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently.
GKD: A General Knowledge Distillation Framework for Large-scale Pre-trained Language Model
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.
Generating Accurate and Faithful Discharge Instructions: Task, Dataset, and Model
We build a benchmark clinical dataset and propose the Re3Writer, which imitates the working patterns of physicians to first retrieve related working experience from historical PIs written by physicians, then reason related medical knowledge.
Lifting the Curse of Capacity Gap in Distilling Language Models
However, when the capacity gap between the teacher and the student is large, a curse of capacity gap appears, invoking a deficiency in distilling LMs.
GUESS:GradUally Enriching SyntheSis for Text-Driven Human Motion Generation
The whole text-driven human motion synthesis problem is then divided into multiple abstraction levels and solved with a multi-stage generation framework with a cascaded latent diffusion model: an initial generator first generates the coarsest human motion guess from a given text description; then, a series of successive generators gradually enrich the motion details based on the textual description and the previous synthesized results.
Ranked #6 on
Motion Synthesis
on KIT Motion-Language
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech
Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems.
Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice System
The MST graph provides a virtual representation of the status and scheduling relationships among service instances of a real-world microservice system.
Inexact Block Coordinate Descent Algorithms for Nonsmooth Nonconvex Optimization
Interestingly, when the approximation subproblem is solved by a descent algorithm, convergence of a subsequence to a stationary point is still guaranteed even if the approximation subproblem is solved inexactly by terminating the descent algorithm after a finite number of iterations.
Self-supervised Discriminative Feature Learning for Deep Multi-view Clustering
To leverage the multi-view complementary information, we concatenate all views' embedded features to form the global features, which can overcome the negative impact of some views' unclear clustering structures.
Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19.
Alleviating Feature Confusion for Generative Zero-shot Learning
An inevitable issue of such a paradigm is that the synthesized unseen features are prone to seen references and incapable to reflect the novelty and diversity of real unseen instances.
Probability Weighted Compact Feature for Domain Adaptive Retrieval
Most of the existing image retrieval methods only focus on single-domain retrieval, which assumes that the distributions of retrieval databases and queries are similar.
Measuring Perceptual Color Differences of Smartphone Photographs
Measuring perceptual color differences (CDs) is of great importance in modern smartphone photography.
Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets
Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging problem.
Universal Weighting Metric Learning for Cross-Modal Matching
Furthermore, we introduce a new polynomial loss under the universal weighting framework, which defines a weight function for the positive and negative informative pairs respectively.
Universal Prompt Tuning for Graph Neural Networks
In this paper, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy.
Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
Specifically, on two key tasks, \textit{i. e.}, image-to-text and text-to-image retrieval, HAT achieves 7. 6\% and 16. 7\% relative score improvement of Recall@1 on MSCOCO, and 4. 4\% and 11. 6\% on Flickr30k respectively.
LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models
Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts.
Learning a Deep Color Difference Metric for Photographic Images
Most well-established and widely used color difference (CD) metrics are handcrafted and subject-calibrated against uniformly colored patches, which do not generalize well to photographic images characterized by natural scene complexities.
Visible-Infrared Person Re-Identification via Semantic Alignment and Affinity Inference
We propose a Semantic Alignment and Affinity Inference framework (SAAI), which aims to align latent semantic part features with the learnable prototypes and improve inference with affinity information.
Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability.
Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination
Most existing image-text matching methods adopt triplet loss as the optimization objective, and choosing a proper negative sample for the triplet of <anchor, positive, negative> is important for effectively training the model, e. g., hard negatives make the model learn efficiently and effectively.
Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification
Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification.
Non-Autoregressive Math Word Problem Solver with Unified Tree Structure
For evaluating the possible expression variants, we design a path-based metric to evaluate the partial accuracy of expressions of a unified tree.
Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
In our work, we first design a new model called "high order LSTM" to predict multiple tags for the current token which contains not only the current tag but also the previous several tags.
ProxSGD: Training Structured Neural Networks under Regularization and Constraints
In this paper, we consider the problem of training neural networks (NN).
Learning to Check Contract Inconsistencies
This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract.
ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding
Despite their effectiveness, existing methods suffer from the difficulty of low recognition accuracy in cases of multiple adjacent objects with similar appearances. To address this issue, this work intuitively introduces the human-robot interaction as a cue to facilitate the development of 3D visual grounding.
Functional Geometry Guided Protein Sequence and Backbone Structure Co-Design
In this paper, we propose NAEPro, a model to jointly design Protein sequence and structure based on automatically detected functional sites.
Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach
Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.
Free-breathing and ungated cardiac cine using navigator-less spiral SToRM
An iterative kernel low-rank algorithm is introduced to estimate the manifold structure of the images, or equivalently the manifold Laplacian matrix, from the central k-space regions.
IDToolkit: A Toolkit for Benchmarking and Developing Inverse Design Algorithms in Nanophotonics
These obstacles prevent AI researchers from developing specialized methods for scientific designs.
An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
We present Expert-Token-Routing, a unified generalist framework that facilitates seamless integration of multiple expert LLMs.
A Unified Successive Pseudo-Convex Approximation Framework
In this paper, we propose a successive pseudo-convex approximation algorithm to efficiently compute stationary points for a large class of possibly nonconvex optimization problems.
Optimization and Control Numerical Analysis
Rethinking the Value of Gazetteer in Chinese Named Entity Recognition
Gazetteer is widely used in Chinese named entity recognition (NER) to enhance span boundary detection and type classification.
Bayesian Structure Scores for Probabilistic Circuits
Probabilistic circuits (PCs) are a prominent representation of probability distributions with tractable inference.
When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
All convex combinations of graphon bases give rise to a generator space, from which graphs generated form the solution space for those downstream data that can benefit from pre-training.
A Novel Correlation-optimized Deep Learning Method for Wind Speed Forecast
Finally, the effectiveness of the proposed method is verified by three wind prediction cases from a wind farm in Liaoning, China.
Towards Efficient and Effective Unlearning of Large Language Models for Recommendation
However, in order to protect user privacy and optimize utility, it is also crucial for LLMRec to intentionally forget specific user data, which is generally referred to as recommendation unlearning.
Rethinking the Misalignment Problem in Dense Object Detection
On the basis of SALT and SDR loss, we propose SALT-Net, which explicitly exploits task-aligned point-set features for accurate detection results.
Multi-View Clustering for Open Knowledge Base Canonicalization
In this paper, we propose CMVC, a novel unsupervised framework that leverages these two views of knowledge jointly for canonicalizing OKBs without the need of manually annotated labels.
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.
Accelerating Dynamic Network Embedding with Billions of Parameter Updates to Milliseconds
Network embedding, a graph representation learning method illustrating network topology by mapping nodes into lower-dimension vectors, is challenging to accommodate the ever-changing dynamic graphs in practice.
Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
The proposed pre-training pipeline is called the data-active graph pre-training (APT) framework, and is composed of a graph selector and a pre-training model.
Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns
In this paper, we identify the fundamental cause of structural divergence as the discrepancy of generative patterns between the pre-training and downstream graphs.
Towards Fair Graph Federated Learning via Incentive Mechanisms
Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.
Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
In this work, we choose to represent this quantity with a physically inspired ML model that captures two distinct physical effects: local atomic polarization is captured within the symmetry-adapted Gaussian process regression (SA-GPR) framework, which assigns a (vector) dipole moment to each atom, while movement of charge across the entire molecule is captured by assigning a partial (scalar) charge to each atom.
Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images
Underwater visual perception is essentially important for underwater exploration, archeology, ecosystem and so on.
MiniDisc: Minimal Distillation Schedule for Language Model Compression
In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $\lambda$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student.
Probabilistic Multi-Dimensional Classification
We propose a formal framework for probabilistic MDC in which learning an optimal multi-dimensional classifier can be decomposed, without loss of generality, into learning a set of (smaller) single-variable multi-class probabilistic classifiers and a directed acyclic graph.
Solving Math Word Problems with Reexamination
Math word problem (MWP) solving aims to understand the descriptive math problem and calculate the result, for which previous efforts are mostly devoted to upgrade different technical modules.
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model
We achieve a biomedical multilingual corpus by incorporating three granularity knowledge alignments (entity, fact, and passage levels) into monolingual corpora.
Can GNN be Good Adapter for LLMs?
In terms of efficiency, the GNN adapter introduces only a few trainable parameters and can be trained with low computation costs.
Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
Bargaining is an important and unique part of negotiation between humans.
Learning Fair Representations via an Adversarial Framework
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval.
BASN -- Learning Steganography with Binary Attention Mechanism
Secret information sharing through image carrier has aroused much research attention in recent years with images' growing domination on the Internet and mobile applications.
Collaborative Learning for Extremely Low Bit Asymmetric Hashing
Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression.
Distributed Bayesian Matrix Decomposition for Big Data Mining and Clustering
Such a method should scale up well, model the heterogeneous noise, and address the communication issue in a distributed system.
Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph
Most of the prior efforts are devoted to learning node embeddings with graph neural networks (GNNs), which preserve the signed network topology by message-passing along edges to facilitate the downstream link prediction task.
The hybrid dimensional representation of permeability tensor: a reinterpretation of the discrete fracture model and its extension on nonconforming meshes
The discrete fracture model (DFM) has been widely used in the simulation of fluid flow in fractured porous media.
Numerical Analysis Numerical Analysis
Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications
The design of MAFENN framework and algorithm are dedicated to enhance the learning capability of the feedfoward DL networks or their variations with the simple data feedback.
A Progressive Framework for Role-Aware Rumor Resolution
Existing works on rumor resolution have shown great potential in recognizing word appearance and user participation.
FakeEdge: Alleviate Dataset Shift in Link Prediction
In this paper, we first identify the dataset shift problem in the link prediction task and provide theoretical analyses on how existing link prediction methods are vulnerable to it.
DOMFN: A Divergence-Orientated Multi-Modal Fusion Network for Resume Assessment
Inspired by practical resume evaluations that consider both the content and layout, we construct the multi-modalities from resumes but face a new challenge that sometimes the performance of multi-modal fusion is even worse than the best uni-modality.
Non-Autoregressive Sentence Ordering
Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step.
Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph
In this paper, we argue that properly fetching and condensing the background nodes from massive web graph data might be a more economical shortcut to tackle the obstacles fundamentally.
FingerVision Tactile Sensor Design and Slip Detection Using Convolutional LSTM Network
Tactile sensing is essential to the human perception system, so as to robot.
MrTF: Model Refinery for Transductive Federated Learning
We propose a novel learning paradigm named transductive federated learning (TFL) to simultaneously consider the structural information of the to-be-inferred data.
Learning to Generate Lumped Hydrological Models
Overall, this study demonstrates that the hydrological behavior of a catchment can be effectively described using a small number of latent variables, and that well-fitting hydrologic model functions can be reconstructed from these variables.
Robust Semi-Supervised Learning for Self-learning Open-World Classes
Existing semi-supervised learning (SSL) methods assume that labeled and unlabeled data share the same class space.
AccidentBlip2: Accident Detection With Multi-View MotionBlip2
We also extend our approach to a multi-vehicle cooperative system by deploying Motion Qformer on each vehicle and simultaneously inputting the inference-generated query into the MLP for autoregressive inference.
r-Instance Learning for Missing People Tweets Identification
The number of missing people (i. e., people who get lost) greatly increases in recent years.
Boosting Cooperative Coevolution for Large Scale Optimization with a Fine-Grained Computation Resource Allocation Strategy
Cooperative coevolution (CC) has shown great potential in solving large scale optimization problems (LSOPs).
Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs
We then construct three individual networks: a Focus-Net to extract depth from a single focal stack, a EDoF-Net to obtain the extended depth of field (EDoF) image from the focal stack, and a Stereo-Net to conduct stereo matching.
Deep Learning Scaling is Predictable, Empirically
As DL application domains grow, we would like a deeper understanding of the relationships between training set size, computational scale, and model accuracy improvements to advance the state-of-the-art.
Representation Learning for Scale-free Networks
Existing network embedding works primarily focus on preserving the microscopic structure, such as the first- and second-order proximity of vertexes, while the macroscopic scale-free property is largely ignored.
A Parallel Best-Response Algorithm with Exact Line Search for Nonconvex Sparsity-Regularized Rank Minimization
In this paper, we propose a convergent parallel best-response algorithm with the exact line search for the nondifferentiable nonconvex sparsity-regularized rank minimization problem.
Cross-Domain Image Retrieval with Attention Modeling
For query images, we use each candidate image in the database as the context to locate the query attention.
In search of inliers: 3d correspondence by local and global voting
The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast.
Learning Efficient Image Representation for Person Re-Identification
Then, a robust image representation based on color names is obtained by concatenating the statistical descriptors in each stripe.
Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a. k. a., image description, has been remarkably advanced in recent years.
Binary Subspace Coding for Query-by-Image Video Retrieval
The first approach, termed Inner-product Binary Coding (IBC), preserves the inner relationships of images and videos in a common Hamming space.
Chinese/English mixed Character Segmentation as Semantic Segmentation
We take advantage of the successful architecture called fully convolutional networks (FCN) in the field of semantic segmentation.
Embedding Deep Metric for Person Re-identication A Study Against Large Variations
From this point of view, selecting suitable positive i. e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations.
Zero-Shot Hashing via Transferring Supervised Knowledge
Supervised knowledge e. g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the quality of hash codes and hash functions.
Bidirectional Long-Short Term Memory for Video Description
Video captioning has been attracting broad research attention in multimedia community.
Towards Empathetic Human-Robot Interactions
Although research on empathetic robots is still in the early stage, we described our approach using signal processing techniques, sentiment analysis and machine learning algorithms to make robots that can "understand" human emotion.
Learning Binary Codes and Binary Weights for Efficient Classification
The optimization alternatively proceeds over the binary classifiers and image hash codes.
Constrained Deep Metric Learning for Person Re-identification
In this paper, we propose a novel CNN-based method to learn a discriminative metric with good robustness to the over-fitting problem in person re-identification.
Inferring Social Status and Rich Club Effects in Enterprise Communication Networks
Our model can predict social status of individuals with 93% accuracy.
Successive Convex Approximation Algorithms for Sparse Signal Estimation with Nonconvex Regularizations
The proposed framework has several attractive features, namely, i) flexibility, as different choices of the approximate function lead to different type of algorithms; ii) fast convergence, as the problem structure can be better exploited by a proper choice of the approximate function and the stepsize is calculated by the line search; iii) low complexity, as the approximate function is convex and the line search scheme is carried out over a differentiable function; iv) guaranteed convergence to a stationary point.
Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learning
Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming.
XJTLUIndoorLoc: A New Fingerprinting Database for Indoor Localization and Trajectory Estimation Based on Wi-Fi RSS and Geomagnetic Field
In this paper, we present a new location fingerprinting database comprised of Wi-Fi received signal strength (RSS) and geomagnetic field intensity measured with multiple devices at a multi-floor building in Xi'an Jiatong-Liverpool University, Suzhou, China.
Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning
Experimental results show that our model is effective to extract relation mentions from noisy data.
Automatic Grammar Augmentation for Robust Voice Command Recognition
For a given grammar set, a set of potential grammar expressions (candidate set) for augmentation is constructed from an AM-specific statistical pronunciation dictionary that captures the consistent patterns and errors in the decoding of AM induced by variations in pronunciation, pitch, tempo, accent, ambiguous spellings, and noise conditions.
An Interpretable Neural Network with Topical Information for Relevant Emotion Ranking
As such, it is crucial to predict and rank multiple relevant emotions by their intensities.
Relevant Emotion Ranking from Text Constrained with Emotion Relationships
As such, emotion detection, to predict multiple emotions associated with a given text, can be cast into a multi-label classification problem.
Zara: A Virtual Interactive Dialogue System Incorporating Emotion, Sentiment and Personality Recognition
Zara, or {`}Zara the Supergirl{'} is a virtual robot, that can exhibit empathy while interacting with an user, with the aid of its built in facial and emotion recognition, sentiment analysis, and speech module.
Automatic 3D Indoor Scene Modeling From Single Panorama
The recovered layout is then used to guide shape estimation of the remaining objects using their normal information.
ML-LocNet: Improving Object Localization with Multi-view Learning Network
This paper addresses Weakly Supervised Object Localization (WSOL) with only image-level supervision.
Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video
In order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders.
Ambient Occlusion via Compressive Visibility Estimation
This enables a sparsity-prior based solution for iteratively recovering the surface normal, the surface albedo, and the visibility function from a small number of images.
Matrix Tri-Factorization With Manifold Regularizations for Zero-Shot Learning
By additionally introducing manifold regularizations on visual data and semantic embeddings, the learned projection can effectively captures the geometrical manifold structure residing in both visual and semantic spaces.
Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images
Recently, researchers have made great processes to build category-specific 3D shape models from 2D images with manual annotations consisting of class labels, keypoints, and ground truth figure-ground segmentations.
Learning Binary Codes for Maximum Inner Product Search
Inspired by the latest advance in asymmetric hashing schemes, we propose an asymmetric binary code learning framework based on inner product fitting.
Point Set Registration With Global-Local Correspondence and Transformation Estimation
We present a new point set registration method with global-local correspondence and transformation estimation (GL-CATE).
Snap and Find: Deep Discrete Cross-domain Garment Image Retrieval
With the increasing number of online stores, there is a pressing need for intelligent search systems to understand the item photos snapped by customers and search against large-scale product databases to find their desired items.
Judging Chemical Reaction Practicality From Positive Sample only Learning
Chemical reaction practicality is the core task among all symbol intelligence based chemical information processing, for example, it provides indispensable clue for further automatic synthesis route inference.
A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition
Besides, we propose a View-guided Skeleton CNN (VS-CNN) to tackle the problem of arbitrary-view action recognition.
One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
It is well known that humans can learn and recognize objects effectively from several limited image samples.
Capturing Evolution Genes for Time Series Data
The modeling of time series is becoming increasingly critical in a wide variety of applications.
Missing Movie Synergistic Completion across Multiple Isomeric Online Movie Knowledge Libraries
Online knowledge libraries refer to the online data warehouses that systematically organize and categorize the knowledge-based information about different kinds of concepts and entities.
Adversarial Category Alignment Network for Cross-domain Sentiment Classification
Cross-domain sentiment classification aims to predict sentiment polarity on a target domain utilizing a classifier learned from a source domain.
Simultaneous reconstruction of the initial pressure and sound speed in photoacoustic tomography using a deep-learning approach
Photoacoustic tomography seeks to reconstruct an acoustic initial pressure distribution from the measurement of the ultrasound waveforms.
X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
Motivated by the development of deep convolution neural networks (DCNNs), tremendous progress has been gained in the field of aircraft detection.
Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way.
CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
Thus, a multi-modal cycle-consistency loss between the synthesized semantic representations and the ground truth can be learned and leveraged to enforce the generated semantic features to approximate to the real distribution in semantic space.
Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures
This Slide-to-Wall grasping task assumes no prior knowledge except the partial observation of a target object.
Learning to Generate 6-DoF Grasp Poses with Reachability Awareness
Motivated by the stringent requirements of unstructured real-world where a plethora of unknown objects reside in arbitrary locations of the surface, we propose a voxel-based deep 3D Convolutional Neural Network (3D CNN) that generates feasible 6-DoF grasp poses in unrestricted workspace with reachability awareness.
Interpretable Relevant Emotion Ranking with Event-Driven Attention
Unveiling the hidden event information can help to understand how the emotions are evoked and provide explainable results.
Feedback Recurrent AutoEncoder
In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency.
Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data.
Cross-modal supervised learning for better acoustic representations
On the contrary, we can easily collect data with machine-generated labels.
A Big Data Enabled Channel Model for 5G Wireless Communication Systems
This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling.
Guided Variational Autoencoder for Disentanglement Learning
We propose an algorithm, guided variational autoencoder (Guided-VAE), that is able to learn a controllable generative model by performing latent representation disentanglement learning.
An Eigenspace Divide-and-Conquer Approach for Large-Scale Optimization
Different from existing DC-based algorithms that perform decomposition and optimization in the original decision space, EDC first establishes an eigenspace by conducting singular value decomposition on a set of high-quality solutions selected from recent generations.
Feedback Recurrent Autoencoder for Video Compression
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems.
Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing
Compared to existing datasets, the queries in the dataset here are derived from the eligibility criteria of clinical trials and include \textit{Order-sensitive, Counting-based, and Boolean-type} cases which are not seen before.
Color Point Cloud Registration Based on Supervoxel Correspondence
Different from traditional feature-based methods, we design a hybrid feature representation with color moments of the point, which could be applied naturally for any color point cloud.
Multi-level Training and Bayesian Optimization for Economical Hyperparameter Optimization
Hyperparameters play a critical role in the performances of many machine learning methods.
Service Chain Composition with Failures in NFV Systems: A Game-Theoretic Perspective
In this paper, we formulate the problem of service chain composition in NFV systems with failures as a non-cooperative game.
Green Offloading in Fog-Assisted IoT Systems: An Online Perspective Integrating Learning and Control
In this paper, we formulate such a task offloading problem with unknown system dynamics as a combinatorial multi-armed bandit (CMAB) problem with long-term constraints on time-averaged energy consumptions.
History-Aware Online Cache Placement in Fog-Assisted IoT Systems: An Integration of Learning and Control
Due to uncertainties in practice such as unknown file popularities, cache placement scheme design is still an open problem with unresolved challenges: 1) how to maintain time-averaged storage costs under budgets, 2) how to incorporate online learning to aid cache placement to minimize performance loss (a. k. a.
Networking and Internet Architecture Signal Processing
Boundary Content Graph Neural Network for Temporal Action Proposal Generation
To address this issue, we propose a novel Boundary Content Graph Neural Network (BC-GNN) to model the insightful relations between the boundary and action content of temporal proposals by the graph neural networks.
Ranked #25 on
Temporal Action Localization
on ActivityNet-1.3
Hierarchical Bi-Directional Feature Perception Network for Person Re-Identification
To solve this issue, we propose a novel model named Hierarchical Bi-directional Feature Perception Network (HBFP-Net) to correlate multi-level information and reinforce each other.
S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification
Open set classification (OSC) tackles the problem of determining whether the data are in-class or out-of-class during inference, when only provided with a set of in-class examples at training time.
Learning Adaptive Embedding Considering Incremental Class
To this end, we propose a Class-Incremental Learning without Forgetting (CILF) framework, which aims to learn adaptive embedding for processing novel class detection and model update in a unified framework.
Query-aware Tip Generation for Vertical Search
Existing work on tip generation does not take query into consideration, which limits the impact of tips in search scenarios.
Collaborative Filtering with Social Exposure: A Modular Approach to Social Recommendation
We assume that people get information of products from their online friends and they do not have to share similar preferences, which is less restrictive and seems closer to reality.
The Disruptions of 5G on Data-driven Technologies and Applications
With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management.
Networking and Internet Architecture Databases Distributed, Parallel, and Cluster Computing
Location Prediction of Social Images via Generative Model
In particularly, we propose a geographical topic model GTMI (geographical topic model of social image) to integrate multiple types of image content as well as the geographical distributions, In GTMI, image topic is modeled on both text vocabulary and visual feature.
Evaluating Link Prediction Methods
Link prediction is a popular research area with important applications in a variety of disciplines, including biology, social science, security, and medicine.
A Novel Received Signal Strength Assisted Perspective-three-Point Algorithm for Indoor Visible Light Positioning
The basic idea of R-P3P is to joint visual and strength information to estimate the receiver position using 3 LEDs regardless of the LEDs' orientations.
Power Efficient LED Placement Algorithm for Indoor Visible Light Communication
Due to the interactions among LEDs and the illumination uniformity constraint, the formulated problem is complex and non-convex.
Unsupervised Adversarially-Robust Representation Learning on Graphs
Additionally, we explore a provable connection between the robustness of the unsupervised graph encoder and that of models on downstream tasks.
Denoising-based Turbo Message Passing for Compressed Video Background Subtraction
In this paper, we consider the compressed video background subtraction problem that separates the background and foreground of a video from its compressed measurements.
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs
To bridge the gap between theoretical graph attacks and real-world scenarios, in this work, we propose a novel and more realistic setting: strict black-box graph attack, in which the attacker has no knowledge about the victim model at all and is not allowed to send any queries.
PURE: A Framework for Analyzing Proximity-based Contact Tracing Protocols
Many proximity-based tracing (PCT) protocols have been proposed and deployed to combat the spreading of COVID-19.
Computers and Society C.3; H.4; J.3; J.7; K.4; K.6.5
Federated Unlearning
In this paper, we take the first step to fill this gap by presenting FedEraser, the first federated unlearning methodology that can eliminate the influence of a federated client's data on the global FL model while significantly reducing the time used for constructing the unlearned FL model. The basic idea of FedEraser is to trade the central server's storage for unlearned model's construction time, where FedEraser reconstructs the unlearned model by leveraging the historical parameter updates of federated clients that have been retained at the central server during the training process of FL.
What social media told about us in the time of COVID-19: a scoping review
With the onset of COVID-19 pandemic, social media has rapidly become a crucial communication tool for information generation, dissemination, and consumption.
Misinformation
Social and Information Networks
Upper Limits on the Isotropic Gravitational-Wave Background from Advanced LIGO's and Advanced Virgo's Third Observing Run
Unlike in previous observing runs in the advanced detector era, we include Virgo in the search for the GWB.
General Relativity and Quantum Cosmology Cosmology and Nongalactic Astrophysics
The Hybrid-dimensional Darcy's Law: A Reinterpreted Discrete Fracture Model for Fracture and Barrier Networks on Non-conforming Meshes
In this paper, we extend the reinterpreted discrete fracture model for flow simulation of fractured porous media containing flow blocking barriers on non-conforming meshes.
Numerical Analysis Numerical Analysis
A Unified Light Framework for Real-time Fault Detection of Freight Train Images
Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements.
Text-Embedded Bilinear Model for Fine-Grained Visual Recognition
Specially, we first conduct a text-embedded network to embed text feature into the discriminative image feature learning to get a embedded feature.
Fine-Grained Image Recognition
Fine-Grained Visual Recognition
+1
Progressive Neural Image Compression with Nested Quantization and Latent Ordering
We present PLONQ, a progressive neural image compression scheme which pushes the boundary of variable bitrate compression by allowing quality scalable coding with a single bitstream.
A proof by foliation that Lawson's cones are $A_Φ$-minimizing
We also analyze the behavior at infinity of the leaves in the foliations.
Analysis of PDEs Differential Geometry
Integrating Pre-trained Model into Rule-based Dialogue Management
Rule-based dialogue management is still the most popular solution for industrial task-oriented dialogue systems for their interpretablility.
Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning
Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images.
Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
Most of the existing deep learning based end-to-end image/video coding (DLEC) architectures are designed for non-subsampled RGB color format.
Optimization of User Selection and Bandwidth Allocation for Federated Learning in VLC/RF Systems
Then, the problem of user selection and bandwidth allocation is studied for FL implemented over a hybrid VLC/RF system aiming to optimize the FL performance.
HAMIL: Hierarchical Aggregation-Based Multi-Instance Learning for Microscopy Image Classification
Multi-instance learning is common for computer vision tasks, especially in biomedical image processing.
Collision-Aware Target-Driven Object Grasping in Constrained Environments
Grasping a novel target object in constrained environments (e. g., walls, bins, and shelves) requires intensive reasoning about grasp pose reachability to avoid collisions with the surrounding structures.
