Search Results for author:
Found 158 papers, 55 papers with code
HiGraphDTI: Hierarchical Graph Representation Learning for Drug-Target Interaction Prediction
Specifically, HiGraphDTI learns hierarchical drug representations from triple-level molecular graphs to thoroughly exploit chemical information embedded in atoms, motifs, and molecules.
Struggle with Adversarial Defense? Try Diffusion
Unlike data-driven classifiers, TMDC, guided by Bayesian principles, utilizes the conditional likelihood from diffusion models to determine the class probabilities of input images, thereby insulating against the influences of data shift and the limitations of adversarial training.
Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples
However, the intrinsic class imbalance in multi-label data may bias the model towards majority labels, since samples relevant to minority labels may be underrepresented in each mini-batch.
Multimodal Fusion with Pre-Trained Model Features in Affective Behaviour Analysis In-the-wild
Multimodal fusion is a significant method for most multimodal tasks.
GT-Rain Single Image Deraining Challenge Report
This report reviews the results of the GT-Rain challenge on single image deraining at the UG2+ workshop at CVPR 2023.
Self-supervised Contrastive Learning for Implicit Collaborative Filtering
Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.
3D-aware Image Generation and Editing with Multi-modal Conditions
3D-consistent image generation from a single 2D semantic label is an important and challenging research topic in computer graphics and computer vision.
MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection
Inspired by the recent basic model with linear complexity for long-distance modeling, called Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper.
Can Deception Detection Go Deeper? Dataset, Evaluation, and Benchmark for Deception Reasoning
To address data scarcity, this paper proposes a new data collection pipeline.
Learning Contrastive Feature Representations for Facial Action Unit Detection
To address the challenge posed by noisy AU labels, we augment the supervised signal through the introduction of a self-supervised signal.
Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
This bidirectional interaction narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations.
TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection
We abstract this process as the directional movement of feature map pixels to target areas through convolution, pooling and interactions with surrounding pixels, which can be analogous to the movement of thermal particles constrained by surrounding variables and particles.
WiOpen: A Robust Wi-Fi-based Open-set Gesture Recognition Framework
This uncertainty, resulting from noise and domains, leads to widely scattered and irregular data distributions in collected Wi-Fi sensing data.
HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition
Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in recent years for its critical role in creating emotion-ware intelligent machines.
Ranked #3 on
Dynamic Facial Expression Recognition
on MAFW
Contrastive Learning
Dynamic Facial Expression Recognition
+3
SVFAP: Self-supervised Video Facial Affect Perceiver
Video-based facial affect analysis has recently attracted increasing attention owing to its critical role in human-computer interaction.
Ranked #3 on
Dynamic Facial Expression Recognition
on FERV39k
Dynamic Facial Expression Recognition
Emotion Recognition
+2
GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition
To bridge this gap, we present the quantitative evaluation results of GPT-4V on 21 benchmark datasets covering 6 tasks: visual sentiment analysis, tweet sentiment analysis, micro-expression recognition, facial emotion recognition, dynamic facial emotion recognition, and multimodal emotion recognition.
Towards More Unified In-context Visual Understanding
Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines.
Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents
By incorporating the guidance from the teacher agent, the student agent can distill the prior knowledge of the LLM into its own model.
Filter Pruning For CNN With Enhanced Linear Representation Redundancy
In this paper, we propose a new structured pruning method.
Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding
Existing methods for multi-modal manipulation detection and grounding primarily focus on fusing vision-language features to make predictions, while overlooking the importance of modality-specific features, leading to sub-optimal results.
Emotion-Aware Prosodic Phrasing for Expressive Text-to-Speech
Prosodic phrasing is crucial to the naturalness and intelligibility of end-to-end Text-to-Speech (TTS).
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
Unsupervised Out-of-Distribution Detection by Restoring Lossy Inputs with Variational Autoencoder
Deep generative models have been demonstrated as problematic in the unsupervised out-of-distribution (OOD) detection task, where they tend to assign higher likelihoods to OOD samples.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Contrastive Learning of Temporal Distinctiveness for Survival Analysis in Electronic Health Records
Therefore, in this paper, we propose a novel Ontology-aware Temporality-based Contrastive Survival (OTCSurv) analysis framework that utilizes survival durations from both censored and observed data to define temporal distinctiveness and construct negative sample pairs with adjustable hardness for contrastive learning.
Video Captioning with Aggregated Features Based on Dual Graphs and Gated Fusion
The application of video captioning models aims at translating the content of videos by using accurate natural language.
Debiased Pairwise Learning from Positive-Unlabeled Implicit Feedback
Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and information retrieval.
Unveiling the Potential of Knowledge-Prompted ChatGPT for Enhancing Drug Trafficking Detection on Social Media
By integrating prior knowledge and the proposed prompts, ChatGPT can effectively identify and label drug trafficking activities on social networks, even in the presence of deceptive language and euphemisms used by drug dealers to evade detection.
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition
Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines.
Ranked #2 on
Dynamic Facial Expression Recognition
on FERV39k
Dynamic Facial Expression Recognition
Facial Expression Recognition
MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators
Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans.
EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors
Transformer is popular in recent 3D human pose estimation, which utilizes long-term modeling to lift 2D keypoints into the 3D space.
Ranked #85 on
3D Human Pose Estimation
on Human3.6M
Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
Our proposed method can simultaneously (1) secure VARS from adversarial attacks characterized by local perturbations by image reconstruction based on global vision transformers; and (2) accurately detect adversarial examples using a novel contrastive learning approach.
A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge
We first generated several variants of the E2E-Spot model, resulting in a candidate model set.
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
In this paper, we explore how to enable intelligent cost-effective interactions between the agent and an LLM.
Reducing Popularity Bias in Recommender Systems through AUC-Optimal Negative Sampling
To achieve this win-win situation, we propose to intervene in model training through negative sampling thereby modifying model predictions.
Multi-spectral Class Center Network for Face Manipulation Detection and Localization
Next, a novel Multi-Spectral Class Center Network (MSCCNet) is proposed for face manipulation detection and localization.
Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification
Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID).
Restormer-Plus for Real World Image Deraining: the Runner-up Solution to the GT-RAIN Challenge (CVPR 2023 UG2+ Track 3)
It consists of four main modules: the single-image de-raining module (Restormer-X), the median filtering module, the weighted averaging module, and the post-processing module.
MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning
The first Multimodal Emotion Recognition Challenge (MER 2023) was successfully held at ACM Multimedia.
Use the Detection Transformer as a Data Augmenter
In contrast, DeMix elaborately selects a semantically rich patch, located by a pre-trained DETR.
On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks.
Futures Quantitative Investment with Heterogeneous Continual Graph Neural Network
This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks.
Towards Commonsense Knowledge based Fuzzy Systems for Supporting Size-Related Fine-Grained Object Detection
To achieve accurate fine-grained detection, one needs to employ a large enough model and a vast amount of data annotations.
Toward NeuroDM: Where Computational Neuroscience Meets Data Mining
At the intersection of computational neuroscience (CN) and data mining (DM), we advocate a holistic view toward their rich connections.
Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention
In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention.
3D Colored Shape Reconstruction from a Single RGB Image through Diffusion
In shape prediction module, the reference RGB image is first encoded into a high-level shape feature and then the shape feature is utilized as a condition to predict the reverse geometric noise in diffusion model.
A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
We study stochastic delayed feedback in general multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs).
Bayesian Self-Supervised Contrastive Learning
Recent years have witnessed many successful applications of contrastive learning in diverse domains, yet its self-supervised version still remains many exciting challenges.
MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset
Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays.
Fine-Grained Selective Similarity Integration for Drug-Target Interaction Prediction
Recently, with the availability of abundant heterogeneous biological information from diverse data sources, computational methods have been able to leverage multiple drug and target similarities to boost the performance of DTI prediction.
IRNet: Iterative Refinement Network for Noisy Partial Label Learning
In this paper, we relax this assumption and focus on a more general problem, noisy PLL, where the ground-truth label may not exist in the candidate set.
SML:Enhance the Network Smoothness with Skip Meta Logit for CTR Prediction
In light of the smoothness property brought by skip connections in ResNet, this paper proposed the Skip Logit to introduce the skip connection mechanism that fits arbitrary DNN dimensions and embraces similar properties to ResNet.
Learning by Consuming: Optimal Pricing with Endogenous Information Provision
We study the revenue-maximizing mechanism when a buyer's value evolves endogenously because of learning-by-consuming.
Q-Net: Query-Informed Few-Shot Medical Image Segmentation
Deep learning has achieved tremendous success in computer vision, while medical image segmentation (MIS) remains a challenge, due to the scarcity of data annotations.
Efficient Multimodal Transformer with Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis
With the proliferation of user-generated online videos, Multimodal Sentiment Analysis (MSA) has attracted increasing attention recently.
Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task.
Intelligent decision-making method of TBM operating parameters based on multiple constraints and objective optimization
This method is verified in the field of the Second Water Source Channel of Hangzhou, China, resulting in the average penetration rate increased by 11. 3%, and the total cost decreased by 10. 0%, which proves the practicability and effectiveness of the developed decision-making model.
Two-Aspect Information Fusion Model For ABAW4 Multi-task Challenge
In this paper, we propose the solution to the Multi-Task Learning (MTL) Challenge of the 4th Affective Behavior Analysis in-the-wild (ABAW) competition.
Towards Intrinsic Common Discriminative Features Learning for Face Forgery Detection using Adversarial Learning
Existing face forgery detection methods usually treat face forgery detection as a binary classification problem and adopt deep convolution neural networks to learn discriminative features.
Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models
In this paper, we propose a novel adversarial en-semble training approach that jointly learns the label dependencies and member models.
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.
Emergence of Double-slit Interference by Representing Visual Space in Artificial Neural Networks
Artificial neural networks have realized incredible successes at image recognition, but the underlying mechanism of visual space representation remains a huge mystery.
BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models
In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process.
Real-time Online Multi-Object Tracking in Compressed Domain
Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance.
Bayesian Negative Sampling for Recommendation
Although previous studies have proposed some approaches to sample informative instances, few has been done to discriminating false negative from true negative for unbiased negative sampling.
i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems
Noisy features and inappropriate embedding dimension assignments can deteriorate the performance of recommender systems and introduce unnecessary complexity in model training and online serving.
EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition
Speech emotion recognition (SER) is an important research topic in human-computer interaction.
GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation
To this end, we propose a novel framework for incomplete multimodal learning in conversations, called "Graph Complete Network (GCNet)", filling the gap of existing works.
WSLRec: Weakly Supervised Learning for Neural Sequential Recommendation Models
Motivated by the observation that model-free methods like behavioral retargeting (BR) and item-based collaborative filtering (ItemCF) hit different parts of the user-item relevance compared to neural sequential recommendation models, we propose a novel model-agnostic training approach called WSLRec, which adopts a three-stage framework: pre-training, top-$k$ mining, and fine-tuning.
ADD 2022: the First Audio Deep Synthesis Detection Challenge
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021.
PFGE: Parsimonious Fast Geometric Ensembling of DNNs
Ensemble methods are commonly used to enhance the generalization performance of machine learning models.
Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation
In this paper, we propose a novel method to extend ANN search to arbitrary matching functions, e. g., a deep neural network.
Multiple Similarity Drug-Target Interaction Prediction with Random Walks and Matrix Factorization
Moreover, the validation of highly ranked non-interacting pairs also demonstrates the potential of MDMF2A to discover novel DTIs.
Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation
In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector.
Ranked #7 on
Multi-Object Tracking
on MOT16
(using extra training data)
Stochastic Weight Averaging Revisited
PSWA outperforms its backbone SGD remarkably, providing experimental evidences for the existence of global geometric structures.
Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems
In our study, we use real data sets and the state-of-the-art machine learning model to evaluate our attack detection scheme and the results confirm the effectiveness of our detection method.
Unsupervised Finetuning
This problem is more challenging than the supervised counterpart, as the low data density in the small-scale target data is not friendly for unsupervised learning, leading to the damage of the pretrained representation and poor representation in the target domain.
Asymmetric Graph Representation Learning
We define an incoming embedding and an outgoing embedding for each node to model its sending and receiving features respectively.
ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation
Third, we compute the similarities between each pixel representation and the image-level contextual information, the semantic-level contextual information, respectively.
Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks
Current model selection methods all require access to a batch of labeled data for computing a pre-specified performance metric, such as the cross-entropy loss, the classification error rate and the negative log-likelihood.
Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach
Accordingly, accurate detection of illicit drug trafficking events (IDTEs) from social media has become even more challenging.
Identifying Illicit Drug Dealers on Instagram with Large-scale Multimodal Data Fusion
Unlike existing methods that focus on posting-based detection, we propose to tackle the problem of illicit drug dealer identification by constructing a large-scale multimodal dataset named Identifying Drug Dealers on Instagram (IDDIG).
Escaping the Gradient Vanishing: Periodic Alternatives of Softmax in Attention Mechanism
Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms.
Abnormal Behavior Detection Based on Target Analysis
To this end, we propose a multivariate fusion method that analyzes each target through three branches: object, action and motion.
Cascaded Residual Density Network for Crowd Counting
Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes.
Improve Unsupervised Pretraining for Few-label Transfer
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets.
Robust Dynamic Multi-Modal Data Fusion: A Model Uncertainty Perspective
Then the problem of concern is formalized as a task of nonlinear non-Gaussian state filtering under model uncertainty, which is addressed by a dynamic model averaging (DMA) based particle filter (PF) algorithm.
Optimizing Area Under the Curve Measures via Matrix Factorization for Predicting Drug-Target Interaction with Multiple Similarities
In drug discovery, identifying drug-target interactions (DTIs) via experimental approaches is a tedious and expensive procedure.
Intelligent Decision Method for Main Control Parameters of Tunnel Boring Machine based on Multi-Objective Optimization of Excavation Efficiency and Cost
Therefore, this paper proposes an intelligent decision method for the main control parameters of the TBM based on the multi-objective optimization of excavation efficiency and cost.
"Weak AI" is Likely to Never Become "Strong AI", So What is its Greatest Value for us?
AI has surpassed humans across a variety of tasks such as image classification, playing games (e. g., go, "Starcraft" and poker), and protein structure prediction.
Diverse Semantic Image Synthesis via Probability Distribution Modeling
In this paper, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level.
Ranked #1 on
Image-to-Image Translation
on ADE20K Labels-to-Photos
(LPIPS metric)
Bayesian adversarial multi-node bandit for optimal smart grid protection against cyber attacks
The cybersecurity of smart grids has become one of key problems in developing reliable modern power and energy systems.
A Random Algorithm for Profit Maximization with Multiple Adoptions in Online Social Networks
Through "word of mouth" effects, information or product adoption could spread from some influential individuals to millions of users in social networks.
Social and Information Networks
Data Poisoning Attacks to Deep Learning Based Recommender Systems
Specifically, we formulate our attack as an optimization problem, such that the injected ratings would maximize the number of normal users to whom the target items are recommended.
Drug-Target Interaction Prediction via an Ensemble of Weighted Nearest Neighbors with Interaction Recovery
In addition, WkNNIR exploits local imbalance to promote the influence of more reliable similarities on the interaction recovery and prediction processes.
Learning distributed sentence vectors with bi-directional 3D convolutions
Similar to the Bi-LSTM, these n-gram detectors learn both forward and backward distributional semantic knowledge from the sentence tensor.
Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning
This paper proposes a deep time delay neural network (TDNN) for speech enhancement with full data learning.
Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition
The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Context-Dependent Domain Adversarial Neural Network for Multimodal Emotion Recognition
Emotion recognition remains a complex task due to speaker variations and low-resource training samples.
Ranked #1 on
Speech Emotion Recognition
on IEMOCAP
(using extra training data)
Enhanced Lidov-Kozai migration and the formation of the transiting giant planet WD1856+534b
By requiring that perturbations from the companion stars be able to overcome short-range forces and excite the planet's eccentricity to $e \simeq 1$, we obtain an absolute limit of $a_{1} \gtrsim 8 \, {\rm AU} \, (a_{3} / 1500 \, {\rm AU})^{6/7}$ for the planet's semi-major axis just before migration (where $a_{3}$ is the semi-major axis of the 'outer' orbit).
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Quantum droplets in two-dimensional optical lattices
We study the stability of zero-vorticity and vortex lattice quantum droplets (LQDs), which are described by a two-dimensional (2D) Gross-Pitaevskii (GP) equation with a periodic potential and Lee-Huang-Yang (LHY) term.
Pattern Formation and Solitons Quantum Physics
Parametric Instance Classification for Unsupervised Visual Feature Learning
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning.
A Deep Learning Approach to Quasar Continuum Prediction
We apply iQNet and predict the continua of $\sim$3200 SDSS-DR16 quasar spectra at higher redshift ($2< z \leq 5$) and measure the redshift evolution of mean transmitted flux ($< F >$) in the Ly-$\alpha$ forest region.
Astrophysics of Galaxies
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Multi-Label Sampling based on Local Label Imbalance
Experimental results on 13 multi-label datasets demonstrate the effectiveness of the proposed measure and sampling approaches for a variety of evaluation metrics, particularly in the case of an ensemble of classifiers trained on repeated samples of the original data.
Simultaneous Denoising and Dereverberation Using Deep Embedding Features
In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC).
Density-Aware Graph for Deep Semi-Supervised Visual Recognition
Motivated by these limitations, this paper proposes to solve the SSL problem by building a novel density-aware graph, based on which the neighborhood information can be easily leveraged and the feature learning and label propagation can also be trained in an end-to-end way.
Negative Margin Matters: Understanding Margin in Few-shot Classification
This paper introduces a negative margin loss to metric learning based few-shot learning methods.
AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model.
Ranked #29 on
Click-Through Rate Prediction
on Criteo
Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
Secondly, to pay more attention to the outputs of the pre-separation stage, an attention module is applied to acquire deep attention fusion features, which are extracted by computing the similarity between the mixture and the pre-separated speech.
Cross-modality Person re-identification with Shared-Specific Feature Transfer
In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance.
Cross-Modality Person Re-identification
Person Re-Identification
Uncovering Insurance Fraud Conspiracy with Network Learning
In order to detect and prevent fraudulent insurance claims, we developed a novel data-driven procedure to identify groups of organized fraudsters, one of the major contributions to financial losses, by learning network information.
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
Specifically, we apply the deep clustering network to extract deep embedding features.
Concise and Effective Network for 3D Human Modeling from Orthogonal Silhouettes
In this paper, we revisit the problem of 3D human modeling from two orthogonal silhouettes of individuals (i. e., front and side views).
GPRInvNet: Deep Learning-Based Ground Penetrating Radar Data Inversion for Tunnel Lining
The results have demonstrated that the GPRInvNet is capable of effectively reconstructing complex tunnel lining defects with clear boundaries.
Text classification with pixel embedding
The first two dimensions of the convolutional kernel size equal the size of the word image and the last dimension of the kernel size is $n$.
Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces
Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities.
Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
Prior works on speech emotion recognition utilize various unsupervised learning approaches to deal with low-resource samples.
Domain adversarial learning for emotion recognition
The secondary task is to learn a common representation where speaker identities can not be distinguished.
Conversational Emotion Analysis via Attention Mechanisms
Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis.
Normal Estimation for 3D Point Clouds via Local Plane Constraint and Multi-scale Selection
Then we use multi-task optimization to train the normal estimation and local plane classification tasks simultaneously. Also, to integrate the advantages of multi-scale results, a scale selection strategy is adopted, which is a data-driven approach for selecting the optimal scale around each point and encourages subnetwork specialization.
Sequential Learning for Dirichlet Process Mixtures
We propose an evidence upper bound (EUBO) to act as the surrogate loss, and fit a DP mixture to the given data by minimizing the EUBO, which is equivalent to minimizing the KL-divergence between the target distribution and the DP mixture.
Memory-Based Neighbourhood Embedding for Visual Recognition
Learning discriminative image feature embeddings is of great importance to visual recognition.
Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features
Firstly, a DC network is trained to extract deep embedding features, which contain each source's information and have an advantage in discriminating each target speakers.
Sequential online prediction in the presence of outliers and change points: an instant temporal structure learning approach
We propose an INstant TEmporal structure Learning (INTEL) algorithm to address this problem.
Synthetic Oversampling of Multi-Label Data based on Local Label Distribution
Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods.
A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis
Multiple-object tracking and behavior analysis have been the essential parts of surveillance video analysis for public security and urban management.
Deep Learning Inversion of Electrical Resistivity Data
According to the comprehensive qualitative analysis and quantitative comparison, ERSInvNet with tier feature map, smooth constraints, and depth weighting function together achieve the best performance.
Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction
Easy-to-use, Modular and Extendible package of deep-learning based CTR models. DeepFM, DeepInterestNetwork(DIN), DeepInterestEvolutionNetwork(DIEN), DeepCrossNetwork(DCN), AttentionalFactorizationMachine(AFM), Neural Factorization Machine(NFM), AutoInt, Deep Session Interest Network(DSIN)
Ranked #1 on
Click-Through Rate Prediction
on Huawei App Store
Semantics Disentangling for Text-to-Image Generation
Synthesizing photo-realistic images from text descriptions is a challenging problem.
Context and Attribute Grounded Dense Captioning
Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language.
Ranked #3 on
Dense Captioning
on Visual Genome
Harnessing Low-Fidelity Data to Accelerate Bayesian Optimization via Posterior Regularization
Bayesian optimization (BO) is a powerful paradigm for derivative-free global optimization of a black-box objective function (BOF) that is expensive to evaluate.
Deep Triplet Quantization
We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets.
Ranked #1 on
Image Retrieval
on NUS-WIDE
Transfer-Learning Oriented Class Imbalance Learning for Cross-Project Defect Prediction
(2) feature weighting (FW) strategy improves the average G-Measure by 11\%, and the average MCC by 29. 2\%.
Deep-Learning Inversion of Seismic Data
We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i. e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs).
Deep Metric Transfer for Label Propagation with Limited Annotated Data
In this paper, we propose a generic framework that utilizes unlabeled data to aid generalization for all three tasks.
Real-Time Anomaly Detection With HMOF Feature
Most existing methods are computation consuming, which cannot satisfy the real-time requirement.
What and Where: A Context-based Recommendation System for Object Insertion
In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes.
A Very Brief and Critical Discussion on AutoML
This contribution presents a very brief and critical discussion on automated machine learning (AutoML), which is categorized here into two classes, referred to as narrow AutoML and generalized AutoML, respectively.
Cross-Modal Hamming Hashing
Extensive experiments demonstrate that CMHH can generate highly concentrated hash codes and achieve state-of-the-art cross-modal retrieval performance for both hash lookups and linear scan scenarios on three benchmark datasets, NUS-WIDE, MIRFlickr-25K, and IAPR TC-12.
A Particle Filter based Multi-Objective Optimization Algorithm: PFOPS
To this end, we make an effort to extend the scope of application of the PFO paradigm to multi-objective optimization (MOO) cases.
Making Classifier Chains Resilient to Class Imbalance
Class imbalance is an intrinsic characteristic of multi-label data.
Particle Filtering Methods for Stochastic Optimization with Application to Large-Scale Empirical Risk Minimization
There is a recent interest in developing statistical filtering methods for stochastic optimization (FSO) by leveraging a probabilistic perspective of incremental proximity methods (IPMs).
Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors.
HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN
The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information.
Deep Cauchy Hashing for Hamming Space Retrieval
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding.
Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training
In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Distilling Knowledge Using Parallel Data for Far-field Speech Recognition
The close-talking model is called the teacher model.
Simultaneous Modeling of Multiple Complications for Risk Profiling in Diabetes Care
The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified.
Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications.
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
The visibility map of the target is learned and used for inferring the spatial attention map.
Maximum Likelihood Estimation based on Random Subspace EDA: Application to Extrasolar Planet Detection
A population based searching method, called estimation of distribution algorithm (EDA), is adopted to explore the model parameter space starting from a batch of random locations.
Tensor Decomposition via Variational Auto-Encoder
Another assumption of these methods is that a predefined rank should be known.
Student's t Distribution based Estimation of Distribution Algorithms for Derivative-free Global Optimization
Observing that the Student's t distribution has heavier and longer tails than the Gaussian, which may be beneficial for exploring the solution space, we propose a novel EDA algorithm termed ESTDA, in which the Student's t distribution, rather than Gaussian, is employed.
Vision-based Traffic Flow Prediction using Dynamic Texture Model and Gaussian Process
The proposed method consists of three elemental operators, that are dynamic texture model based motion segmentation, feature extraction and Gaussian process (GP) regression.
Ternary Weight Networks
We present a memory and computation efficient ternary weight networks (TWNs) - with weights constrained to +1, 0 and -1.
Robust video object tracking via Bayesian model averaging based feature fusion
In this article, we are concerned with tracking an object of interest in video stream.
Robust video object tracking using particle filter with likelihood based feature fusion and adaptive template updating
In this solution, the bootstrap particle filter (PF) is initialized by an object detector, which models the time-evolving background of the video signal by an adaptive Gaussian mixture.
