Search Results for author:
Found 170 papers, 81 papers with code
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.
VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism.
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
The I2V model is designed to produce videos that strictly adhere to the content of the provided reference image, preserving its content, structure, and style.
Ranked #3 on
Text-to-Video Generation
on EvalCrafter Text-to-Video (ECTV) Dataset
(using extra training data)
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
Based on this stronger coupling, we shift the distribution to higher quality without motion degradation by finetuning spatial modules with high-quality images, resulting in a generic high-quality video model.
Ranked #1 on
Text-to-Video Generation
on EvalCrafter Text-to-Video (ECTV) Dataset
(using extra training data)
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
In this work, we propose to train CNNs from images annotated with multiple tags, to enhance the quality of visual representation of the trained CNN model.
DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
Animating a still image offers an engaging visual experience.
Personalized Cross-Silo Federated Learning on Non-IID Data
Non-IID data present a tough challenge for federated learning.
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
We also have a better zero-shot shape-aware editing ability based on the text-to-video model.
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
Our framework elevates the resolution of the synthesized talking face to 1024*1024 for the first time, even though the training dataset has a lower resolution.
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
Ranked #10 on
Motion Synthesis
on HumanML3D
OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models
We also observe that the initiation denoising timestep for noise blending is the key to identity preservation and layout.
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
We propose a novel 3D GAN framework for unsupervised learning of generative, high-quality and 3D-consistent facial avatars from unstructured 2D images.
High-Fidelity GAN Inversion for Image Attribute Editing
With a low bit-rate latent code, previous works have difficulties in preserving high-fidelity details in reconstructed and edited images.
ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
Our work also suggests that a pre-trained diffusion model trained on low-resolution images can be directly used for high-resolution visual generation without further tuning, which may provide insights for future research on ultra-high-resolution image and video synthesis.
Latent Video Diffusion Models for High-Fidelity Long Video Generation
Diffusion models have shown remarkable results recently but require significant computational resources.
Ranked #2 on
Video Generation
on Taichi
DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
In this paper, we introduce a novel self-supervised disentanglement framework to decouple pose and expression without 3DMMs and paired data, which consists of a motion editing module, a pose generator, and an expression generator.
AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
For appearance control, we borrow intermediate latents and their features from the text-to-image (T2I) generation for ensuring the generated first frame is equal to the given generated image.
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
With the availability of large-scale video datasets and the advances of diffusion models, text-driven video generation has achieved substantial progress.
Inserting Anybody in Diffusion Models via Celeb Basis
Empowered by the proposed celeb basis, the new identity in our customized model showcases a better concept combination ability than previous personalization methods.
TaleCrafter: Interactive Story Visualization with Multiple Characters
Accurate Story visualization requires several necessary elements, such as identity consistency across frames, the alignment between plain text and visual content, and a reasonable layout of objects in images.
Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation
For the first module, we leverage an off-the-shelf video retrieval system and extract video depths as motion structure.
FENeRF: Face Editing in Neural Radiance Fields
2D GANs can generate high fidelity portraits but with low view consistency.
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework
We adopt a two-stage training strategy for the diffusion model, effectively binding movements with specific appearances.
UCF: Uncovering Common Features for Generalizable Deepfake Detection
Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries.
DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
To fill this gap, we present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions: 1) a unified data management system to ensure consistent input across all detectors, 2) an integrated framework for state-of-the-art methods implementation, and 3) standardized evaluation metrics and protocols to promote transparency and reproducibility.
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point.
ReliableSwap: Boosting General Face Swapping Via Reliable Supervision
To avoid the potential artifacts and drive the distribution of the network output close to the natural one, we reversely take synthetic images as input while the real face as reliable supervision during the training stage of face swapping.
StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter
To address these challenges, we introduce StyleCrafter, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image.
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability.
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Following this principle, we propose to enrich the "diversity" of forgeries by synthesizing augmented forgeries with a pool of forgery configurations and strengthen the "sensitivity" to the forgeries by enforcing the model to predict the forgery configurations.
DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization
Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user.
E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion
Based on this disentanglement, face swapping can be simplified as style and mask swapping.
High-Fidelity Clothed Avatar Reconstruction from a Single Image
This paper presents a framework for efficient 3D clothed avatar reconstruction.
LAS-AT: Adversarial Training with Learnable Attack Strategy
In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness.
Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities.
Ranked #2 on
Referring Expression Segmentation
on RefCOCO
An Effective and Robust Detector for Logo Detection
Moreover, we have applied the proposed methods to competition ACM MM2021 Robust Logo Detection that is organized by Alibaba on the Tianchi platform and won top 2 in 36489 teams.
CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying
Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing.
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos.
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
Diffusion models have proven to be highly effective in image and video generation; however, they still face composition challenges when generating images of varying sizes due to single-scale training data.
Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection
Such design decomposes the process of HOI set prediction into two subsequent phases, i. e., an interaction proposal generation is first performed, and then followed by transforming the non-parametric interaction proposals into HOI predictions via a structure-aware Transformer.
Ranked #3 on
Human-Object Interaction Detection
on V-COCO
VDTR: Video Deblurring with Transformer
For multi-frame temporal modeling, we adapt Transformer to fuse multiple spatial features efficiently.
E4SRec: An Elegant Effective Efficient Extensible Solution of Large Language Models for Sequential Recommendation
Furthermore, practical ID-based recommendation strategies, reliant on a huge number of unique identities (IDs) to represent users and items, have gained prominence in real-world recommender systems due to their effectiveness and efficiency.
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process.
IMF: Interactive Multimodal Fusion Model for Link Prediction
To this end, we propose a two-stage multimodal fusion framework to preserve modality-specific knowledge as well as take advantage of the complementarity between different modalities.
Generalizable Black-Box Adversarial Attack with Meta Learning
In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget.
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space
Specifically, cheap scene graph supervision data can be easily obtained by parsing image language descriptions into semantic graphs.
Sparse Adversarial Attack via Perturbation Factorization
Based on this factorization, we formulate the sparse attack problem as a mixed integer programming (MIP) to jointly optimize the binary selection factors and continuous perturbation magnitudes of all pixels, with a cardinality constraint on selection factors to explicitly control the degree of sparsity.
Semi-Autoregressive Transformer for Image Captioning
To tackle this issue, non-autoregressive image captioning models have recently been proposed to significantly accelerate the speed of inference by generating all words in parallel.
ChatTraffic: Text-to-Traffic Generation via Diffusion Model
The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations.
BjTT: A Large-scale Multimodal Dataset for Traffic Prediction
The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations.
DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis
Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency.
Improved Test-Time Adaptation for Domain Generalization
Generally, a TTT strategy hinges its performance on two main factors: selecting an appropriate auxiliary TTT task for updating and identifying reliable parameters to update during the test phase.
SimROD: A Simple Adaptation Method for Robust Object Detection
This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD).
Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
We describe an augmented intelligence system for simplifying and enhancing the modeling experience for operations research.
NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description.
Domain Generalization via Rationale Invariance
Specifically, we propose treating the element-wise contributions to the final results as the rationale for making a decision and representing the rationale for each sample as a matrix.
Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method.
Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
The ambiguity naturally leads to the issue of \emph{implicit multi-label}, motivating the need for diverse predictions.
Prior-Guided Adversarial Initialization for Fast Adversarial Training
Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process.
Adversarial Attack
Adversarial Attack on Video Classification
CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks.
A deep learning-based remaining useful life prediction approach for bearings
In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs).
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Due to the sequential dependencies among words in a caption, we formulate the generation of adversarial noises for targeted partial captions as a structured output learning problem with latent variables.
Online Portfolio Management via Deep Reinforcement Learning with High-Frequency Data
In addition, while the vast majority of SOTA strategies maintain a poor turnover rate of approximately greater than 50% on average, our framework enjoys a relatively low turnover rate on all datasets, efficiency analysis illustrates that our framework no longer has the quadratic dependency limitation.
Auto-Split: A General Framework of Collaborative Edge-Cloud AI
At the same time, large amounts of input data are collected at the edge of cloud.
Towards Real-World Video Deblurring by Exploring Blur Formation Process
We believe the novel realistic synthesis pipeline and the corresponding RAW video dataset can help the community to easily construct customized blur datasets to improve real-world video deblurring performance largely, instead of laboriously collecting real data pairs.
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing answers.
GasHisSDB: A New Gastric Histopathology Image Dataset for Computer Aided Diagnosis of Gastric Cancer
In order to prove that the methods of different periods in the field of image classification have discrepancies on GasHisSDB, we select a variety of classifiers for evaluation.
ETran: Energy-Based Transferability Estimation
This is the first work that proposes transferability estimation for object detection task.
Ranked #1 on
Transferability
on classification benchmark
Few-shot Object Localization
This task achieves generalized object localization by leveraging a small number of labeled support samples to query the positional information of objects within corresponding images.
Estimating Visual Information From Audio Through Manifold Learning
Therefore, audio-based methods can be useful even for applications in which only visual information is of interest Our framework is based on Manifold Learning and consists of two steps.
AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics
The introduction of ChatGPT and the subsequent improvement of Large Language Models (LLMs) have prompted more and more individuals to turn to the use of ChatBots, both for information and assistance with decision-making.
A Causal Inspired Early-Branching Structure for Domain Generalization
By d-separation, we observe that the causal feature can be further characterized by being independent of the domain conditioned on the object, and we propose the following two strategies as complements for the basic framework.
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
To this end, we propose an Energy-Based Joint Reasoning (EBJR) framework that adaptively distributes the samples between shallow and deep models to achieve an accuracy close to the deep model, but latency close to the shallow one.
Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?
As an attempt to mitigate this dilemma, this paper investigates the idea of combining multiple trained neural networks using unlabeled data.
Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples
Through an extensive set of experiments, we demonstrate the usefulness of the repainted examples in training, for the tasks of image classification (ImageNet) and object detection (COCO), over several state-of-the-art network architectures at different capacities, and across different data availability regimes.
GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation
Knowledge distillation from LLMs is essential for the efficient deployment of language models.
Targeted Advertising Based on Browsing History
Audience interest, demography, purchase behavior and other possible classifications are ex- tremely important factors to be carefully studied in a targeting campaign.
Schatten-$p$ Quasi-Norm Regularized Matrix Optimization via Iterative Reweighted Singular Value Minimization
In particular, we first introduce a class of first-order stationary points for them, and show that the first-order stationary points introduced in [11] for an SPQN regularized $vector$ minimization problem are equivalent to those of an SPQN regularized $matrix$ minimization reformulation.
Human activity recognition based on time series analysis using U-Net
Traditional human activity recognition (HAR) based on time series adopts sliding window analysis method.
Siamese Networks for Semantic Pattern Similarity
Semantic Pattern Similarity is an interesting, though not often encountered NLP task where two sentences are compared not by their specific meaning, but by their more abstract semantic pattern (e. g., preposition or frame).
Unifying Topic, Sentiment & Preference in an HDP-Based Rating Regression Model for Online Reviews
TSPRA combines topics (i. e. product aspects), word sentiment and user preference as regression factors, and is able to perform topic clustering, review rating prediction, sentiment analysis and what we invent as "critical aspect" analysis altogether in one framework.
The Sentimental Value of Chinese Sub-Character Components
Sub-character components of Chinese characters carry important semantic information, and recent studies have shown that utilizing this information can improve performance on core semantic tasks.
MainiwayAI at IJCNLP-2017 Task 2: Ensembles of Deep Architectures for Valence-Arousal Prediction
This paper introduces Mainiway AI Labs submitted system for the IJCNLP 2017 shared task on Dimensional Sentiment Analysis of Chinese Phrases (DSAP), and related experiments.
Penalty Decomposition Methods for Rank Minimization
In this paper we consider general rank minimization problems with rank appearing in either objective function or constraint.
Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation
Facial action unit (AU) intensity estimation plays an important role in affective computing and human-computer interaction.
Classifier Learning With Prior Probabilities for Facial Action Unit Recognition
To alleviate this issue, we propose a knowledge-driven method for jointly learning multiple AU classifiers without any AU annotation by leveraging prior probabilities on AUs, including expression-independent and expression-dependent AU probabilities.
Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation
The majority of methods directly apply supervised learning techniques to AU intensity estimation while few methods exploit unlabeled samples to improve the performance.
Wasserstein-Fisher-Rao Document Distance
As a fundamental problem of natural language processing, it is important to measure the distance between different documents.
Improving Distributed Similarity Join in Metric Space with Error-bounded Sampling
To address the limitation, we propose SP-Join, an end-to-end framework to support distributed similarity join in metric space based on the MapReduce paradigm, which (i) employs an estimation-based stratified sampling method to produce pivots with quality guarantees for any sample size, and (ii) devises an effective cost model as the guideline to split the whole datasets into partition in map and reduce phases according to the sampled pivots.
Databases
Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation
Accurate AU intensity estimation depends on three major elements: image representation, intensity estimator, and supervisory information.
A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed.
Context-Aware Feature and Label Fusion for Facial Action Unit Intensity Estimation With Partially Labeled Data
The latter enables the model to be trained on a partially annotated database.
LAC-Nav: Collision-Free Mutiagent Navigation Based on The Local Action Cells
Based on the realtime updated local action cells, we propose the LAC-Nav approach to navigate the agent with the properly selected velocity; and furthermore, we coupled the local action cell with an adaptive learning framework, in which the effect of selections are evaluated and used as the references for making decisions in the following updates.
Ensemble emotion recognizing with multiple modal physiological signals
Multiple physiological signals fusing models, building the uniform classification model by means of consistent and complementary information from different emotions to improve recognition performance.
Structural-Aware Sentence Similarity with Recursive Optimal Transport
Moreover, we further develop Recursive Optimal Similarity (ROTS) for sentences with the valuable semantic insights from the connections between cosine similarity of weighted average of word vectors and optimal transport.
Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition
To facilitate end-to-end training, we further develop a scenario context information extraction branch to extract context information from raw RGB video directly.
Ranked #83 on
Skeleton Based Action Recognition
on NTU RGB+D
Controllable Descendant Face Synthesis
Most of the existing methods train models for one-versus-one kin relation, which only consider one parent face and one child face by directly using an auto-encoder without any explicit control over the resemblance of the synthesized face to the parent face.
Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
In this work, we study the detection of adversarial examples, based on the assumption that the output and internal responses of one DNN model for both adversarial and benign examples follow the generalized Gaussian distribution (GGD), but with different parameters (i. e., shape factor, mean, and variance).
Too Much Information Kills Information: A Clustering Perspective
Clustering is one of the most fundamental tools in the artificial intelligence area, particularly in the pattern recognition and learning theory.
Adaptive Tree Wasserstein Minimization for Hierarchical Generative Modeling
In this work, we consider OT over tree metrics, which is more general than the sliced Wasserstein and includes the sliced Wasserstein as a special case, and we propose a fast minimization algorithm in $O(n)$ for the optimal Wasserstein-1 transport plan between two distributions in the tree structure.
Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction
In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment.
A Relaxed Matching Procedure for Unsupervised BLI
Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest.
Dual ResGCN for Balanced Scene GraphGeneration
We propose to incorporate the prior about the co-occurrence of relation pairs into the graph to further help alleviate the class imbalance issue.
Automated Prostate Cancer Diagnosis Based on Gleason Grading Using Convolutional Neural Network
The Gleason grading system using histological images is the most powerful diagnostic and prognostic predictor of prostate cancer.
1.23-Tb/s per Wavelength Single-Waveguide On-Chip Optical Interconnect Enabled by Mode-division Multiplexing
We experimentally demonstrate a record net capacity per wavelength of 1. 23~Tb/s over a single silicon-on-insulator (SOI) multimode waveguide for optical interconnects employing on-chip mode-division multiplexing and 11$\times$11 multiple-in-multiple-out (MIMO) digital signal processing.
QoS-aware Link Scheduling Strategy for Data Transmission in SDVN
The original contributions of this paper are summarized as follows: (1) Model the packets collision probability of broadcast or NACK transmission in VANET with the combination theory and investigate the potential influence of miss my packets (MMP) problem.
Networking and Internet Architecture
A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches
This paper reviews the methods of WSI analysis based on machine learning.
A Hierarchical Conditional Random Field-based Attention Mechanism Approach for Gastric Histopathology Image Classification
The HCRF-AM model consists of an Attention Mechanism (AM) module and an Image Classification (IC) module.
Generalizing Face Forgery Detection with High-frequency Features
The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective.
Robust Counterfactual Explanations on Graph Neural Networks
Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition.
Finding Representative Interpretations on Convolutional Neural Networks
Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models.
Data Pricing in Machine Learning Pipelines
We also investigate pricing in the step of collaborative training of machine learning models, and overview pricing machine learning models for end users in the step of machine learning deployment.
An Optimal Resource Allocator of Elastic Training for Deep Learning Jobs on Cloud
Cloud training platforms, such as Amazon Web Services and Huawei Cloud provide users with computational resources to train their deep learning jobs.
FedFair: Training Fair Models In Cross-Silo Federated Learning
In this paper, we first propose a federated estimation method to accurately estimate the fairness of a model without infringing the data privacy of any party.
Achieving Model Fairness in Vertical Federated Learning
To solve it in a federated and privacy-preserving manner, we consider the equivalent dual form of the problem and develop an asynchronous gradient coordinate-descent ascent algorithm, where some active data parties perform multiple parallelized local updates per communication round to effectively reduce the number of communication rounds.
Robust Physical-World Attacks on Face Recognition
Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications.
Improving Fairness for Data Valuation in Horizontal Federated Learning
The success of federated learning depends largely on the participation of data owners.
Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack
To tackle these issues, we propose a class-agnostic and model-agnostic physical adversarial attack model (Meta-Attack), which is able to not only generate robust physical adversarial examples by simulating color and shape distortions, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images.
Boosting Fast Adversarial Training with Learnable Adversarial Initialization
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training.
Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting.
Metro Passenger Flow Prediction via Dynamic Hypergraph Convolution Networks
Metro passenger flow prediction is a strategically necessary demand in an intelligent transportation system to alleviate traffic pressure, coordinate operation schedules, and plan future constructions.
A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method
Data-driven methods for remaining useful life (RUL) prediction normally learn features from a fixed window size of a priori of degradation, which may lead to less accurate prediction results on different datasets because of the variance of local features.
Mining Minority-class Examples With Uncertainty Estimates
In the real world, the frequency of occurrence of objects is naturally skewed forming long-tail class distributions, which results in poor performance on the statistically rare classes.
ML4CO: Is GCNN All You Need? Graph Convolutional Neural Networks Produce Strong Baselines For Combinatorial Optimization Problems, If Tuned and Trained Properly, on Appropriate Data
The 2021 NeurIPS Machine Learning for Combinatorial Optimization (ML4CO) competition was designed with the goal of improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models.
Fair and efficient contribution valuation for vertical federated learning
We show that VerFedSV not only satisfies many desirable properties for fairness but is also efficient to compute, and can be adapted to both synchronous and asynchronous vertical federated learning algorithms.
Jointly Learning Knowledge Embedding and Neighborhood Consensus with Relational Knowledge Distillation for Entity Alignment
We adopt GCN-based models to learn the representation of entities by considering the graph structure and incorporating the relation semantic information into GCN via knowledge distillation.
EBHI:A New Enteroscope Biopsy Histopathological H&E Image Dataset for Image Classification Evaluation
Traditional machine learning methods achieve maximum accuracy of 76. 02% and deep learning method achieves a maximum accuracy of 95. 37%.
Self-Attention for Incomplete Utterance Rewriting
In this paper, we propose a novel method by directly extracting the coreference and omission relationship from the self-attention weight matrix of the transformer instead of word embeddings and edit the original text accordingly to generate the complete utterance.
How and what to learn:The modes of machine learning
We consider weights in pathways that link neurons longitudinally from input neurons to output neurons, or simply weight pathways, as the basic units for understanding a neural network, and decompose a neural network into a series of subnetworks of such weight pathways.
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models
As such, it can be applied to black-box pre-trained models without a need for architectural manipulations, reassembling of modules, or re-training.
Membership Privacy Protection for Image Translation Models via Adversarial Knowledge Distillation
Image-to-image translation models are shown to be vulnerable to the Membership Inference Attack (MIA), in which the adversary's goal is to identify whether a sample is used to train the model or not.
Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach
In complex problems with large state and action spaces, it is advantageous to extend MAPG methods to use higher-level actions, also known as options, to improve the policy search efficiency.
Hierarchical Reinforcement Learning
Multi-agent Reinforcement Learning
+3
Cross-subject Action Unit Detection with Meta Learning and Transformer-based Relation Modeling
Ablation study and visualization show that our MARL can eliminate identity-caused differences, thus obtaining a robust and generalized AU discriminative embedding representation.
Fast Adversarial Training with Adaptive Step Size
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.
Spatial Cross-Attention Improves Self-Supervised Visual Representation Learning
Unsupervised representation learning methods like SwAV are proved to be effective in learning visual semantics of a target dataset.
Extending Momentum Contrast with Cross Similarity Consistency Regularization
Contrastive self-supervised representation learning methods maximize the similarity between the positive pairs, and at the same time tend to minimize the similarity between the negative pairs.
Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch
We propose a new approach for solving the data labeling and inference latency issues in combinatorial optimization based on the use of the reinforcement learning (RL) paradigm.
AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data
Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data.
Multi-Camera View Based Proactive BS Selection and Beam Switching for V2X
In this paper, we proposed a multi-camera view based proactive BS selection and beam switching that can predict the optimal BS of the user in the future frame and switch the corresponding beam pair.
Revealing Unfair Models by Mining Interpretable Evidence
The key idea is to find solid evidence in the form of a group of data instances discriminated most by the model.
Knowledge-Injected Federated Learning
Federated learning is an emerging technique for training models from decentralized data sets.
SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding
Our method of semantically meaningful image augmentation for object detection via language grounding, SemAug, starts by calculating semantically appropriate new objects that can be placed into relevant locations in the image (the what and where problems).
A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans
In addition, in order to improve the segmentation performance, we adopt multi-view and multi-window level method, at the same time we employ a fine-tune strategy to mitigate the impact of inconsistent labeling.
Fine-Grained Face Swapping via Regional GAN Inversion
We rethink face swapping from the perspective of fine-grained face editing, \textit{i. e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components.
High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors
Compared with existing works, we obtain superior novel view synthesis results and faithfully face reenactment performance.
3D GAN Inversion with Facial Symmetry Prior
It is natural to associate 3D GANs with GAN inversion methods to project a real image into the generator's latent space, allowing free-view consistent synthesis and editing, referred as 3D GAN inversion.
IPProtect: protecting the intellectual property of visual datasets during data valuation
Data trading is essential to accelerate the development of data-driven machine learning pipelines.
Improving Fast Adversarial Training with Prior-Guided Knowledge
This initialization is generated by using high-quality adversarial perturbations from the historical training process.
Multi-User Matching and Resource Allocation in Vision Aided Communications
Visual perception is an effective way to obtain the spatial characteristics of wireless channels and to reduce the overhead for communications system.
Generating Human Motion From Textual Descriptions With Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance
Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model that is pre-trained for still image synthesis and then promoted for video generation with the introduction of temporal modules.
Robust Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
We hope that the proposed VSSC trigger and implementation approach could inspire future studies on designing more practical triggers in backdoor attacks.
Data-Driven Bilateral Generalized Two-Dimensional Quaternion Principal Component Analysis with Application to Color Face Recognition
A new data-driven bilateral generalized two-dimensional quaternion principal component analysis (BiG2DQPCA) is presented to extract the features of matrix samples from both row and column directions.
Intelligence of Astronomical Optical Telescope: Present Status and Future Perspectives
Artificial intelligence technology has been widely used in astronomy, and new artificial intelligence technologies and application scenarios are constantly emerging.
OpenSiteRec: An Open Dataset for Site Recommendation
As a representative information retrieval task, site recommendation, which aims at predicting the optimal sites for a brand or an institution to open new branches in an automatic data-driven way, is beneficial and crucial for brand development in modern business.
On the Cultural Gap in Text-to-Image Generation
Accordingly, we propose a novel multi-modal metric that considers object-text alignment to filter the fine-tuning data in the target culture, which is used to fine-tune a T2I model to improve cross-cultural generation.
NOFA: NeRF-based One-shot Facial Avatar Reconstruction
In this work, we propose a one-shot 3D facial avatar reconstruction framework that only requires a single source image to reconstruct a high-fidelity 3D facial avatar.
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism
Chinese Automatic Speech Recognition (ASR) error correction presents significant challenges due to the Chinese language's unique features, including a large character set and borderless, morpheme-based structure.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Prompt Guided Copy Mechanism for Conversational Question Answering
Conversational Question Answering (CQA) is a challenging task that aims to generate natural answers for conversational flow questions.
ToonTalker: Cross-Domain Face Reenactment
Moreover, since no paired data is provided, we propose a novel cross-domain training scheme using data from two domains with the designed analogy constraint.
SAI: Solving AI Tasks with Systematic Artificial Intelligence in Communication Network
In the rapid development of artificial intelligence, solving complex AI tasks is a crucial technology in intelligent mobile networks.
ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages
Despite the success of these multi-modal language models with different modalities, there is no existing solution for neural network architectures and natural languages.
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator.
Exact Combinatorial Optimization with Temporo-Attentional Graph Neural Networks
Combinatorial optimization finds an optimal solution within a discrete set of variables and constraints.
Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Process
The rapid advancement of artificial intelligence (AI) techniques has opened up new opportunities to revolutionize various fields, including operations research (OR).
Machine Learning Insides OptVerse AI Solver: Design Principles and Applications
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
Leveraging Biases in Large Language Models: "bias-kNN'' for Effective Few-Shot Learning
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning.
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
In addressing this issue, we are inspired by the notion that a backdoor acts as a shortcut and posit that this shortcut stems from the contrast between the trigger and the data utilized for poisoning.
Fast Gradient Computation for Gromov-Wasserstein Distance
In this way, the original computational bottleneck is broken and the new entropic solution can be obtained with total quadratic time, which is almost optimal complexity.
