Search Results for author:
Found 63 papers, 23 papers with code
PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony.
PerfTracker: Online Performance Troubleshooting for Large-scale Model Training in Production
In this paper, we present PerfTracker, the first online troubleshooting system utilizing fine-grained profiling, to diagnose performance issues of large-scale model training in production.
Sounding Like a Winner? Prosodic Differences in Post-Match Interviews
This study examines the prosodic characteristics associated with winning and losing in post-match tennis interviews.
PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents
Photo retouching is integral to photographic art, extending far beyond simple technical fixes to heighten emotional expression and narrative depth.
Automatically Generating Rules of Malicious Software Packages via Large Language Model
Today's security tools predominantly rely on predefined rules crafted by experts, making them poorly adapted to the emergence of software supply chain attacks.
OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning
This paper presents OmniSage, a large-scale representation framework that learns universal representations for a variety of applications at Pinterest.
Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
Compared to existing methods, Turbo2K is up to 20$\times$ faster for inference, making high-resolution video generation more scalable and practical for real-world applications.
Hiding Images in Diffusion Models by Editing Learned Score Functions
Hiding data using neural networks (i. e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks.
POSTA: A Go-to Framework for Customized Artistic Poster Generation
To train our models, we develop the PosterArt dataset, comprising high-quality artistic posters annotated with layout, typography, and pixel-level stylized text segmentation.
From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification
The rationale of L2RW is that integrating decentralized training into VI-ReID can address privacy concerns in scenarios with limited data-sharing regulation.
Is an Ultra Large Natural Image-Based Foundation Model Superior to a Retina-Specific Model for Detecting Ocular and Systemic Diseases?
DINOv2-large model outperformed RETFound in detecting diabetic retinopathy (AUROC=0. 850-0. 952 vs 0. 823-0. 944, across three datasets, all P<=0. 007) and multi-class eye diseases (AUROC=0. 892 vs. 0. 846, P<0. 001).
VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models
Extensive experiments demonstrate that VENOM achieves superior ASR and image quality compared to prior methods, marking a significant advancement in adversarial example generation and providing insights into model vulnerabilities for improved defense development.
LCFed: An Efficient Clustered Federated Learning Framework for Heterogeneous Data
By leveraging model partitioning and adopting distinct aggregation strategies for each sub-model, LCFed effectively incorporates global knowledge into intra-cluster co-training, achieving optimal training performance.
Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images
This image set comprises the original image as well as versions that have been subjected to varying levels of noise and subsequently denoised using a pre-trained diffusion model.
JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration
Vision-centric perception systems often struggle with unpredictable and coupled weather degradations in the wild.
Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detection
In environmental protection, tree monitoring plays an essential role in maintaining and improving ecosystem health.
3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
We benchmark a wide range of open-sourced and proprietary LMMs, uncovering their limitations in various aspects of 3D awareness, such as height, orientation, location, and multi-object reasoning, as well as their degraded performance on images with uncommon camera viewpoints.
Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization
Specifically, we construct a real-world dataset with 85 snowy videos, and then present a Semi-supervised Video Desnowing Network (SemiVDN) equipped by a novel Distribution-driven Contrastive Regularization.
Ranked #2 on
Snow Removal
on RVSD
(using extra training data)
A load forecasting approach for integrated energy systems based on aggregation hybrid modal decomposition and combined model
To improve the granularity of load decomposition within integrated energy system (IES), a novel multiple load forecasting approach is proposed.
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration.
Learned HDR Image Compression for Perceptually Optimal Storage and Display
High dynamic range (HDR) capture and display have seen significant growth in popularity driven by the advancements in technology and increasing consumer demand for superior image quality.
UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands.
Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model
In zero-shot scenarios, RetiZero achieves Top-5 accuracies of 0. 843 for 15 diseases and 0. 756 for 52 diseases.
Confidence-aware multi-modality learning for eye disease screening
In this study, we propose a novel multi-modality evidential fusion pipeline for eye disease screening.
NeRO: Neural Road Surface Reconstruction
Accurately reconstructing road surfaces is pivotal for various applications especially in autonomous driving.
TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals
Engagement analysis finds various applications in healthcare, education, advertisement, services.
Towards Robust 3D Pose Transfer with Adversarial Learning
This work is driven by the intuition that the robustness of the model can be enhanced by introducing adversarial samples into the training, leading to a more invulnerable model to the noisy inputs, which even can be further extended to directly handling the real-world data like raw point clouds/scans without intermediate processing.
FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data
Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity in federated learning (FL) by grouping similar clients for cluster-wise model training.
Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning
Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facilitating fine-tuning of SR models without requiring paired high-resolution (HR) images.
Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis
Recent progress in multi-modal conditioned face synthesis has enabled the creation of visually striking and accurately aligned facial images.
CoSeR: Bridging Image and Language for Cognitive Super-Resolution
We achieve this by marrying image appearance and language understanding to generate a cognitive embedding, which not only activates prior information from large text-to-image diffusion models but also facilitates the generation of high-quality reference images to optimize the SR process.
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution
In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images.
Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification
Failure to recognize samples from the classes unseen during training is a major limitation of artificial intelligence in the real-world implementation for recognition and classification of retinal anomalies.
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.
Masked Image Training for Generalizable Deep Image Denoising
To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training.
Reliable Multimodality Eye Disease Screening via Mixture of Student's t Distributions
To address this issue, we introduce a novel multimodality evidential fusion pipeline for eye disease screening, EyeMoSt, which provides a measure of confidence for unimodality and elegantly integrates the multimodality information from a multi-distribution fusion perspective.
Prior Information based Decomposition and Reconstruction Learning for Micro-Expression Recognition
To solve this issue, driven by the prior information that the category of ME can be inferred by the relationship between the actions of facial different components, this work designs a novel model that can conform to this prior information and learn ME movement features in an interpretable way.
Graph Representation Learning
Micro Expression Recognition
+1
Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning
Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all encountered classes previously.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Snow Removal in Video: A New Dataset and A Novel Method
We also develop a deep learning framework for video snow removal.
Ranked #4 on
Snow Removal
on RVSD
Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning
We evaluate our approach in simulation for both discrete and continuous state-space domains and illustrate the feasibility of developing a robotic system that can accurately evaluate demonstration sufficiency.
Hiding Images in Deep Probabilistic Models
As an instantiation, we adopt a SinGAN, a pyramid of generative adversarial networks (GANs), to learn the patch distribution of one cover image.
Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network
Transformers have enabled breakthroughs in NLP and computer vision, and have recently began to show promising performance in trajectory prediction for Autonomous Vehicle (AV).
ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest
Learned embeddings for products are an important building block for web-scale e-commerce recommendation systems.
KEMP: Keyframe-Based Hierarchical End-to-End Deep Model for Long-Term Trajectory Prediction
Predicting future trajectories of road agents is a critical task for autonomous driving.
On Learning and Testing of Counterfactual Fairness through Data Preprocessing
Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly.
Geometry-Contrastive Transformer for Generalized 3D Pose Transfer
Specifically, we propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies across the given meshes.
AniFormer: Data-driven 3D Animation with Transformer
Instead, we introduce AniFormer, a novel Transformer-based architecture, that generates animated 3D sequences by directly taking the raw driving sequences and arbitrary same-type target meshes as inputs.
Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
With the strength of deep generative models, 3D pose transfer regains intensive research interests in recent years.
iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
We introduce a new dataset for the emotional artificial intelligence research: identity-free video dataset for Micro-Gesture Understanding and Emotion analysis (iMiGUE).
Attention in Attention Network for Image Super-Resolution
In this work, we attempt to quantify and visualize attention mechanisms in SISR and show that not all attention modules are equally beneficial.
Counterfactual Fairness through Data Preprocessing
Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly.
Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric
To answer the questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing ALgorithms (PIPAL) dataset.
Statistical Inference for Online Decision Making via Stochastic Gradient Descent
Focusing on the statistical inference of online decision making, we establish the asymptotic normality of the parameter estimator produced by our algorithm and the online inverse probability weighted value estimator we used to estimate the optimal value.
Statistical Inference for Online Decision-Making: In a Contextual Bandit Setting
Based on the properties of the parameter estimators, we further show that the in-sample inverse propensity weighted value estimator is asymptotically normal.
AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results
Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details.
Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
Gesture recognition has attracted considerable attention owing to its great potential in applications.
2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework
To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems.
PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration
To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset.
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
Human action recognition from skeleton data, fueled by the Graph Convolutional Network (GCN), has attracted lots of attention, due to its powerful capability of modeling non-Euclidean structure data.
Super-Resolution Perception for Industrial Sensor Data
In this paper, we present the problem formulation and methodology framework of Super-Resolution Perception (SRP) on industrial sensor data.
An Efficient Minibatch Acceptance Test for Metropolis-Hastings
We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data.
Fast Parallel SAME Gibbs Sampling on General Discrete Bayesian Networks
A fundamental task in machine learning and related fields is to perform inference on Bayesian networks.
Experiments on Parallel Training of Deep Neural Network using Model Averaging
Data is partitioned and distributed to different nodes for local model updates, and model averaging across nodes is done every few minibatches.
