Search Results for author:
Found 51 papers, 14 papers with code
Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning
While state-of-the-art vision-language models (VLMs) have demonstrated remarkable capabilities in complex visual-text tasks, their success heavily relies on massive model scaling, limiting their practical deployment.
DecoupledGaussian: Object-Scene Decoupling for Physics-Based Interaction
We present DecoupledGaussian, a novel system that decouples static objects from their contacted surfaces captured in-the-wild videos, a key prerequisite for realistic Newtonian-based physical simulations.
SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis
However, the high computational cost of NeRF presents challenges for synthesizing high-resolution (HR) images.
ZenSVI: An Open-Source Software for the Integrated Acquisition, Processing and Analysis of Street View Imagery Towards Scalable Urban Science
Street view imagery (SVI) has been instrumental in many studies in the past decade to understand and characterize street features and the built environment.
Results of the Big ANN: NeurIPS'23 competition
The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect the growing complexity and diversity of workloads.
One-Shot Learning for Pose-Guided Person Image Synthesis in the Wild
Current Pose-Guided Person Image Synthesis (PGPIS) methods depend heavily on large amounts of labeled triplet data to train the generator in a supervised manner.
DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition
In this paper, we address the problem of plausible object placement for the challenging task of realistic image composition.
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
In this paper, we introduce GaussianPrediction, a novel framework that empowers 3D Gaussian representations with dynamic scene modeling and future scenario synthesis in dynamic environments.
Diff3DS: Generating View-Consistent 3D Sketch via Differentiable Curve Rendering
Specifically, we perform perspective projection to render the 3D rational B\'ezier curves into 2D curves, which are subsequently converted to a 2D raster image via our customized differentiable rasterizer.
Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation
In this framework, each agent is specialized in a distinct aspect, such as foreground understanding, diversity enhancement, object integrity protection, and textual prompt consistency.
PGAHum: Prior-Guided Geometry and Appearance Learning for High-Fidelity Animatable Human Reconstruction
In this work, we introduce PGAHum, a prior-guided geometry and appearance learning framework for high-fidelity animatable human reconstruction.
D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes
To address this issue, we propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes.
OSTAF: A One-Shot Tuning Method for Improved Attribute-Focused T2I Personalization
Personalized text-to-image (T2I) models not only produce lifelike and varied visuals but also allow users to tailor the images to fit their personal taste.
SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generation
Notably, SemanticHuman-HD is also the first method to achieve 3D-aware image synthesis at $1024^2$ resolution, benefiting from our proposed 3D-aware super-resolution module.
3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
Text-driven 3D scene generation techniques have made rapid progress in recent years.
TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization
In this paper, we aim for both fast and high-quality implicit field learning, and propose TaylorGrid, a novel implicit field representation which can be efficiently computed via direct Taylor expansion optimization on 2D or 3D grids.
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network.
3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities.
A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models
Notably, models like stable diffusion, which excel in text-to-image synthesis, heighten the risk of copyright infringement and unauthorized distribution. Machine unlearning, which seeks to eradicate the influence of specific data or concepts from machine learning models, emerges as a promising solution by eliminating the \enquote{copyright memories} ingrained in diffusion models.
P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion
Inferring missing regions from severely occluded point clouds is highly challenging.
B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation
In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.
Breaking On-device Training Memory Wall: A Systematic Survey
In this systematic survey, we aim to explore the current state-of-the-art techniques for breaking on-device training memory walls, focusing on methods that can enable larger and more complex models to be trained on resource-constrained devices.
Self-similarity-based super-resolution of photoacoustic angiography from hand-drawn doodles
To address this challenge, we propose a novel approach that employs a super-resolution PAA method trained with forged PAA images.
Network Algebraization and Port Relationship for Power-Electronic-Dominated Power Systems
With this simplest model, the roles of both nodes and the network become apparent. Simulations verify the proposed model framework in the modified 9-bus system.
MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal Representations
Existing cross-modal contrastive representation learning (XM-CLR) methods such as CLIP are not fully suitable for multifold data as they only consider one positive pair and treat other pairs as negative when computing the contrastive loss.
P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification
Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification.
Shape-Aware Fine-Grained Classification of Erythroid Cells
BMEC contains 5, 666 images of individual erythroid cells, each of which is extracted from the bone marrow erythroid cell smears and professionally annotated to one of the four types of erythroid cells.
Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanisms
The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks.
Realization Scheme for Visual Cryptography with Computer-generated Holograms
This method can expand the application range of visual cryptography and further increase the security of visual cryptography.
Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment
More specifically, we develop a dynamic parameter isolation strategy to sequentially update the task-specific parameter subsets, which are non-overlapped with each other.
CAEN: A Hierarchically Attentive Evolution Network for Item-Attribute-Change-Aware Recommendation in the Growing E-commerce Environment
Traditional recommendation systems mainly focus on modeling user interests.
FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs
In this paper, we propose a novel CAM weighting scheme, named FD-CAM, to improve both the faithfulness and discriminability of the CAM-based CNN visual explanation.
Contemporary Recommendation Systems on Big Data and Their Applications: A Survey
This survey paper conducts a comprehensive analysis of the evolution and contemporary landscape of recommendation systems, which have been extensively incorporated across a myriad of web applications.
Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization
The design automation of analog circuits is a longstanding challenge.
FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems
The overhead of these collective communication operations in a distributed AI training system can bottleneck its performance, with more pronounced effects as the number of nodes increases.
Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems.
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders.
Ranked #1 on
Image Compression
on kodak
Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning
The design automation of analog circuits is a longstanding challenge in the integrated circuit field.
Phase-SLAM: Phase Based Simultaneous Localization and Mapping for Mobile Structured Light Illumination Systems
In this paper, we propose a phase based Simultaneous Localization and Mapping (Phase-SLAM) framework for fast and accurate SLI sensor pose estimation and 3D object reconstruction.
A Predictive Online Transient Stability Assessment with Hierarchical Generative Adversarial Networks
In this paper, a new data-driven TSA approach is developed for TSA with fewer data compared to the conventional methods.
SAC-GAN: Structure-Aware Image Composition
Specifically, our network takes the semantic layout features from the input scene image, features encoded from the edges and silhouette in the input object patch, as well as a latent code as inputs, and generates a 2D spatial affine transform defining the translation and scaling of the object patch.
A Modular 1D-CNN Architecture for Real-time Digital Pre-distortion
This study reports a novel hardware-friendly modular architecture for implementing one dimensional convolutional neural network (1D-CNN) digital predistortion (DPD) technique to linearize RF power amplifier (PA) real-time. The modular nature of our design enables DPD system adaptation for variable resource and timing constraints. Our work also presents a co-simulation architecture to verify the DPD performance with an actual power amplifier hardware-in-the-loop. The experimental results with 100 MHz signals show that the proposed 1D-CNN obtains superior performance compared with other neural network architectures for real-time DPD application.
Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting
Recent learning-based inpainting algorithms have achieved compelling results for completing missing regions after removing undesired objects in videos.
Toward Real-world Image Super-resolution via Hardware-based Adaptive Degradation Models
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e. g., bicubic downsampling.
Closed-loop Feedback Registration for Consecutive Images of Moving Flexible Targets
Considering the nature of temporal continuity and consecution of the product images, in this paper, we propose a closed-loop feedback registration algorithm for matching and stitching the deformable printed patterns on a moving flexible substrate.
Fast Wireless Sensor Anomaly Detection based on Data Stream in Edge Computing Enabled Smart Greenhouse
However, traditional anomaly detection algorithms originally designed for anomaly detection in static data have not properly considered the inherent characteristics of data stream produced by wireless sensor such as infiniteness, correlations and concept drift, which may pose a considerable challenge on anomaly detection based on data stream, and lead to low detection accuracy and efficiency.
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes
We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research.
Finding structural hole spanners based on community forest model and diminishing marginal utility in large scale social networks
In this paper, we try to give a more visual and detailed definition of structural hole spanner based on the existing work, and propose a novel algorithm to identify structural hole spanner based on community forest model and diminishing marginal utility.
Identify the cells' nuclei based on the deep learning neural network
The cells' nuclei identification task is also kind of image segmentation.
MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps.
Tractable Fully Bayesian Inference via Convex Optimization and Optimal Transport Theory
We demonstrate with optimal transport theory that when the source distribution can be easily sampled from and the target distribution is log-concave, this can be tractably solved with convex optimization.
