Search Results for author:
Found 76 papers, 30 papers with code
Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
Captioned images are widely available on the web, while the captions often contain the names of the subjects in the images.
DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shading
To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading.
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects.
Recent Advances in 3D Gaussian Splatting
The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis.
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping.
Depth Estimation Algorithm Based on Transformer-Encoder and Feature Fusion
This research presents a novel depth estimation algorithm based on a Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset.
Sinkhorn Distance Minimization for Knowledge Distillation
We propose the Sinkhorn Knowledge Distillation (SinKD) that exploits the Sinkhorn distance to ensure a nuanced and precise assessment of the disparity between teacher and student distributions.
Growing from Exploration: A self-exploring framework for robots based on foundation models
In this work, we propose a framework named GExp, which enables robots to explore and learn autonomously without human intervention.
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences.
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
The rapid development of open-source large language models (LLMs) has been truly remarkable.
Guidelines in Wastewater-based Epidemiology of SARS-CoV-2 with Diagnosis
With the global spread and increasing transmission rate of SARS-CoV-2, more and more laboratories and researchers are turning their attention to wastewater-based epidemiology (WBE), hoping it can become an effective tool for large-scale testing and provide more ac-curate predictions of the number of infected individuals.
Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases
We conducted a series of structured experiments to evaluate their performance in various industrial application scenarios, offering a comprehensive perspective on their practical utility.
Building Lane-Level Maps from Aerial Images
In this paper, we introduce for the first time a large-scale aerial image dataset built for lane detection, with high-quality polyline lane annotations on high-resolution images of around 80 kilometers of road.
HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
Extensive experiments demonstrate the effectiveness of HyperDreamer in modeling region-aware materials with high-resolution textures and enabling user-friendly editing.
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents.
GPT4Point: A Unified Framework for Point-Language Understanding and Generation
Multimodal Large Language Models (MLLMs) have excelled in 2D image-text comprehension and image generation, but their understanding of the 3D world is notably deficient, limiting progress in 3D language understanding and generation.
Retargeting Visual Data with Deformation Fields
Seam carving is an image editing method that enable content-aware resizing, including operations like removing objects.
Towards Robust Text Retrieval with Progressive Learning
However, existing embedding models for text retrieval usually have three non-negligible limitations.
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses
State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility.
Geometry-Guided Ray Augmentation for Neural Surface Reconstruction with Sparse Views
In this paper, we propose a novel method for 3D scene and object reconstruction from sparse multi-view images.
1st Place Solution of Egocentric 3D Hand Pose Estimation Challenge 2023 Technical Report:A Concise Pipeline for Egocentric Hand Pose Reconstruction
This report introduce our work on Egocentric 3D Hand Pose Estimation workshop.
Large-Vocabulary 3D Diffusion Model with Transformer
To this end, we propose a novel triplane-based 3D-aware Diffusion model with TransFormer, DiffTF, for handling challenges via three aspects.
Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN
To explore the differences between Transformers and CNNs, we employ a sparse pixel approach to contrastively analyze the distinctions between the two.
Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation
Recently, tensor low-rank representation (TLRR) has become a popular tool for tensor data recovery and clustering, due to its empirical success and theoretical guarantees.
Towards Trustworthy Explanation: On Causal Rationalization
With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction.
Differential Privacy for Class-based Data: A Practical Gaussian Mechanism
In this paper, we present a notion of differential privacy (DP) for data that comes from different classes.
AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance.
Privacy-Preserving In-Context Learning for Large Language Models
Based on the general paradigm of DP-ICL, we instantiate several techniques showing how to privatize ICL for text classification and language generation.
A Randomized Approach for Tight Privacy Accounting
In this paper, we propose a new differential privacy paradigm called estimate-verify-release (EVR), which addresses the challenges of providing a strict upper bound for privacy parameter in DP compositions by converting an estimate of privacy parameter into a formal guarantee.
V3Det: Vast Vocabulary Visual Detection Dataset
2) Hierarchical Category Organization: The vast vocabulary of V3Det is organized by a hierarchical category tree which annotates the inclusion relationship among categories, encouraging the exploration of category relationships in vast and open vocabulary object detection.
Constrained Reinforcement Learning for Predictive Control in Real-Time Stochastic Dynamic Optimal Power Flow
This paper presents a novel primal-dual approach for learning optimal constrained DRL policies for dynamic optimal power flow problems, with the aim of controlling power generations and battery outputs.
Uncovering Adversarial Risks of Test-Time Adaptation
Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts.
LF-checker: Machine Learning Acceleration of Bounded Model Checking for Concurrency Verification (Competition Contribution)
We describe and evaluate LF-checker, a metaverifier tool based on machine learning.
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases.
SLAN: Self-Locator Aided Network for Vision-Language Understanding
By aggregating vision-language information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
In this paper, we introduce a novel dIffusion language modEl pre-training framework for text generation, which we call GENIE.
SLAN: Self-Locator Aided Network for Cross-Modal Understanding
By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction
Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene.
Complex-Value Spatio-temporal Graph Convolutional Neural Networks and its Applications to Electric Power Systems AI
The effective representation, precessing, analysis, and visualization of large-scale structured data over graphs are gaining a lot of attention.
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Our attack can be easily deployed in the real world since it only requires rotating the object, as we show in both image classification and object detection applications.
Human-Robot Commensality: Bite Timing Prediction for Robot-Assisted Feeding in Groups
While existing robotic systems for feeding people with mobility limitations focus on solitary dining, commensality, the act of eating together, is often the practice of choice.
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
First, we uncover a post-hoc workflow underlying most prior work, where defenders passively allow the attack to proceed and then leverage the characteristics of the post-attacked model to uncover poison samples.
Spatio-Temporal Graph Convolutional Neural Networks for Physics-Aware Grid Learning Algorithms
This paper proposes a model-free Volt-VAR control (VVC) algorithm via the spatio-temporal graph ConvNet-based deep reinforcement learning (STGCN-DRL) framework, whose goal is to control smart inverters in an unbalanced distribution system.
Artificial Intelligence Enables Real-Time and Intuitive Control of Prostheses via Nerve Interface
Objective: The next generation prosthetic hand that moves and feels like a real hand requires a robust neural interconnection between the human minds and machines.
Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results
Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration.
Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other.
Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other.
Few-Shot Object Detection via Association and DIscrimination
1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space.
Modeling spatial waves of Wolbachia invasion for controlling mosquito-borne diseases
Field trials and modeling studies have shown that the fraction of infection among the mosquitoes must exceed a threshold level for the infection to persist.
Generalizing Nucleus Recognition Model in Multi-source Images via Pruning
In addition, the model is optimized by fine-tuning on merged domains to eliminate the interference of class mismatching among various domains.
Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation
In inference, we directly use the activation masks from the DA layer as pseudo-labels for segmentation.
Adversarial Robustness under Long-Tailed Distribution
We then perform a systematic study on existing long-tailed recognition methods in conjunction with the adversarial training framework.
Towards Evaluating and Training Verifiably Robust Neural Networks
Recent works have shown that interval bound propagation (IBP) can be used to train verifiably robust neural networks.
RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning
We introduce a new semi-supervised, time series anomaly detection algorithm that uses deep reinforcement learning (DRL) and active learning to efficiently learn and adapt to anomalies in real-world time series data.
Hot electron generation through near-field excitation of plasmonic nanoresonators
We theoretically study hot electron generation through the emission of a dipole source coupled to a nanoresonator on a metal surface.
Optics Mesoscale and Nanoscale Physics
Privacy-Preserving Distributed Optimal Power Flow with Partially Homomorphic Encryption
In this way, the dual update of ADMM can be encrypted by PHE.
A Coarse-to-Fine Auto-Sampler For Long-tailed Image Recognition
The long-tail distributed data in the real world has always been a great challenge for deep learning.
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification.
Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition
To this end, in this work, we present a novel end-to-end 3D lip motion Network (3LMNet) by utilizing the sentence-level 3D lip motion (S3DLM) to recognize speakers in both the text-independent and text-dependent contexts.
TM-NET: Deep Generative Networks for Textured Meshes
We introduce a conditional autoregressive model for texture generation, which can be conditioned on both part geometry and textures already generated for other parts to achieve texture compatibility.
Graphics
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild.
Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions.
Ranked #7 on
Long-tail Learning
on VOC-MLT
Adversarial Robustness of Deep Sensor Fusion Models
First, we find that the fusion model is usually both more accurate, and more robust against single-source attacks than single-sensor deep neural networks.
Meta Segmentation Network for Ultra-Resolution Medical Images
MSN can fast generate the weights of fusion layers through a simple meta-learner, requiring only a few training samples and epochs to converge.
Representation Learning of EHR Data via Graph-Based Medical Entity Embedding
Automatic representation learning of key entities in electronic health record (EHR) data is a critical step for healthcare informatics that turns heterogeneous medical records into structured and actionable information.
Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning
Models have been proposed to extract temporal patterns from longitudinal electronic health records (EHR) for clinical predictive models.
Defending Against Physically Realizable Attacks on Image Classification
Finally, we demonstrate that adversarial training using our new attack yields image classification models that exhibit high robustness against the physically realizable attacks we study, offering the first effective generic defense against such attacks.
AIBench: An Industry Standard Internet Service AI Benchmark Suite
On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.
SDM-NET: Deep Generative Network for Structured Deformable Mesh
At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.
A Mobile Cloud Collaboration Fall Detection System Based on Ensemble Learning
Falls are one of the important causes of accidental or unintentional injury death worldwide.
Predicting Treatment Initiation from Clinical Time Series Data via Graph-Augmented Time-Sensitive Model
Many computational models were proposed to extract temporal patterns from clinical time series for each patient and among patient group for predictive healthcare.
Deep Compressive Autoencoder for Action Potential Compression in Large-Scale Neural Recording
The proposed model is built upon a deep compressive autoencoder (CAE) with discrete latent embeddings.
Human Action Attribute Learning From Video Data Using Low-Rank Representations
Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization.
Learning the nonlinear geometry of high-dimensional data: Models and algorithms
This paper revisits the problem of data-driven learning of these geometric structures and puts forth two new nonlinear geometric models for data describing "related" objects/phenomena.
Painting Analysis Using Wavelets and Probabilistic Topic Models
In this paper, computer-based techniques for stylistic analysis of paintings are applied to the five panels of the 14th century Peruzzi Altarpiece by Giotto di Bondone.
