Search Results for author:
Found 37 papers, 17 papers with code
Counting Stacked Objects from Multi-View Images
Visual object counting is a fundamental computer vision task underpinning numerous real-world applications, from cell counting in biomedicine to traffic and wildlife monitoring.
Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
To improve the model's compositional ability, we propose a method for mining these reliable cases, resulting in a curated training set of generated images without requiring any manual annotation.
Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting
Existing 3D OCF approaches struggle to predict plausible spatial details for movable objects and suffer from slow inference speeds due to neglecting the bias and uneven distribution of changing occupancy states in both space and time.
SIFM: A Foundation Model for Multi-granularity Arctic Sea Ice Forecasting
Arctic sea ice performs a vital role in global climate and has paramount impacts on both polar ecosystems and coastal communities.
IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior
Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate.
GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving
Place recognition is a crucial module to ensure autonomous vehicles obtain usable localization information in GPS-denied environments.
Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation
The training signals for this predictor are obtained through our emotion-agnostic intensity pseudo-labeling method without the need of frame-wise intensity labeling.
GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning
3DGS utilizes multi-view rendered images as input to generate enhanced point cloud distributions and novel view images, facilitating data augmentation and cross-modal contrastive learning.
Assessing Sample Quality via the Latent Space of Generative Models
We show that the proposed score correlates highly with the sample quality for various generative models including VAEs, GANs and Latent Diffusion Models.
RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering
3D Gaussian Splatting (3D-GS) has made a notable advancement in the field of neural rendering, 3D scene reconstruction, and novel view synthesis.
Lightening Anything in Medical Images
The development of medical imaging techniques has made a significant contribution to clinical decision-making.
MFA-Net: Multi-Scale feature fusion attention network for liver tumor segmentation
Though recent methods based on Fully Convolutional Neural Networks (F-CNNs) have shown success in many segmentation tasks, fusing features from images with different scales is still a challenge: (1) Due to the lack of spatial awareness, F-CNNs share the same weights at different spatial locations.
Unifying Lane-Level Traffic Prediction from a Graph Structural Perspective: Benchmark and Baseline
Traffic prediction has long been a focal and pivotal area in research, witnessing both significant strides from city-level to road-level predictions in recent years.
Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing).
Explicit Interaction for Fusion-Based Place Recognition
Fusion-based place recognition is an emerging technique jointly utilizing multi-modal perception data, to recognize previously visited places in GPS-denied scenarios for robots and autonomous vehicles.
3D Gaussian as a New Era: A Survey
3D Gaussian Splatting (3D-GS) has emerged as a significant advancement in the field of Computer Graphics, offering explicit scene representation and novel view synthesis without the reliance on neural networks, such as Neural Radiance Fields (NeRF).
Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications
Furthermore, the standardized evaluation protocol for preset multiple tasks is also provided to compare the performance of all the proposed baselines on present and future occupancy estimation with respect to objects of interest in autonomous driving scenarios.
LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition
However, most existing multimodal place recognition methods only use limited field-of-view camera images, which leads to an imbalance between features from different modalities and limits the effectiveness of sensor fusion.
Zero-Shot Object Counting with Language-Vision Models
Thus, we propose zero-shot object counting (ZSC), a new setting where only the class name is available during test time.
Enforcing 3D Topological Constraints in Composite Objects via Implicit Functions
Medical applications often require accurate 3D representations of complex organs with multiple parts, such as the heart and spine.
Learning from Pseudo-labeled Segmentation for Multi-Class Object Counting
In this paper, we point out that the task of counting objects of interest when there are multiple object classes in the image (namely, multi-class object counting) is particularly challenging for current object counting models.
Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection
To mitigate this issue, we propose a novel variational autoencoder (VAE) based data generation model, which is capable of generating data with increased crop-related diversity.
Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
We introduce algebraic machine reasoning, a new reasoning framework that is well-suited for abstract reasoning.
Zero-shot Object Counting
By applying this model to all the candidate patches, we can select the most suitable patches as exemplars for counting.
Ranked #7 on
Zero-Shot Counting
on FSC147
CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data
LiDAR-based place recognition (LPR) is one of the most crucial components of autonomous vehicles to identify previously visited places in GPS-denied environments.
SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data
It uses multi-scale transformers to generate a global descriptor for each sequence of LiDAR range images in an end-to-end fashion.
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.
Generating Representative Samples for Few-Shot Classification
To mitigate this issue, we propose to generate visual samples based on semantic embeddings using a conditional variational autoencoder (CVAE) model.
FedCorr: Multi-Stage Federated Learning for Label Noise Correction
Although there exist methods in centralized learning for tackling label noise, such methods do not perform well on heterogeneous label noise in FL settings, due to the typically smaller sizes of client datasets and data privacy requirements in FL.
A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles
Different exploration methods of DRL, including adding action space noise and parameter space noise, are compared against each other in the transfer learning process in this work.
Training Classifiers that are Universally Robust to All Label Noise Levels
In particular, we shall assume that a small subset of any given noisy dataset is known to have correct labels, which we treat as "positive", while the remaining noisy subset is treated as "unlabeled".
Ranked #7 on
Image Classification
on Clothing1M (using clean data)
(using extra training data)
Variational Feature Disentangling for Fine-Grained Few-Shot Classification
We assume that the distribution of intra-class variance generalizes across the base class and the novel class.
Ranked #16 on
Few-Shot Image Classification
on CUB 200 5-way 5-shot
Learning Clusterable Visual Features for Zero-Shot Recognition
However, some testing data are considered "hard" as they lie close to the decision boundaries and are prone to misclassification, leading to performance degradation for ZSL.
GOMP: Grasp-Optimized Motion Planning for Bin Picking
Rapid and reliable robot bin picking is a critical challenge in automating warehouses, often measured in picks-per-hour (PPH).
Robotics
A Semantic Loss Function for Deep Learning with Symbolic Knowledge
This paper develops a novel methodology for using symbolic knowledge in deep learning.
