Search Results for author:
Found 38 papers, 6 papers with code
DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
This point cloud serves as the initial state for the centroids of 3D Gaussians.
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation.
TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection
The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement.
BLoad: Enhancing Neural Network Training with Efficient Sequential Data Handling
The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods.
SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment
Unsupervised image-to-image (I2I) translation learns cross-domain image mapping that transfers input from the source domain to output in the target domain while preserving its semantics.
Unsupervised Green Object Tracker (GOT) without Offline Pre-training
The labeling cost and the huge computational complexity hinder their applications on edge devices.
SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets
In this work, we relax both of these assumptions by addressing the problem of adapting a set of models trained independently on uni-modal data to a target domain consisting of unlabeled multi-modal data, without having access to the original source dataset.
Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints
Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training.
A Study on Improving Realism of Synthetic Data for Machine Learning
Synthetic-to-real data translation using generative adversarial learning has achieved significant success in improving synthetic data.
Frequency-domain Learning for Volumetric-based 3D Data Perception
Frequency-domain learning draws attention due to its superior tradeoff between inference accuracy and input data size.
TransUPR: A Transformer-based Uncertain Point Refiner for LiDAR Point Cloud Semantic Segmentation
Uncertain points are sampled from coarse semantic segmentation results of 2D image segmentation where uncertain points are located close to the object boundaries in the 2D range image representation and 3D spherical projection background points.
DDS: Decoupled Dynamic Scene-Graph Generation Network
Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data.
ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction
One school of thought is to encode a latent vector for each point (point latents).
Enhanced Low-resolution LiDAR-Camera Calibration Via Depth Interpolation and Supervised Contrastive Learning
Motivated by the increasing application of low-resolution LiDAR recently, we target the problem of low-resolution LiDAR-camera calibration in this work.
LGSQE: Lightweight Generated Sample Quality Evaluatoin
Despite prolific work on evaluating generative models, little research has been done on the quality evaluation of an individual generated sample.
GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences
Supervised and unsupervised deep trackers that rely on deep learning technologies are popular in recent years.
Not Just Streaks: Towards Ground Truth for Single Image Deraining
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image.
DefakeHop++: An Enhanced Lightweight Deepfake Detector
Second, for discriminant features selection, DefakeHop uses an unsupervised approach while DefakeHop++ adopts a more effective approach with supervision, called the Discriminant Feature Test (DFT).
Unsupervised Lightweight Single Object Tracking with UHP-SOT++
Based on the experimental results, we compare pros and cons of supervised and unsupervised trackers and provide a new perspective to understand the performance gap between supervised and unsupervised methods, which is the third contribution of this work.
Geo-DefakeHop: High-Performance Geographic Fake Image Detection
A robust fake satellite image detection method, called Geo-DefakeHop, is proposed in this work.
Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning
Though thermal cameras are widely used for military applications and increasingly for commercial applications, there is a lack of robust algorithms to robustly exploit the thermal imagery due to the limited availability of labeled thermal data.
UHP-SOT: An Unsupervised High-Performance Single Object Tracker
An unsupervised online object tracking method that exploits both foreground and background correlations is proposed and named UHP-SOT (Unsupervised High-Performance Single Object Tracker) in this work.
GTNet:Guided Transformer Network for Detecting Human-Object Interactions
For detecting HOI, it is important to utilize relative spatial configurations and object semantics to find salient spatial regions of images that highlight the interactions between human object pairs.
Evaluation of Multimodal Semantic Segmentation using RGB-D Data
Our goal is to develop stable, accurate, and robust semantic scene understanding methods for wide-area scene perception and understanding, especially in challenging outdoor environments.
CalibDNN: Multimodal Sensor Calibration for Perception Using Deep Neural Networks
Current perception systems often carry multimodal imagers and sensors such as 2D cameras and 3D LiDAR sensors.
DefakeHop: A Light-Weight High-Performance Deepfake Detector
A light-weight high-performance Deepfake detection method, called DefakeHop, is proposed in this work.
Low-Resolution Face Recognition In Resource-Constrained Environments
A non-parametric low-resolution face recognition model for resource-constrained environments with limited networking and computing is proposed in this work.
Constructing Multilayer Perceptrons as Piecewise Low-Order Polynomial Approximators: A Signal Processing Approach
Through the construction, a one-to-one correspondence between the approximation of an MLP and that of a piecewise low-order polynomial is established.
From Two-Class Linear Discriminant Analysis to Interpretable Multilayer Perceptron Design
Besides input layer $l_{in}$ and output layer $l_{out}$, the MLP of interest consists of two intermediate layers, $l_1$ and $l_2$.
FaceHop: A Light-Weight Low-Resolution Face Gender Classification Method
For gray-scale face images of resolution $32 \times 32$ in the LFW and the CMU Multi-PIE datasets, FaceHop achieves correct gender classification rates of 94. 63% and 95. 12% with model sizes of 16. 9K and 17. 6K parameters, respectively.
Object Detection on Single Monocular Images through Canonical Correlation Analysis
In this report, we propose a two-dimensional CCA(canonical correlation analysis) framework to fuse monocular images and corresponding predicted depth images for basic computer vision tasks like image classification and object detection.
PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification
In PixelHop++, one can control the learning model size of fine-granularity, offering a flexible tradeoff between the model size and the classification performance.
Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion
Such a transformation enables CFCNet to predict features and reconstruct data of missing depth measurements according to their corresponding, transformed RGB features.
Visualization, Discriminability and Applications of Interpretable Saak Features
In this work, we study the power of Saak features as an effort towards interpretable deep learning.
Robustness Of Saak Transform Against Adversarial Attacks
This work investigates the robustness of Saak transform against adversarial attacks towards high performance image classification.
Learning to Prune Filters in Convolutional Neural Networks
Specifically, we introduce a "try-and-learn" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way.
Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks
The 3D-ED-GAN is a 3D convolutional neural network trained with a generative adversarial paradigm to fill missing 3D data in low-resolution.
Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning
A novel neural network architecture is built for scene labeling tasks where one of the variants of the new RNN unit, Gated Recurrent Unit with Explicit Long-range Conditioning (GRU-ELC), is used to model multi scale contextual dependencies in images.
