Search Results for author:
Found 33 papers, 15 papers with code
MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing
To address this challenge, this paper proposes MambaVO, which conducts robust initialization, Mamba-based sequential matching refinement, and smoothed training to enhance the matching quality and improve the pose estimation in deep visual odometry.
Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation
In this study, we propose a novel Feature Fusion Transferability Aware Transformer (FFTAT) to enhance ViT performance in UDA tasks.
Ranked #1 on
Domain Adaptation
on VisDA2017
Towards Real-Time Generation of Delay-Compensated Video Feeds for Outdoor Mobile Robot Teleoperation
Teleoperation is an important technology to enable supervisors to control agricultural robots remotely.
Iterative Convex Optimization for Safety-Critical Model Predictive Control
Most of this research limits discussions to CBFs with relative degree one with respect to the system dynamics.
GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System
GSLAMOT utilizes camera and LiDAR multimodal information as inputs and divides the representation of the dynamic scene into a semantic map for representing the static environment, a trajectory of the ego-agent, and an online maintained Tracklet Graph (TG) for tracking and predicting the 3D poses of the detected mobile objects.
RoCo:Robust Collaborative Perception By Iterative Object Matching and Pose Adjustment
However, in collaborative perception, the quality of object detection based on a modality is highly sensitive to the relative pose errors among the agents.
LIT: Large Language Model Driven Intention Tracking for Proactive Human-Robot Collaboration -- A Robot Sous-Chef Application
Large Language Models (LLM) and Vision Language Models (VLM) enable robots to ground natural language prompts into control actions to achieve tasks in an open world.
DuoSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection
Recent advances in multi-view camera-only 3D object detection either rely on an accurate reconstruction of bird's-eye-view (BEV) 3D features or on traditional 2D perspective view (PV) image features.
Private Wasserstein Distance with Random Noises
Wasserstein distance is a principle measure of data divergence from a distributional standpoint.
InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
In this paper, we introduce InterLUDE, a new approach to enhance SSL made of two parts that each benefit from labeled-unlabeled interaction.
Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis
However, existing deep learning pipelines for assessing AS from echocardiograms have two key limitations.
VOLoc: Visual Place Recognition by Querying Compressed Lidar Map
Then the QPC is compressed by the same GPC, and is aggregated into a global descriptor by an attention-based aggregation module, to query the compressed Lidar map in the vector space.
MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR
Motion prediction has been an essential component of autonomous driving systems since it handles highly uncertain and complex scenarios involving moving agents of different types.
Split-and-Denoise: Protect large language model inference with local differential privacy
Large Language Models (LLMs) excel in natural language understanding by capturing hidden semantics in vector space.
NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems
We theoretically prove the enhancement gained from positive noise by reducing the task complexity defined by information entropy and experimentally show the significant performance gain in large image datasets, such as the ImageNet.
Workshop on Document Intelligence Understanding
Document understanding and information extraction include different tasks to understand a document and extract valuable information automatically.
Systematic comparison of semi-supervised and self-supervised learning for medical image classification
Yet past benchmarks do not focus on medical tasks and rarely compare self- and semi- methods together on an equal footing.
FSD: Fully-Specialized Detector via Neural Architecture Search
Most generic object detectors are mainly built for standard object detection tasks such as COCO and PASCAL VOC.
Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning
To automate screening for AS, deep networks must learn to mimic a human expert's ability to identify views of the aortic valve then aggregate across these relevant images to produce a study-level diagnosis.
AirBirds: A Large-scale Challenging Dataset for Bird Strike Prevention in Real-world Airports
To advance the research and practical solutions for bird strike prevention, in this paper, we present a large-scale challenging dataset AirBirds that consists of 118, 312 time-series images, where a total of 409, 967 bounding boxes of flying birds are manually, carefully annotated.
Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data
Semi-supervised learning (SSL) promises improved accuracy compared to training classifiers on small labeled datasets by also training on many unlabeled images.
Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning
Impressive results in natural language processing (NLP) based on the Transformer neural network architecture have inspired researchers to explore viewing offline reinforcement learning (RL) as a generic sequence modeling problem.
Data Encryption based on 9D Complex Chaotic System with Quaternion for Smart Grid
In this paper, a new 9D complex chaotic system with quaternion is proposed for the encryption of smart grid data.
V-Doc : Visual questions answers with Documents
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks.
Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph
We study the problem of safe and intention-aware robot navigation in dense and interactive crowds.
V-Doc: Visual Questions Answers With Documents
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks.
A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms
Semi-supervised image classification has shown substantial progress in learning from limited labeled data, but recent advances remain largely untested for clinical applications.
Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction
Multi-pedestrian trajectory prediction is an indispensable element of autonomous systems that safely interact with crowds in unstructured environments.
Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
Breast cancer is the most common cancer in women, and hundreds of thousands of unnecessary biopsies are done around the world at a tremendous cost.
Long-term Pedestrian Trajectory Prediction using Mutable Intention Filter and Warp LSTM
Trajectory prediction is one of the key capabilities for robots to safely navigate and interact with pedestrians.
Online monitoring for safe pedestrian-vehicle interactions
As autonomous systems begin to operate amongst humans, methods for safe interaction must be investigated.
Robotics Multiagent Systems Signal Processing
Gradual Network for Single Image De-raining
Taking the residual result (the coarse de-rained result) between the rainy image sample (i. e. the input data) and the output of coarse stage (i. e. the learnt rain mask) as input, the fine stage continues to de-rain by removing the fine-grained rain streaks (e. g. light rain streaks and water mist) to get a rain-free and well-reconstructed output image via a unified contextual merging sub-network with dense blocks and a merging block.
Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening
We present a deep convolutional neural network for breast cancer screening exam classification, trained and evaluated on over 200, 000 exams (over 1, 000, 000 images).
