CRV20
* *CRV
* Automatic Classification of Woodcuts and Copperplate Engravings
* CVNodes: A Visual Programming Paradigm for Developing Computer Vision Algorithms
* Depth from Defocus on a Transmissive Diffraction Mask-based Sensor
* Depth Prediction for Monocular Direct Visual Odometry
* Differentiable Mask for Pruning Convolutional and Recurrent Networks
* Domain Adaptation in Crowd Counting
* Domain Generalization via Optical Flow: Training a CNN in a Low-Quality Simulation to Detect Obstacles in the Real World
* Domain Generalization via Universal Non-volume Preserving Approach
* Evaluation of Skid-Steering Kinematic Models for Subarctic Environments
* Gas Prices of America: The Machine-Augmented Crowd-Sourcing Era
* Geometry-Guided Adaptation for Road Segmentation
* Gradient-Based Auto-Exposure Control Applied to a Self-Driving Car
* Histological Image Classification using Deep Features and Transfer Learning
* Image classification by Distortion-Free Graph Embedding and KNN-Random forest
* In-Time 3D Reconstruction and Instance Segmentation from Monocular Sensor Data
* It's Not Just Black and White: Classifying Defendant Mugshots Based on the Multidimensionality of Race and Ethnicity
* Leveraging Temporal Data for Automatic Labelling of Static Vehicles
* MASC-Net: Multi-scale Anisotropic Sparse Convolutional Network for Sparse Depth Densification
* Non-contact Method for Extracting Heart and Respiration Rates, A
* Pre-trained CNNs as Visual Feature Extractors: A Broad Evaluation
* PVF-NET: Point Voxel Fusion 3D Object Detection Framework for Point Cloud
* Real-time Motion Planning for Robotic Teleoperation Using Dynamic-goal Deep Reinforcement Learning
* Recognizing and Tracking High-Level, Human-Meaningful Navigation Features of Occupancy Grid Maps
* Simultaneous Demosaicing and Chromatic Aberration Correction through Spectral Reconstruction
* Single-Stage End-to-End Temporal Activity Detection in Untrimmed Videos
* SpotNet: Self-Attention Multi-Task Network for Object Detection
* TimeConvNets: A Deep Time Windowed Convolution Neural Network Design for Real-time Video Facial Expression Recognition
* Towards End-to-end Learning of Visual Inertial Odometry with an EKF
* Towards Richer 3D Reference Maps in Urban Scenes
* Tree bark re-identification using a deep-learning feature descriptor
* Unsupervised depth prediction from monocular sequences: Improving performances through instance segmentation
32 for CRV20
CRV21
* *CRV
* 2LSPE: 2D Learnable Sinusoidal Positional Encoding using Transformer for Scene Text Recognition
* Accurate outdoor ground truth based on total stations
* Building Facades to Normal Maps: Adversarial Learning from Single View Images
* Building Height Estimation using Street-View Images, Deep-Learning, Contour Processing, and Geospatial Data
* Deep Koopman Representation for Control over Images (DKRCI)
* Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation
* Few-Shot Learning by Integrating Spatial and Frequency Representation
* Improved Point Transformation Methods For Self-Supervised Depth Prediction
* Improving state-of-the-art in Detecting Student Engagement with Resnet and TCN Hybrid Network
* LIDAR Scan Registration Robust to Extreme Motions
* Mobile Manipulation in Unknown Environments with Differential Inverse Kinematics Control
* Multi-Resolution and Multi-Domain Analysis of Off-Road Datasets for Autonomous Driving
* new geometric approach for three view line reconstruction and motion estimation in Manhattan Scenes, A
* PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms
* Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification
* RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users
* Relatively Lazy: Indoor-Outdoor Navigation Using Vision and GNSS
* Robotic Object Manipulation with Full-Trajectory GAN-Based Imitation Learning
* Self-Calibration of the Offset Between GPS and Semantic Map Frames for Robust Localization
* Sequential Fusion via Bounding Box and Motion PointPainting for 3D Objection Detection
* SGNet: A Super-class Guided Network for Image Classification and Object Detection
* To Keystone or Not to Keystone, that is the Correction
* Uncertainty-Aware Policy Sampling and Mixing for Safe Interactive Imitation Learning
* Waypoint Planning Networks
25 for CRV21
CRV22
* *CRV
* 3DVQA: Visual Question Answering for 3D Environments
* Adaptive Memory Management for Video Object Segmentation
* Anomaly Detection with Adversarially Learned Perturbations of Latent Space
* Attention based Occlusion Removal for Hybrid Telepresence Systems
* CellDefectNet: A Machine-designed Attention Condenser Network for Electroluminescence-based Photovoltaic Cell Defect Inspection
* Classification of handwritten annotations in mixed-media documents
* Exact Fast Fourier Method for Morphological Dilation and Erosion Using the Umbra Technique, An
* GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation, The
* Improving tracking with a tracklet associator
* Instance Segmentation of Herring and Salmon Schools in Acoustic Echograms using a Hybrid U-Net
* Integrating High-Resolution Tactile Sensing into Grasp Stability Prediction
* Inter- and Intra-City Image Geolocalization
* Lasso Method for Multi-Robot Foraging, The
* Learned Intrinsic Auto-Calibration From Fundamental Matrices
* M2A: Motion Aware Attention for Accurate Video Action Recognition
* Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers
* Multiple Classifiers Based Adversarial Training for Unsupervised Domain Adaptation
* Object Class Aware Video Anomaly Detection through Image Translation
* Occluded Text Detection and Recognition in the Wild
* Occlusion-Aware Self-Supervised Stereo Matching with Confidence Guided Raw Disparity Fusion
* Permutation Model for the Self-Supervised Stereo Matching Problem, A
* ROS-X-Habitat: Bridging the ROS Ecosystem with Embodied AI
* Safe Landing Zones Detection for UAVs Using Deep Regression
* Semi-Supervised Grounding Alignment for Multi-Modal Feature Learning
* Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset, A
* Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos
* Temporal Convolutions for Multi-Step Quadrotor Motion Prediction
* TemporalNet: Real-time 2D-3D Video Object Detection
* Understanding the impact of image and input resolution on deep digital pathology patch classifiers
* View Invariant Human Action Recognition System for Noisy Inputs, A
31 for CRV22
CRV23
* *CRV
* Adaptive Multiple Distributed Bidirectional Spiral Path Planning for Foraging Robot Swarms
* Along Similar Lines: Local Obstacle Avoidance for Long-Term Autonomous Path Following
* aUToLights: A Robust Multi-Camera Traffic Light Detection and Tracking System
* CANDID: Correspondence AligNment for Deep-burst Image Denoising
* Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness
* Class Instance Balanced Learning for Long-Tailed Classification
* Continuous-Time Range-Only Pose Estimation
* Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
* CrossMoCo: Multi-Modal Momentum Contrastive Learning for Point Cloud
* Deformation Modeling for the Robotic Manipulation of 3D Elastic Objects using Physics-Informed Graph Neural Networks
* Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection
* Empirical Thresholding on Spatio-Temporal Autoencoders Trained on Surveillance Videos in a Dementia Care Unit
* Enhancing Satellite Trail Detection in Night Sky Imagery with Automatic Salience Thresholding
* Evaluating 3D Shape Analysis Methods for Robustness to Rotation Invariance
* Fast Fine-Tuning Using Curriculum Domain Adaptation
* Few-Shot Personality-Specific Image Captioning via Meta-Learning
* Generalized Kronecker-based Adapters for Parameter-efficient Fine-tuning of Vision Transformers
* Gradient-Based Maximally Interfered Retrieval for Domain Incremental 3D Object Detection
* HyperMODEST: Self-Supervised 3D Object Detection with Confidence Score Filtering
* Hyperspectral Image Compression Using Implicit Neural Representations
* InterTrack: Interaction Transformer for 3D Multi-Object Tracking
* Kaskade-CNN and NB-KDE-CNN: CNN Architectures with KDE and Probabilistic Reasoning Layers
* LatentKeypointGAN: Controlling Images via Latent Keypoints
* Learning-to-Count by Learning-to-Rank
* Living in a Material World: Learning Material Properties from Full-Waveform Flash Lidar Data for Semantic Segmentation
* Local Region-to-Region Mapping-based Approach to Classify Articulated Objects
* Multi-Object Tracking and Segmentation with a Space-Time Memory Network
* Naive Scene Graphs: How Visual is Modern Visual Relationship Detection?
* Next-Best-View Selection for Robot Eye-in-Hand Calibration
* ProPanDL: A Modular Architecture for Uncertainty-Aware Panoptic Segmentation
* Real-Time Instance Segmentation with Polygons Using an Intersection-Over-Union Loss
* Rehabilitation Exercise Repetition Segmentation and Counting Using Skeletal Body Joints
* Reversible Transformer for LiDAR Point Cloud Semantic Segmentation, A
* Robust Scuba Diver Tracking and Recovery in Open Water Using YOLOv7, SORT, and Spiral Search
* Sparse Shape Encoding for Topologically Improved Instance Segmentation
* Towards Low-Cost Learning-based Camera ISP via Unrolled Optimization
* Towards Open World NeRF-Based SLAM
* Transformer-Based Human Action Recognition with Dynamic Feature Selection
* Tree Health Assessment from UAV Images: Improving Object Detection and Classification Using Hard Negative Mining and Semi-Supervised Autoencoder
* What does the Occluding Contour Tell us about Quantitative Shape?
41 for CRV23