Rahtu, E.[Esa]
Co Author Listing * ADVIO: An Authentic Dataset for Visual-Inertial Odometry
* Affine Invariant Pattern Recognition Using Multiscale Autoconvolution
* Affine Registration with Multi-Scale Autoconvolution
* Analysis of Sampling Techniques for Learning Binarized Statistical Image Features Using Fixations and Salience
* Applying Visual Object Categorization and Memory Colors for Automatic Color Constancy
* Automated Video Face Labelling for Films and TV Material
* Automatic Dynamic Texture Segmentation Using Local Descriptors and Optical Flow
* AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval
* Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion
* Bottom-Up Attention Guidance for Recurrent Image Recognition
* Bridging the Gap Between Image Coding for Machines and Humans
* BSIF: Binarized statistical image features
* Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis
* CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image Denoising
* Compressing Sparse Feature Vectors Using Random Ortho-Projections
* Dense and Deformable Motion Segmentation for Wide Baseline Images
* DGC-Net: Dense Geometric Correspondence Network
* Digging Deeper Into Egocentric Gaze Prediction
* Emotional Valence Recognition, Analysis of Salience and Eye Movements
* End-to-End Learning for Video Frame Compression with Self-Attention
* Enhanced Data-Recalibration: Utilizing Validation Data to Mitigate Instance-Dependent Noise in Classification
* FACEGAN: Facial Attribute Controllable rEenactment GAN
* Fast and Efficient Saliency Detection Using Sparse Sampling and Kernel Density Estimation
* Generalized affine moment invariants for object recogn
* Generating Object Segmentation Proposals Using Global and Local Search
* Guiding Monocular Depth Estimation Using Depth-attention Volume
* HybVIO: Pushing the Limits of Real-time Visual-inertial Odometry
* ICface: Interpretable and Controllable Face Reenactment Using GANs
* Image Patch Matching Using Convolutional Descriptors with Euclidean Distance
* Image-Based Localization Using Hourglass Networks
* Improved Blur Insensitivity for Decorrelated Local Phase Quantization
* Learned Video Compression with Intra-Guided Enhancement and Implicit Motion Information
* Learning a category independent object detection cascade
* Learning Image-to-Image Translation Using Paired and Unpaired Training Samples
* Learning Joint Representations of Videos and Sentences with Web Image Search
* Lightweight Monocular Depth with a Novel Neural Architecture Search Method
* Local phase quantization for blur-insensitive image analysis
* Long-term Visual Place Recognition
* MLAttack: Fooling Semantic Segmentation Networks by Multi-layer Attacks
* Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss
* Multi-modal Dense Video Captioning
* Multiscale Autoconvolution Histograms for Affine Invariant Pattern Recognition
* New Affine Invariant Image Transform Based on Ridgelets, A
* New Convexity Measure Based on a Probabilistic Interpretation of Images, A
* New Efficient Method for Producing Global Affine Invariants, A
* New Method for Affine Registration of Images and Point Sets, A
* Non Maximal Suppression in Cascaded Ranking Models
* Nonlinear Functionals in the Construction of Multiscale Affine Invariants
* Novel Method for Automatic Localization of Joint Area on Knee Plain Radiographs, A
* O(nlogn) Cutting Plane Algorithm for Structured Output Ranking, An
* Object classification with multi-scale autoconvolution
* Object recognition and segmentation by non-rigid quasi-dense matching
* On the Importance of Encrypting Deep Features
* Online Panoptic 3D Reconstruction as a Linear Assignment Problem
* Optimal Correction Cost for Object Detection Evaluation
* OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation
* PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation
* Predicting Novel Views Using Generative Adversarial Query Network
* Properties of Patch Based Approaches for the Recognition of Visual Object Classes
* Real-Time Detection of Landscape Scenes
* Recognition of blurred faces using Local Phase Quantization
* Relative Camera Pose Estimation Using Convolutional Neural Networks
* Rethinking the Evaluation of Video Summaries
* RGBD-Net: Predicting Color and Depth Images for Novel Views Synthesis
* Robust loop closures for scene reconstruction by combining odometry and visual correspondences
* Rotation invariant local phase quantization for blur insensitive texture analysis
* Saliency Detection Using Joint Temporal and Spatial Decorrelation
* Segmenting Salient Objects from Images and Videos
* Sequential View Synthesis with Transformer
* Siamese network features for image matching
* Simple and efficient saliency detector for background subtraction, A
* Single Source One Shot Reenactment using Weighted Motion from Paired Feature Points
* Spherical Center-Surround for Video Saliency Detection Using Sparse Sampling
* Stochastic bottom-up fixation prediction and saccade generation
* Summarization of User-Generated Sports Video by Using Deep Action Recognition Features
* Temporal Saliency for Fast Motion Detection
* Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
* TPSAD: Learning to Detect and Localize Anomalies With Thin Plate Spline Transformation
* TriCoS: A Tri-level Class-Discriminative Co-segmentation Method for Image Classification
* Understanding Objects in Detail with Fine-Grained Attributes
* V-SlowFast Network for Efficient Visual Sound Separation
* Video Summarization Using Deep Semantic Features
* Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations
* Visually Guided Sound Source Separation Using Cascaded Opponent Filter Network
* Volume Local Phase Quantization for Blur-Insensitive Dynamic Texture Classification
* Watermark Recovery from a Dual Layer Hologram with a Digital Camera
Includes: Rahtu, E.[Esa] Rahtu, E.
86 for Rahtu, E.