Soatti, G.
Co Author Listing * Augmenting Vehicle Localization by Cooperative Sensing of the Driving Environment: Insight on Data Association in Urban Traffic Scenarios
* Implicit Cooperative Positioning in Vehicular Networks
Soatto, S.[Stefano]
Co Author Listing * Home Page.
* email: Soatto, S.[Stefano]: soatto AT cs ucla edu
* 3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation
* 3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination
* 3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion-Blur
* 3D shape from anistropic diffusion
* Actionable information in vision
* Actionable saliency detection: Independent motion detection without independent motion estimation
* Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation
* Adaptive Discretizations for Non-smooth Variational Vision
* Adaptive Regularization of Some Inverse Problems in Image Analysis
* Adaptive Regularization With the Structure Tensor
* Analyzing Diving: A Dataset for Judging Action Quality
* ARCH++: Animation-Ready Clothed Human Reconstruction Revisited
* Asymmetric Sparse Kernel Approximations for Large-Scale Visual Search
* Autocalibration and Uncalibrated Reconstruction of Shape from Defocus
* Background Subtraction on Distributions
* Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction
* Categorization in natural time-varying image sequences
* Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects
* CLAM: Coupled Localization and Mapping with Efficient Outlier Handling
* Class Segmentation and Object Localization with Superpixel Neighborhoods
* Class-Incremental Learning with Strong Pre-trained Models
* Classification and Recognition of Dynamical Models: The Role of Phase, Independent Components, Kernels and Optimal Transport
* Classifying Human Dynamics Without Contact Forces
* Compatibility-aware Heterogeneous Visual Search
* Conditional Prior Networks for Optical Flow
* Control Theory and Fast Marching Methods for Brain Connectivity Mapping
* Control Theory and Fast Marching Techniques for Brain Connectivity Mapping
* Correspondence Transfer for the Registration of Multimodal Images
* Critical Learning Periods for Multisensory Integration in Deep Networks
* Curious snakes: A minimum latency solution to the cluttered background problem in active contours
* Deepvoxels++: Enhancing the Fidelity of Novel View Synthesis from 3d Voxel Embeddings
* Deformotion: Deforming Motion, Shape Average and the Joint Registration and Approximation of Structures in Images
* DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images
* Dense Depth Posterior (DDP) From Single Image and Sparse Range
* Depth Estimation from Camera Image and mmWave Radar Point Cloud
* Detachable Object Detection with Efficient Model Selection
* Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video
* Detecting Occlusions as an Inverse Problem
* Direct Sparse Deblurring
* Discovering discriminative action parts from mid-level video representations
* Domain-size pooling in local descriptors: DSP-SIFT
* Dynamic Rigid Motion Estimation from Weak Perspective
* Dynamic Shape and Appearance Modeling via Moving and Deforming Layers
* Dynamic Shape and Appearance Models
* Dynamic Texture Recognition
* Dynamic texture segmentation
* Dynamic Textures
* Dynamic visual motion estimation from subspace constraints
* DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping*
* Earth Mover Distance on superpixels
* Edge descriptors for robust wide-baseline correspondence
* Editable dynamic textures
* Editorial for the Special Issue on Photometric Analysis for Computer Vision
* Editorial: CVPR 2005 Award Papers
* Efficient minimal-surface regularization of perspective depth maps in variational stereo
* Embedded Imagers: Detecting, Localizing, and Recognizing Objects and Events in Natural Habitats
* Empirical Evaluation of Current Convolutional Architectures: Ability to Manage Nuisance Location and Scale Variability, An
* Empirical Study of the Topology and Geometry of Deep Networks
* Entropy-Scale Profiles for Texture Segmentation
* Estimation of 3D surface shape and smooth radiance from 2D images: A Level Set Approach
* Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
* Euclidean Reconstruction and Reprojection Up to Subgroups
* Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks
* Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
* Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression
* Fast planar object detection and tracking via edgel templates
* FDA: Fourier Domain Adaptation for Semantic Segmentation
* Features for Recognition: Viewpoint Invariance for Non-Planar Scenes
* Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training
* Filtering Internet image search results towards keyword based category recognition
* Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss
* Flexible dictionaries for action classification
* Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-output Observations
* Geometric Approach to Blind Deconvolution with Application to Shape from Defocus, A
* Geometric Approach to Shape from Defocus, A
* geometric framework for dynamic vision, A
* GeoNet: Deep Geodesic Networks for Point Cloud Analysis
* Guided Recommendation for Model Fine-Tuning
* Harmonic Embeddings for Linear Shape Analysis
* Harnessing Unrecognizable Faces for Improving Face Recognition
* Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits
* Incremental Few-shot Meta-learning via Indirect Discriminant Alignment
* Information Dropout: Learning Optimal Representations Through Noisy Computation
* Information-Seeking Control Under Visibility-Based Uncertainty
* Inpainting from multiple views
* Input and Weight Space Smoothing for Semi-Supervised Learning
* Integral Invariants for Shape Matching
* Invitation to 3-D Vision: From Images to Geometric Models, An
* Joint data alignment up to (lossy) transformations
* Joint Priors for Variational Shape and Appearance Modeling
* KALMANSAC: Robust Filtering by Consensus
* Kernel Density Estimation and Intrinsic Alignment for Knowledge-Driven Segmentation: Teaching Level Sets to Walk
* Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation
* Landmark based inpainting from multiple views
* Layered Active Appearance Models
* Learning and matching multiscale template descriptors for real-time detection, localization and tracking
* Learning Hierarchical Graph Neural Networks for Image Clustering
* Learning Semantic-Aware Dynamics for Video Prediction
* Learning Shape from Defocus
* Learning to Manipulate Individual Objects in an Image
* Linear Spaces of Meanings: Compositional Structures in Vision-Language Models
* Linear Systems Approach to Imaging Through Turbulence, A
* Local Features, All Grown Up
* Localizing Objects with Smart Dictionaries
* Long-Range Spatio-Temporal Modeling of Video with Application to Fire Detection
* LQF: Linear Quadratic Fine-Tuning
* MeMOT: Multi-Object Tracking with Memory
* Meta-Learning Approach to Predicting Performance and Data Requirements, A
* Meta-Learning With Differentiable Convex Optimization
* mid-level representation of visual structures for video compression, A
* Mixed Differential Privacy in Computer Vision
* Mixed-Privacy Forgetting in Deep Networks
* model (In)validation approach to gait recognition, A
* Modeling and Synthesis of Facial Motion Driven by Speech
* Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation
* Motion Estimation on the Essential Manifold
* Motion estimation via dynamic vision
* Motion from Fixation
* Motion segmentation with occlusions on the superpixel graph
* Moving Forward in Structure From Motion
* Multi-view feature engineering and learning
* Multi-view stereo beyond Lambert
* Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance
* Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis
* Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images
* New Geometric Metric in the Space of Curves, and Applications to Tracking Deforming Objects by Prediction and Filtering, A
* Non-local Approach to Shape from Ambient Shading, A
* Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques
* Nonlocal Similarity Image Filtering
* Nonrigid registration combining global and local statistics
* Not Just Streaks: Towards Ground Truth for Single Image Deraining
* OATM: Occlusion Aware Template Matching by Consensus Set Maximization
* Observing Shape from Defocused Images
* Omni-DETR: Omni-Supervised Object Detection with Transformers
* On exploiting occlusions in multiple-view geometry
* On observing shape from defocused images
* On the Blind Classification of Time Series
* On the set of images modulo viewpoint and contrast changes
* One-Shot Integral Invariant Shape Priors for Variational Segmentation
* Optimal Structure from Motion: Local Ambiguities and Global Estimates
* Perspective distortion modeling, learning and compensation
* Phase Consistent Ecological Domain Adaptation
* Positive-Congruent Training: Towards Regression-Free Model Updates
* Proximity Distribution Kernels for Geometric Context in Category Recognition
* Quick Shift and Kernel Methods for Mode Seeking
* Real-time 3D motion and structure of point features: a front-end system for vision-based control and interaction
* Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination
* Real-time Virtual Object Insertion
* Recognition of Human Gaits
* Recursive 3-D Visual-Motion Estimation Using Subspace Constraints
* Recursive estimation of camera motion from uncalibrated image sequences
* Recursive Motion and Structure Estimation with Complete Error Characterization
* Reducing Structure from Motion: A General Framework for Dynamic Vision with Experimental Evaluation
* Reducing Structure-From-Motion: A General Framework For Dynamic Vision Part 1: Modeling
* Reducing Structure-From-Motion: A General Framework for Dynamic Vision Part 2: Implementation And Experimental Assessment
* Region Matching with Missing Parts
* Region-Based Segmentation on Evolving Surfaces with Application to 3D Reconstruction of Shape and Piecewise Constant Radiance
* Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification
* Relaxed matching kernels for robust image comparison
* Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images
* Robust Poisson Surface Reconstruction
* Robust Surface Reconstruction
* S2F: Slow-to-Fast Interpolator Flow
* SaaS: Speed as a Supervisor for Semi-supervised Learning
* SAFE: Machine Unlearning With Shard Graphs
* scale of a texture and its application to segmentation, The
* Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion
* Second-Order Shape Optimization for Geometric Inverse Problems in Vision
* Seeing beyond occlusions (and other marvels of a finite lens aperture)
* Self-Occlusions and Disocclusions in Causal Video Object Segmentation
* semi-direct approach to structure from motion, A
* Shape and Radiance Estimation from the Information Divergence of Blurred Images
* Shape from Defocus via Diffusion
* Shape Matching Using Multiscale Integral Invariants
* Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation
* Shape representation via harmonic embedding
* ShapeFit and ShapeKick for Robust, Scalable Structure from Motion
* Shedding light on stereoscopic segmentation
* Simple Hierarchical Pooling Data Structure for Loop Closure, A
* Sparse Occlusion Detection with Optical Flow
* Spatial Class Distribution Shift in Unsupervised Domain Adaptation: Local Alignment Comes to Rescue
* Spatially Homogeneous Dynamic Textures
* Spike train driven dynamical models for human actions
* Stereoscopic Segmentation
* Stereoscopic Shading: Integrating Multi-Frame Shape Cues in a Variational Framework
* Stereoscopic Universal Perturbations across Different Architectures and Datasets
* Stochastic batch size for adaptive regularization in deep network optimization
* Structure from Motion Causally Integrated Over Time
* Structure from motion for scenes without features
* Study of Face Recognition as People Age, A
* SuperFloxels: A Mid-level Representation for Video Sequences
* Tales of shape and radiance in multi-view stereo
* Tangent Model Composition for Ensembling and Continual Fine-tuning
* Task Adaptive Parameter Sharing for Multi-Task Learning
* Task2Vec: Task Embedding for Meta-Learning
* Texture Regimes for Entropy-Based Multiscale Image Analysis
* Texture representations for image and video synthesis
* Towards Backward-Compatible Representation Learning
* Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation
* Tracklet Descriptors for Action Modeling and Video Analysis
* Train/Test-Time Adaptation with Retrieval
* Two-View Multibody Structure from Motion
* Unsupervised Depth Completion with Calibrated Backprojection Layers
* Unsupervised Domain Adaptation via Regularized Conditional Alignment
* Unsupervised Moving Object Detection via Contextual Information Separation
* Unsupervised multiphase segmentation: A recursive approach
* Variational Approach to Problems in Calibration of Multiple Cameras, A
* variational approach to scene reconstruction and image segmentation from motion-blur cues, A
* Variational multiframe stereo in the presence of specular reflections
* Variational space-time motion segmentation
* Video upscaling via spatio-temporal self-similarity
* Video-based descriptors for object recognition
* Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions
* Visual motion estimation from point features: unified view
* Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries
* Visual-Inertial Object Detection and Mapping
* Visual-Inertial-Semantic Scene Representation for 3D Object Detection
* Volumetric reconstruction applied to perceptual studies of size and weight
* Warping background subtraction
* X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks
* Zero Shot Learning via Multi-scale Manifold Regularization
* À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
Includes: Soatto, S.[Stefano] Soatto, S.
224 for Soatto, S.
Soattoc, S.[Stefano]
Co Author Listing * Causal video object segmentation from persistence of occlusions