iccv 2017 论文列表
2017 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2017, Venice, Italy, October 22-29, 2017.
|
Results and Analysis of ChaLearn LAP Multi-modal Isolated and Continuous Gesture Recognition, and Real Versus Fake Expressed Emotions Challenges.
Action Recognition from RGB-D Data: Comparison and Fusion of Spatio-Temporal Handcrafted Features and Deep Strategies.
Darwintrees for Action Recognition.
Facial Expression Recognition via Joint Deep Learning of RGB-Depth Map Latent Representations.
Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition.
Combining Sequential Geometry and Texture Features for Distinguishing Genuine and Deceptive Emotions.
Large-Scale Multimodal Gesture Segmentation and Recognition Based on Convolutional Neural Networks.
Large-Scale Multimodal Gesture Recognition Using Heterogeneous Networks.
Learning Spatiotemporal Features Using 3DCNN and Convolutional LSTM for Gesture Recognition.
Two-Stream Flow-Guided Convolutional Attention Networks for Action Recognition.
Visualizing Apparent Personality Analysis with Deep Residual Networks.
Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction.
Gesture and Sign Language Recognition with Temporal Residual Networks.
Particle Filter Based Probabilistic Forced Alignment for Continuous Gesture Recognition.
Real vs. Fake Emotion Challenge: Learning to Rank Authenticity from Facial Activity Descriptors.
Discrimination Between Genuine Versus Fake Emotion Using Long-Short Term Memory with Parametric Bias and Facial Landmarks.
Continuous Gesture Recognition with Hand-Oriented Spatiotemporal Feature.
Multimodal Gesture Recognition Based on the ResC3D Network.
Color Image Processing Using Reduced Biquaternions with Application to Face Recognition in a PCA Framework.
Image-Based Relighting with 5-D Incident Light Fields.
Global and Local Contrast Adaptive Enhancement for Non-uniform Illumination Color Images.
A New Low-Light Image Enhancement Algorithm Using Camera Response Model.
A Three-Pathway Psychobiological Framework of Salient Object Detection Using Stereoscopic Technology.
Linear Data Compression of Hyperspectral Images.
Deep Generative Filter for Motion Deblurring.
The Importance of Smoothness Constraints on Spectral Object Reflectances when Modeling Metamer Mismatching.
Color Consistency Correction Based on Remapping Optimization for Image Stitching.
Shape-from-Polarisation: A Nonlinear Least Squares Approach.
Depth Super-Resolution Meets Uncalibrated Photometric Stereo.
LIT: A System and Benchmark for Light Understanding.
An Interactive Tour Guide for a Heritage Site.
Geometry Based Faceting of 3D Digitized Archaeological Fragments.
Analysis of Partial Axial Symmetry on 3D Surfaces and Its Application in the Restoration of Cultural Heritage Objects.
Learning to Detect Fine-Grained Change Under Variant Imaging Conditions.
A Learned Representation of Artist-Specific Colourisation.
Ancient Roman Coin Recognition in the Wild Using Deep Learning Based Recognition of Artistically Depicted Face Profiles.
Active Learning for the Classification of Species in Underwater Images from a Fixed Observatory.
A Computer Vision Framework for Detecting and Preventing Human-Elephant Collisions.
Coral-Segmentation: Training Dense Labeling Models with Sparse Ground Truth.
Deep Census: AUV-Based Scallop Population Monitoring.
Towards Automatic Wild Animal Detection in Low Quality Camera-Trap Images Using Two-Channeled Perceiving Residual Pyramid Networks.
Visual Localisation and Individual Identification of Holstein Friesian Cattle via Deep Learning.
Visual Tracking of Small Animals in Cluttered Natural Environments Using a Freely Moving Camera.
Integral Curvature Representation and Matching Algorithms for Identification of Dolphins and Whales.
Towards Automated Visual Monitoring of Individual Gorillas in the Wild.
Towards Automated Recognition of Facial Expressions in Animal Models.
Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach.
Can the Early Human Visual System Compete with Deep Neural Networks?
Deep Gestalt Reasoning Model: Interpreting Electrophysiological Signals Related to Cognition.
Facial Expression Recognition Using Visual Saliency and Deep Learning.
Exploring Inter-Observer Differences in First-Person Object Views Using Deep Learning Models.
Evaluation of Deep Learning on an Abstract Image Classification Dataset.
The Importance of Phase to Texture Similarity.
Learning RGB-D Salient Object Detection Using Background Enclosure, Depth Contrast, and Top-Down Features.
Predicting the Category and Attributes of Visual Search Targets Using Deep Gaze Pooling.
Show and Recall: Learning What Makes Videos Memorable.
Spatial Attention Improves Object Localization: A Biologically Plausible Neuro-Computational Model for Use in Virtual Reality.
STNet: Selective Tuning of Convolutional Networks for Object Localization.
What are the Visual Features Underlying Human Versus Machine Vision?
Color Representation in CNNs: Parallelisms with Biological Vision.
Can We Speed up 3D Scanning? A Cognitive and Geometric Analysis.
Local Depth Edge Detection in Humans and Deep Neural Networks.
Exploiting Convolution Filter Patterns for Transfer Learning.
Generating Visual Representations for Zero-Shot Classification.
Inferring Human Activities Using Robust Privileged Probabilistic Learning.
Deep Domain Adaptation by Geodesic Distance Minimization.
Deep Depth Domain Adaptation: A Case Study.
Adaptive SVM+: Learning with Privileged Information for Domain Adaptation.
Discrepancy-Based Networks for Unsupervised Domain Adaptation: A Comparative Study.
Deep Modality Invariant Adversarial Network for Shared Representation Learning.
Zero-Shot Learning Posed as a Missing Data Problem.
Curriculum Learning for Multi-task Classification of Visual Attributes.
Unified Framework for Automated Person Re-identification and Camera Network Topology Inference in Camera Networks.
Person Re-identification by Deep Learning Multi-scale Representations.
View-Invariant Gait Representation Using Joint Bayesian Regularized Non-negative Matrix Factorization.
From Groups to Co-Traveler Sets: Pair Matching Based Person Re-identification Framework.
Intelligent Synthesis Driven Model Calibration: Framework and Face Recognition Application.
UHDB31: A Dataset for Better Understanding Face Recognition Across Pose and Illumination Variation.
The Do's and Don'ts for CNN-Based Face Verification.
Learning to Identify While Failing to Discriminate.
Combining Local and Global Features for 3D Face Tracking.
Convolutional Experts Constrained Local Model for 3D Facial Landmark Detection.
Pix2Face: Direct 3D Face Model Estimation.
The 3D Menpo Facial Landmark Tracking Challenge.
KPPF: Keypoint-Based Point-Pair-Feature for Scalable Automatic Global Registration of Large RGB-D Scans.
A Content-Aware Metric for Stitched Panoramic Image Quality Assessment.
Combining Exemplar-Based Approach and learning-Based Approach for Light Field Super-Resolution Using a Hybrid Imaging System.
Multiview Absolute Pose Using 3D - 2D Perspective Line Correspondences and Vertical Direction.
On Tablet 3D Structured Light Reconstruction and Registration.
Accurate Depth Map Estimation from Small Motions.
A Use-Case Study on Multi-view Hypothesis Fusion for 3D Object Classification.
Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternions.
Computer Vision Meets Geometric Modeling: Multi-view Reconstruction of Surface Points and Normals Using Affine Correspondences.
Probabilistic Surfel Fusion for Dense LiDAR Mapping.
Edge SLAM: Edge Points Based Monocular Visual SLAM.
Reading Text in the Wild from Compressed Images.
Outdoor Operation of Structured Light in Mobile Phone.
Fully Convolutional Network and Region Proposal for Instance Identification with Egocentric Vision.
How Shall We Evaluate Egocentric Action Recognition?
An Object is Worth Six Thousand Pictures: The Egocentric, Manual, Multi-image (EMMI) Dataset.
Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention.
Batch-Based Activity Recognition from Egocentric Photo-Streams.
Convolutional Long Short-Term Memory Networks for Recognizing First Person Interactions.
SaltiNet: Scan-Path Prediction on 360 Degree Images Using Saliency Volumes.
Finding Time Together: Detection and Classification of Focused Interaction in Egocentric Video.
Temporal Localization and Spatial Segmentation of Joint Attention in Multiple First-Person Videos.
Hierarchical Category Detector for Clothing Recognition from Visual Data.
Point Cloud Completion of Foot Shape from a Single Depth Map for Fit Matching Using Deep Learning View Synthesis.
Dress Like a Star: Retrieving Fashion Products from Videos.
The Conditional Analogy GAN: Swapping Fashion Articles on People Images.
An Accurate System for Fashion Hand-Drawn Sketches Vectorization.
Recommending Outfits from Personal Closet.
Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction.
Multi-label Fashion Image Classification with Minimal Human Supervision.
3D Garment Digitisation for Virtual Wardrobe Using a Commodity Depth Sensor.
What Makes a Style: Experimental Analysis of Fashion Prediction.
Learning Unified Embedding for Apparel Recognition.
Multi-modal Embedding for Main Product Detection in Fashion.
Multi-view 6D Object Pose Estimation and Camera Motion Planning Using RGBD Images.
Combined Holistic and Local Patches for Recovering 6D Object Pose.
Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk.
Introducing MVTec ITODD - A Dataset for 3D Object Recognition in Industry.
Mutual Hypothesis Verification for 6D Pose Estimation of Natural Objects.
Propagation of Orientation Uncertainty of 3D Rigid Object to Its Points.
3D Pose Regression Using Convolutional Neural Networks.
Efficient and Accurate Registration of Point Clouds with Plane to Plane Correspondences.
Deep Learning of Convolutional Auto-Encoder for Image Matching and 3D Object Reconstruction in the Infrared Range.
Distributed Bundle Adjustment.
Convolutional Neural Network-Based Deep Urban Signatures with Application to Drone Localization.
Robust UAV-Based Tracking Using Hybrid Classifiers.
Feature-Based Efficient Moving Object Detection for Low-Altitude Aerial Platforms.
Embedded Real-Time Object Detection for a UAV Warning System.
Creating Roadmaps in Aerial Images with Generative Adversarial Networks and Smoothing-Based Optimization.
Detection, Estimation and Avoidance of Mobile Objects Using Stereo-Vision and Model Predictive Control.
Leaf Counting with Deep Convolutional and Deconvolutional Networks.
Leveraging Multiple Datasets for Deep Leaf Counting.
ARIGAN: Synthetic Arabidopsis Plants Using Generative Adversarial Network.
Deep Learning for Multi-task Plant Phenotyping.
Drought Stress Classification Using 3D Plant Models.
An Easy-to-Setup 3D Phenotyping Platform for KOMATSUNA Dataset.
Locating Crop Plant Centers from UAV-Based RGB Imagery.
Automated Stem Angle Determination for Temporal Plant Phenotyping Analysis.
Computer Vision Problems in Plant Phenotyping, CVPPP 2017: Introduction to the CVPPP 2017 Workshop Papers.
Recurrent Filter Learning for Visual Tracking.
Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation.
Correlation Filters with Weighted Convolution Responses.
The Benefits of Evaluating Tracker Performance Using Pixel-Wise Segmentations.
UCT: Learning Unified Convolutional Networks for Real-Time Visual Tracking.
The Visual Object Tracking VOT2017 Challenge Results.
Face Generation for Low-Shot Learning Using Generative Adversarial Networks.
Low-Shot Face Recognition with Hybrid Classifiers.
Know You at One Glance: A Compact Vector Representation for Low-Shot Learning.
Doppelganger Mining for Face Representation Learning.
How to Train Triplet Networks with 100K Identities?
High Performance Large Scale Face Recognition with Multi-cognition Softmax and Feature Retrieval.
UHD Video Super-Resolution Using Low-Rank and Sparse Decomposition.
Compressed Singular Value Decomposition for Image and Video Processing.
Background Subtraction via Fast Robust Matrix Completion.
Dynamic Mode Decomposition for Background Modeling.
Weighted Low Rank Approximation for Background Estimation Problems.
Panning and Jitter Invariant Incremental Principal Component Pursuit for Video Background Modeling.
A Batch-Incremental Video Background Estimation Model Using Weighted Low-Rank Approximation of Matrices.
Fast Approximate Karhunen-Loève Transform for Three-Way Array Data.
Robust and Scalable Column/Row Sampling from Corrupted Big Data.
A Non-convex Relaxation for Fixed-Rank Approximation.
Manifold Constrained Low-Rank Decomposition.
Variational Robust Subspace Clustering with Mean Update Algorithm.
Learning Robust Representations for Computer Vision.
Detecting Reflectional Symmetries in 3D Data Through Symmetrical Fitting.
InnerSpec: Technical Report.
SymmSLIC: Symmetry Aware Superpixel Segmentation.
Finding Mirror Symmetry via Registration and Optimal Symmetric Pairwise Assignment of Curves: Algorithm and Results.
Finding Mirror Symmetry via Registration and Optimal Symmetric Pairwise Assignment of Curves.
Fusing Image and Segmentation Cues for Skeleton Extraction in the Wild.
RSRN: Rich Side-Output Residual Network for Medial Axis Detection.
Wavelet-Based Reflection Symmetry Detection via Textural and Color Histograms: Algorithm and Results.
Wavelet-Based Reflection Symmetry Detection via Textural and Color Histograms.
SymmMap: Estimation of the 2-D Reflection Symmetry Map and Its Applications.
Hierarchical Grouping - The Gestalt Assessments Method.
Hierarchical Grouping Using Gestalt Assessments.
2017 ICCV Challenge: Detecting Symmetry in the Wild.
DeepVisage: Making Face Recognition Simple Yet With Powerful Generalization Skills.
Detecting Smiles of Young Children via Deep Transfer Learning.
Learning Deep Convolutional Embeddings for Face Representation Using Joint Sample- and Set-Based Supervision.
Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification.
Disguised Face Identification (DFI) with Facial KeyPoints Using Spatial Fusion Convolutional Network.
Early Adaptation of Deep Priors in Age Prediction from Face Images.
Understanding and Comparing Deep Neural Networks for Age and Gender Classification.
Dense Face Alignment.
Using Synthetic Data to Improve Facial Expression Analysis with 3D Convolutional Networks.
FacePoseNet: Making a Case for Landmark-Free Face Alignment.
From Face Recognition to Kinship Verification: An Adaptation Approach.
SmileNet: Registration-Free Smiling Face Detection In The Wild.
Toward Describing Human Gaits by Onomatopoeias.
Fast and Accurate Face Recognition with Image Sets.
Improving Face Verification and Person Re-Identification Accuracy Using Hyperplane Similarity.
Improved Strategies for HPE Employing Learning-by-Synthesis Approaches.
DSD: Depth Structural Descriptor for Edge-Based Assistive Navigation.
Diabetes60 - Inferring Bread Units From Food Images Using Fully Convolutional Neural Networks.
Depth and Motion Cues with Phosphene Patterns for Prosthetic Vision.
An Innovative Salient Object Detection Using Center-Dark Channel Prior.
A Wearable Assistive Technology for the Visually Impaired with Door Knob Detection and Real-Time Feedback for Hand-to-Handle Manipulation.
A Shared Autonomy Approach for Wheelchair Navigation Based on Learned User Preferences.
Computer Vision for the Visually Impaired: the Sound of Vision System.
To Veer or Not to Veer: Learning from Experts How to Stay Within the Crosswalk.
Estimating Position & Velocity in 3D Space from Monocular Video Sequences Using a Deep Neural Network.
Seeing Without Sight - An Automatic Cognition System Dedicated to Blind and Visually Impaired People.
Mind the Gap: Virtual Shorelines for Blind and Partially Sighted People.
Vision-Based Fallen Person Detection for the Elderly.
Using Technology Developed for Autonomous Cars to Help Navigate Blind People.
Use of Thermal Point Cloud for Thermal Comfort Measurement and Human Pose Estimation in Robotic Monitoring.
Postural Assessment in Dentistry Based on Multiple Markers Tracking.
A Computer Vision Based Approach for Understanding Emotional Involvements in Children with Autism Spectrum Disorders.
Inertial-Vision: Cross-Domain Knowledge Transfer for Wearable Sensors.
Adaptive Binarization for Weakly Supervised Affordance Segmentation.
A Vision-Based System for In-Bed Posture Tracking.
Robust Human Pose Tracking For Realistic Service Robot Applications.
Recurrent Assistance: Cross-Dataset Training of LSTMs on Kitchen Tasks.
BEHAVE - Behavioral Analysis of Visual Events for Assisted Living Scenarios.
A Long Short-Term Memory Convolutional Neural Network for First-Person Vision Activity Recognition.
Learning Invariant Riemannian Geometric Representations Using Deep Nets.
Coupled Manifold Learning for Retrieval Across Modalities.
Margin Based Semi-Supervised Elastic Embedding for Face Image Analysis.
Clustering Positive Definite Matrices by Learning Information Divergences.
moM: Mean of Moments Feature for Person Re-identification.
Real-Time Hand Tracking Under Occlusion from an Egocentric RGB-D Sensor.
Reliable Isometric Point Correspondence from Depth.
Local Geometry Inclusive Global Shape Representation.
Towards Good Practices for Image Retrieval Based on CNN Features.
A Handcrafted Normalized-Convolution Network for Texture Classification.
Few-Shot Hash Learning for Image Retrieval.
The Mating Rituals of Deep Neural Networks: Learning Compact Feature Representations Through Sexual Evolutionary Synthesis.
Rotation Invariant Local Binary Convolution Neural Networks.
Dynamic Computational Time for Visual Attention.
Video Summarization via Multi-view Representative Selection.
Texture and Structure Incorporated ScatterNet Hybrid Deep Learning Network (TS-SHDL) for Brain Matter Segmentation.
Fast CNN-Based Document Layout Analysis.
Multiplicative Noise Channel in Generative Adversarial Networks.
Max-Boost-GAN: Max Operation to Boost Generative Ability of Generative Adversarial Networks.
4D Effect Video Classification with Shot-Aware Frame Selection and Deep Neural Networks.
Efficient Convolutional Network Learning Using Parametric Log Based Dual-Tree Wavelet ScatterNet.
Coarse-to-Fine Deep Kernel Networks.
Oceanic Scene Recognition Using Graph-of-Words (GoW).
End-to-End Visual Target Tracking in Multi-robot Systems Based on Deep Convolutional Neural Network.
Co-localization with Category-Consistent Features and Geodesic Distance Propagation.
Binary-Decomposed DCNN for Accelerating Computation and Compressing Model Without Retraining.
Consistent Iterative Multi-view Transfer Learning for Person Re-identification.
Enlightening Deep Neural Networks with Knowledge of Confounding Factors.
UDNet: Up-Down Network for Compact and Efficient Feature Representation in Image Super-Resolution.
Automatic Discovery of Discriminative Parts as a Quadratic Assignment Problem.
Double-Task Deep Q-Learning with Multiple Views.
Spatial-Temporal Weighted Pyramid Using Spatial Orthogonal Pooling.
Compact Color Texture Descriptor Based on Rank Transform and Product Ordering in the RGB Color Space.
Improved Descriptors for Patch Matching and Reconstruction.
Compact Feature Representation for Image Classification Using ELMs.
Structured Images for RGB-D Action Recognition.
Efficient Fine-Grained Classification and Part Localization Using One Compact Network.
Large-Scale Content-Only Video Recommendation.
Learning Efficient Deep Feature Representations via Transgenerational Genetic Transmission of Environmental Information During Evolutionary Synthesis of Deep Neural Networks.
P-TELU: Parametric Tan Hyperbolic Linear Unit Activation for Deep Neural Networks.
Vehicle Logo Retrieval Based on Hough Transform and Deep Learning.
DelugeNets: Deep Networks with Efficient and Flexible Cross-Layer Information Inflows.
Class-Specific Reconstruction Transfer Learning via Sparse Low-Rank Constraint.
Vision-as-Inverse-Graphics: Obtaining a Rich 3D Explanation of a Scene from a Single Image.
Scaling CNNs for High Resolution Volumetric Reconstruction from a Single Image.
Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network.
3D Scene Mesh from CNN Depth Predictions and Sparse Monocular SLAM.
Homography Estimation from Image Pairs with Hierarchical Convolutional Networks.
3D Morphable Models as Spatial Transformer Networks.
RGB-D Object Recognition Using Deep Convolutional Neural Networks.
Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching.
Image-Based Localization Using Hourglass Networks.
Graph-Based Classification of Omnidirectional Images.
Semantic Texture for Robust Dense Tracking.
Learning-Based Inverse Dynamics of Human Motion.
Towards Implicit Correspondence in Signed Distance Field Evolution.
A Biophysical 3D Morphable Model of Face Appearance.
Efficient Separation Between Projected Patterns for Multiple Projector 3D People Scanning.
Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections.
4D Model-Based Spatiotemporal Alignment of Scripted Taiji Quan Sequences.
Symmetry-Factored Statistical Modelling of Craniofacial Shape.
Realtime Dynamic 3D Facial Reconstruction for Monocular Video In-the-Wild.
Learning to Segment Affordances.
CAD: Scale Invariant Framework for Real-Time Object Detection.
Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid.
Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions.
Lightweight Monocular Obstacle Avoidance by Salient Feature Fusion.
Deterministic Policy Gradient Based Robotic Path Planning with Continuous Action Spaces.
Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds.
Multi-view Stereo with Single-View Semantic Mesh Refinement.
Deep Learning for Confidence Information in Stereo and ToF Data Fusion.
Deep Learning Anthropomorphic 3D Point Clouds from a Single Depth Map Camera Viewpoint.
3D Object Reconstruction from a Single Depth View with Adversarial Learning.
SnapNet-R: Consistent 3D Multi-view Semantic Labeling for Robotics.
SkiMap++: Real-Time Mapping and Object Recognition for Robotics.
Long-Term 3D Localization and Pose from Semantic Labellings.
Deep Learning Based Hand Detection in Cluttered Environment Using Skin Segmentation.
LPSNet: A Novel Log Path Signature Feature Based Hand Gesture Recognition Framework.
YOLSE: Egocentric Fingertip Detection from Single RGB Images.
Conditional Regressive Random Forest Stereo-Based Hand Depth Recovery.
Human Action Recognition: Pose-Based Attention Draws Focus to Hands.
Hand Pose Estimation Using Deep Stereovision and Markov-Chain Monte Carlo.
DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation.
Back to RGB: 3D Tracking of Hands and Hand-Object Interactions Based on Short-Baseline Stereo.
Accurate Structure Recovery via Weighted Nuclear Norm: A Low Rank Approach to Shape-from-Focus.
A Factorization Approach for Enabling Structure-from-Motion/SLAM Using Integer Arithmetic.
Factorized Convolutional Neural Networks.
Multilevel Approximate Robust Principal Component Analysis.
PVNN: A Neural Network Library for Photometric Vision.
HSCNN: CNN-Based Hyperspectral Image Recovery from Spectrally Undersampled Projections.
Hierarchical Feature Degradation Based Blind Image Quality Assessment.
Deep Photometric Stereo Network.
Photo-Realistic Simulation of Road Scene for Data-Driven Methods in Bad Weather.
Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB.
In Defense of Shallow Learned Spectral Reconstruction from RGB Images.
Visual Music Transcription of Clarinet Video Recordings Trained with Audio-Based Labelled Data.
Improved Speech Reconstruction from Silent Video.
Exploiting the Complementarity of Audio and Visual Data in Multi-speaker Tracking.
Unsupervised Cross-Modal Deep-Model Adaptation for Audio-Visual Re-identification with Wearable Cameras.
Improving Speaker Turn Embedding by Crossmodal Transfer Learning from Face Embedding.
Registration of RGB and Thermal Point Clouds Generated by Structure From Motion.
LBP-Flow and Hybrid Encoding for Real-Time Water and Fire Classification.
Multi-task Learning Using Multi-modal Encoder-Decoder Networks with Shared Skip Connections.
Accurate Calibration of LiDAR-Camera Systems Using Ordinary Boxes.
Triplet-Based Deep Similarity Learning for Person Re-Identification.
Mutual Foreground Segmentation with Multispectral Stereo Pairs.
Semantic Segmentation of RGBD Videos with Recurrent Fully Convolutional Neural Networks.
Set2Model Networks: Learning Discriminatively To Learn Generative Models.
Near-Duplicate Video Retrieval with Deep Metric Learning.
ViTS: Video Tagging System from Massive Web Multimedia Collections.
Attending to Distinctive Moments: Weakly-Supervised Attention Models for Action Localization in Video.
Adaptive Pooling in Multi-instance Learning for Web Video Annotation.
Cross-Media Learning for Image Sentiment Analysis in the Wild.
Feature Learning with Rank-Based Candidate Selection for Product Search.
Understanding Scenery Quality: A Visual Attention Measure and Its Computational Model.
Scale-Free Content Based Image Retrieval (or Nearly so).
WebLogo-2M: Scalable Logo Detection by Deep Learning from the Web.
Eliminating the Observer Effect: Shadow Removal in Orthomosaics of the Road Network.
HyKo: A Spectral Dataset for Scene Understanding.
Risky Region Localization with Point Supervision.
Ladder-Style DenseNets for Semantic Segmentation of Large Natural Images.
Large Scale Labelled Video Data Augmentation for Semantic Segmentation in Driving Scenarios.
Fast Vehicle Detector for Autonomous Driving.
Going Deeper: Autonomous Steering with Neural Memory Networks.
Are They Going to Cross? A Benchmark Dataset and Baseline for Pedestrian Crosswalk Behavior.
Real-Time Category-Based and General Obstacle Detection for Autonomous Driving.
Improving a Real-Time Object Detector with Compact Temporal Information.
Detecting Nonexistent Pedestrians.
Distantly Supervised Road Segmentation.
Fusing Geometry and Appearance for Road Segmentation.
Modeling the Anisotropic Reflectance of a Surface with Microstructure Engineered to Obtain Visible Contrast After Rotation.
Efficient BRDF Sampling Using Projected Deviation Vector Parameterization.
A Variational Study on BRDF Reconstruction in a Structured Light Scanner.
Bots for Software-Assisted Analysis of Image-Based Transcriptomics.
Automatic 3D Single Neuron Reconstruction with Exhaustive Tracing.
Computer-Automated Malaria Diagnosis and Quantitation Using Convolutional Neural Networks.
Part-to-Whole Registration of Histology and MRI Using Shape Elements.
Virtual Blood Vessels in Complex Background Using Stereo X-Ray Images.
Synthesising Wider Field Images from Narrow-Field Retinal Video Acquired Using a Low-Cost Direct Ophthalmoscope (Arclight) Attached to a Smartphone.
Deep Convolutional Neural Networks for Detecting Cellular Changes Due to Malignancy.
Siamese Networks for Chromosome Classification.
Towards Virtual H&E Staining of Hyperspectral Lung Histology Images Using Conditional Generative Adversarial Networks.
Towards a Spatio-Temporal Atlas of 3D Cellular Parameters During Leaf Morphogenesis.
Discovery of Rare Phenotypes in Cellular Images Using Weakly Supervised Deep Learning.
Spatially-Variant Kernel for Optical Flow Under Low Signal-to-Noise Ratios Application to Microscopy.
Spheroid Segmentation Using Multiscale Deep Adversarial Networks.
Dual Structured Convolutional Neural Network with Feature Augmentation for Quantitative Characterization of Tissue Histology.
Count-ception: Counting by Fully Convolutional Redundant Counting.
Particle Tracking Accuracy Measurement Based on Comparison of Linear Oriented Forests.
Solving Large Multicut Problems for Connectomics via Domain Decomposition.
