Journals starting with deep

DeepAffective17 * *Deep Affective Learning and Context Modeling
* Action-Affect-Gender Classification Using Multi-task Representation Learning
* DeepSpace: Mood-Based Image Texture Generation for Virtual Reality from Music
* DyadGAN: Generating Facial Expressions in Dyadic Interactions
* EMOTIC: Emotions in Context Dataset
* Exploring Contextual Engagement for Trauma Recovery
* Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
* It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation
* Personalized Automatic Estimation of Self-Reported Pain Intensity from Facial Expressions
* Speech-Driven 3D Facial Animation with Implicit Emotional Awareness: A Deep Learning Approach
10 for DeepAffective17

DeepGlobe18 * *DeepGlobe: A Challenge for Parsing the Earth through Satellite Images
* Building Detection from Satellite Imagery Using a Composite Loss Function
* Building Detection from Satellite Imagery using Ensemble of Size-Specific Detectors
* Building Extraction from Satellite Images Using Mask R-CNN with Building Boundary Regularization
* CNNs Fusion for Building Detection in Aerial Images for the Building Detection Challenge
* D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction
* Deep Aggregation Net for Land Cover Classification
* DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
* Dense Fusion Classmate Network for Land Cover Classification
* Feature Pyramid Network for Multi-class Land Segmentation
* Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery
* Land Cover Classification from Satellite Imagery with U-Net and Lovász-Softmax Loss
* Land Cover Classification with Superpixels and Jaccard Index Post-Optimization
* NU-Net: Deep Residual Wide Field of View Convolutional Neural Network for Semantic Segmentation
* Residual Inception Skip Network for Binary Segmentation
* Road Detection with EOSResUNet and Post Vectorizing Algorithm
* Roadmap Generation using a Multi-stage Ensemble of Deep Neural Networks with Smoothing-Based Optimization
* Rotated Rectangles for Symbolized Building Footprint Extraction
* Semantic Binary Segmentation Using Convolutional Networks without Decoders
* Semantic Segmentation Based Building Extraction Method Using Multi-source GIS Map Datasets and Satellite Imagery
* Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery
* Stacked U-Nets with Multi-output for Road Extraction
* TernausNetV2: Fully Convolutional Network for Instance Segmentation
* Uncertainty Gated Network for Land Cover Segmentation
24 for DeepGlobe18

DeepHealth22 * *Deep-Learning and High Performance Computing to Boost Biomedical Applications
* AI Support for Accelerating Histopathological Slide Examinations of Prostate Cancer in Clinical Studies
* Automatic Detection of Epileptic Seizures with Recurrent and Convolutional Neural Networks
* Compact Deep Ensemble for High Quality Skin Lesion Classification, A
* Detection of Pulmonary Conditions Using the DeepHealth Framework
* Enabling Efficient Training of Convolutional Neural Networks for Histopathology Images
* Fast Learning Framework for Denoising of Ultrasound 2D Videos and 3D Images
* Lung Nodules Segmentation with DeepHealth Toolkit
* UniToBrain Dataset: A Brain Perfusion Dataset
9 for DeepHealth22

DeepLearn-C16 * *Deep Vision: Deep Learning in Computer Vision
* Adversarial Diversity and Hard Positive Generation
* Deep End2End Voxel2Voxel Prediction
* Faster R-CNN Features for Instance Search
* Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association
* Learning by Tracking: Siamese CNN for Robust Target Association
* ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation
* Rich Image Captioning in the Wild
8 for DeepLearn-C16

DeepLearn-G17 * *Deep Vision: Deep Learning in Computer Vision
* 3D Morphable Models as Spatial Transformer Networks
* 3D Scene Mesh from CNN Depth Predictions and Sparse Monocular SLAM
* Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network
* Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching
* Graph-Based Classification of Omnidirectional Images
* Homography Estimation from Image Pairs with Hierarchical Convolutional Networks
* Image-Based Localization Using Hourglass Networks
* RGB-D Object Recognition Using Deep Convolutional Neural Networks
* Scaling CNNs for High Resolution Volumetric Reconstruction from a Single Image
* Semantic Texture for Robust Dense Tracking
* Vision-as-Inverse-Graphics: Obtaining a Rich 3D Explanation of a Scene from a Single Image
12 for DeepLearn-G17

DeepLearn-G18 * *Deep Vision: Deep Learning in Computer Vision
* 3D Surface Reconstruction by Pointillism
* 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues
* Attaining Human-Level Performance with Atlas Location Autocontext for Anatomical Landmark Detection in 3D CT Data
* Deep Fundamental Matrix Estimation Without Correspondences
* Deep Learning for Multi-path Error Removal in ToF Sensors
* Deep Normal Estimation for Automatic Shading of Hand-Drawn Characters
* Detecting Parallel-Moving Objects in the Monocular Case Employing CNN Depth Maps
* Evaluation of CNN-Based Single-Image Depth Estimation Methods
* High Quality Facial Surface and Texture Synthesis via Generative Adversarial Networks
* Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
* Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis
* Learning Structure-from-Motion from Motion
* Multi-kernel Diffusion CNNs for Graph-Based Learning on Point Clouds
* Object Pose Estimation from Monocular Image Using Multi-view Keypoint Correspondence
* PosIX-GAN: Generating Multiple Poses Using GAN for Pose-Invariant Face Recognition
* Scene Coordinate Regression with Angle-Based Reprojection Loss for Camera Relocalization
* Semi-supervised Semantic Matching
* Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshes, A
19 for DeepLearn-G18

DeepLearn-T17 * *Deep Vision: Deep Learning in Computer Vision
* Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition
* Crowd-11: A Dataset for Fine Grained Crowd Behaviour Analysis
* Fixation Prediction in Videos Using Unsupervised Hierarchical Features
* Kernalised Multi-resolution Convnet for Visual Tracking
* Learning Latent Temporal Connectionism of Deep Residual Visual Abstractions for Identifying Surgical Tools in Laparoscopy Procedures
* Recurrent Memory Addressing for Describing Videos
* SANet: Structure-Aware Network for Visual Tracking
* Temporal Domain Neural Encoder for Video Representation Learning
* Temporally Steered Gaussian Attention for Video Understanding
10 for DeepLearn-T17

DeepLearn14 * *Deep Vision: Deep Learning in Computer Vision
* CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
* Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction
* Heterogeneous Multi-Task Learning for Human Pose Estimation with Deep Convolutional Neural Network
* Piggyback Representation for Action Recognition, A
* Unrolling Loopy Top-Down Semantic Feedback in Convolutional Deep Networks

DeepLearn15 * *Deep Vision: Deep Learning in Computer Vision
* Channel-Max, Channel-Drop and Stochastic Max-pooling
* Color constancy using CNNs
* Convolutional recurrent neural networks: Learning spatial dependencies for image representation
* Deep learning of binary hash codes for fast image retrieval
* Exploiting local features from deep networks for image retrieval
* From generic to specific deep representations for visual recognition
* Learning to count with deep object features
* Multi-scale pyramid pooling for deep convolutional representation
* Object level deep feature pooling for compact image representation
* Self-tuned deep super resolution
* Subset feature learning for fine-grained category classification
12 for DeepLearn15

DeepLearn16 * *Deep Vision: Deep Learning in Computer Vision
* 3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information
* Class-Specific Object Pose Estimation and Reconstruction Using 3D Part Geometry
* CNN Cascade for Landmark Guided Semantic Part Segmentation, A
* Deep Disentangled Representations for Volumetric Reconstruction
* Deep Kinematic Pose Regression
* Deep Shape from a Low Number of Silhouettes
* gvnn: Neural Network Library for Geometric Computer Vision
* How Useful Is Photo-Realistic Rendering for Visual Learning?
* Improving Constrained Bundle Adjustment Through Semantic Scene Labeling
* Learning Covariant Feature Detectors
* Learning the Structure of Objects from Web Supervision
* Monocular Surface Reconstruction Using 3D Deformable Part Models
* On-Line Large Scale Semantic Fusion
* Overcoming Occlusion with Inverse Graphics
* Scene Segmentation Driven by Deep Learning and Surface Fitting
* VConv-DAE: Deep Volumetric Shape Learning Without Object Labels
17 for DeepLearn16

DeepLearnRV17 * *Deep Learning for Robotic Vision
* 3D Pose Regression Using Convolutional Neural Networks
* Automated Risk Assessment for Scene Understanding and Domestic Robots Using RGB-D Data and 2.5D CNNs at a Patch Level
* Curiosity-Driven Exploration by Self-Supervised Prediction
* Detecting and Grouping Identical Objects for Region Proposal and Classification
* End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning
* Episode-Based Active Learning with Bayesian Neural Networks
* Finding Anomalies with Generative Adversarial Networks for a Patrolbot
* Hand Movement Prediction Based Collision-Free Human-Robot Interaction
* Learning Robot Activities from First-Person Human Videos Using Convolutional Future Regression
* Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks
* Real-Time Hand Grasp Recognition Using Weakly Supervised Two-Stage Convolutional Neural Networks for Understanding Manipulation Actions
* Semantic Instance Segmentation for Autonomous Driving
* Time-Contrastive Networks: Self-Supervised Learning from Multi-view Observation
* Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination
15 for DeepLearnRV17

DeepLearnRV18 * *Deep Learning for Robotic Vision
* Action-Conditioned Convolutional Future Regression Models for Robot Imitation Learning
* Active Vision Dataset Benchmark
* Embodied Question Answering
* Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation
* Learning Instance Segmentation by Interaction
* New Metrics and Experimental Paradigms for Continual Learning
* Paris-Lille-3D: A Point Cloud Dataset for Urban Scene Segmentation and Classification
* VisDA: A Synthetic-to-Real Benchmark for Visual Domain Adaptation
* Zero-Shot Visual Imitation
10 for DeepLearnRV18

DeepLearnV14 * *Deep Learning on Visual Data
* Deep Learning in the EEG Diagnosis of Alzheimer's Disease
* Human Action Recognition Using Action Bank Features and Convolutional Neural Networks
* Hybrid CNN-HMM Model for Street View House Number Recognition
* Pedestrian Detection with Deep Convolutional Neural Network
* View and Illumination Invariant Object Classification Based on 3D Color Histogram Using Convolutional Neural Networks

DeepMTL21 * *Deep Multi-Task Learning in Computer Vision
* Audio-Visual Transformer Based Crowd Counting
* Concurrent Discrimination and Alignment for Self-Supervised Feature Learning
* ConvNets vs. Transformers: Whose Visual Representations are More Transferable?
* In Defense of the Learning Without Forgetting for Task Incremental Learning
* MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention
* Multi-Modal RGB-D Scene Recognition Across Domains
* UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks
8 for DeepMTL21

DEEPRETAIL20 * *Deep Understanding Shopper Behaviours and Interactions in Intelligent Retail Environments
* 3d Vision-based Shelf Monitoring System for Intelligent Retail
* Data-driven Knowledge Discovery in Retail: Evidences from the Vending Machine's Industry
* Faithful Fit, Markerless, 3d Eyeglasses Virtual Try-on
* People Counting on Low Cost Embedded Hardware During the SARS-COV-2 Pandemic
* Performance Assessment of Face Analysis Algorithms with Occluded Faces
* Saliency-based Technique for Advertisement Layout Optimisation to Predict Customers' Behaviour, A
* Shoppers Detection Analysis in an Intelligent Retail Environment
* Who Is in the Crowd? Deep Face Analysis for Crowd Understanding
9 for DEEPRETAIL20

DeepSLAM18 * *Deep Learning for Visual SLAM
* DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction
* Geometric Consistency for Self-Supervised End-to-End Visual Odometry
* Global Pose Estimation with an Attention-Based Recurrent Network
* Learning 3D Scene Semantics and Structure from a Single Depth Image
* Learning Descriptor, Confidence, and Depth Estimation in Multi-view Stereo
* Mask-SLAM: Robust Feature-Based Monocular SLAM by Masking Using Semantic Segmentation
* Monocular Depth Prediction Using Generative Adversarial Networks
* QuadricSLAM: Dual Quadrics as SLAM Landmarks
* SuperPoint: Self-Supervised Interest Point Detection and Description
* Towards CNN Map Representation and Compression for Camera Relocalisation
* Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning
12 for DeepSLAM18

DeepSLAM19 * *Deep Learning for Visual SLAM
* Adversarial Networks for Camera Pose Regression and Refinement
* Camera Relocalization by Exploiting Multi-View Constraints for Scene Coordinates Regression
* How to Improve CNN-Based 6-DoF Camera Pose Estimation
* SLAMANTIC: Leveraging Semantics to Improve VSLAM in Dynamic Environments
* Spatial Perception by Object-Aware Visual Scene Representation
* System Framework for Localization and Mapping using High Resolution Cameras of Mobile Devices, A
* TriDepth: Triangular Patch-Based Deep Depth Prediction
8 for DeepSLAM19

DeepVision20 * *Deep Vision: Deep Learning in Computer Vision
* Can We Learn Heuristics for Graphical Model Inference Using Reinforcement Learning?
* Deflating Dataset Bias Using Synthetic Data Augmentation
* Distilling Knowledge from Refinement in Multiple Instance Detection Networks
* Homogeneous Linear Inequality Constraints for Neural Network Activations
* MUTE: Inter-class Ambiguity Driven Multi-hot Target Encoding for Deep Neural Network Design
* P2L: Predicting Transfer Learning for Images and Semantic Relations
* Robust One Shot Audio to Video Generation
* S2LD: Semi-Supervised Landmark Detection in Low Resolution Images and Impact on Face Verification
* Semi-Supervised Learning with Scarce Annotations
* SmoothMix: a Simple Yet Effective Data Augmentation to Train Robust Classifiers
* Spatio-temporal action detection and localization using a hierarchical LSTM
* SUW-Learn: Joint Supervised, Unsupervised, Weakly Supervised Deep Learning for Monocular Depth Estimation
* Top-Down Networks: A coarse-to-fine reimagination of CNNs
14 for DeepVision20

DeepVisual16 * *Interpretation and Visualization of Deep Neural Nets
* Dense Residual Pyramid Networks for Salient Object Detection
* Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios
* Glance and Glimpse Network: A Stochastic Attention Model Driven by Class Saliency
* Image Patch Matching Using Convolutional Descriptors with Euclidean Distance
* Multi-Scale Hierarchy Deep Feature Aggregation for Compact Image Representations
* Quantitative Analysis of a Bioplausible Model of Misperception of Slope in the Café Wall Illusion
7 for DeepVisual16

Index for "d"


Last update:16-Mar-24 21:12:13
Use price@usc.edu for comments.