Bagdanov, A.[Andrew]
* 2015: ICDAR 2015 competition on Robust Reading
* 2022: Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition
Includes: Bagdanov, A.[Andrew] Bagdanov, A.[Andy]
Bagdanov, A.D.
* 1993: Annual Research Report
* 1997: Projection Profile Based Skew Estimation Algorithm for JPEG Compressed Images
* 1998: Projection Profile Based Skew Estimation
* 2001: Fine-grained document genre classification using first order random graphs
* 2002: Granulometric analysis of document images
* 2002: Multiscale Document Description Using Rectangular Granulometries
* 2003: First order Gaussian graphs for efficient structure classification
* 2003: Understanding document analysis and understanding (through modeling)
* 2004: Multiscale Document Description Using Rectangular Granulometries
* 2005: Acquisition of high-resolution images through on-line saccade sequence planning
* 2006: Boosting Color Saliency in Image Feature Detection
* 2006: Improving evidential quality of surveillance imagery through active face tracking
* 2006: Learning Foveal Sensing Strategies in Unconstrained Surveillance Environments
* 2006: reinforcement learning approach to active camera foveation, A
* 2007: Adaptive uncertainty estimation for particle filter-based trackers
* 2007: Improving the robustness of particle filter-based visual trackers using online parameter adaptation
* 2009: Robust and Efficient Multipose Face Detection Using Skin Color Segmentation
* 2009: Towards Real-Time Human Action Recognition
* 2010: Automatic Key Pose Selection for 3D Human Action Recognition
* 2010: Harmony potentials for joint classification and segmentation
* 2010: Reactive Object Tracking with a Single PTZ Camera
* 2010: Recursive Coarse-to-Fine Localization for Fast Object Detection
* 2011: Accurate Moving Cast Shadow Suppression Based on Local Color Constancy Detection
* 2011: Efficient discriminative multiresolution cascade for real-time human detection applications
* 2012: Color attributes for object detection
* 2012: Harmony Potentials: Fusing Global and Local Scale for Semantic Image Segmentation
* 2012: Identity Inference: Generalizing Person Re-identification Scenarios
* 2012: Multi-pose face detection for accurate face logging
* 2012: Multipage document retrieval by textual and visual representations
* 2012: Posterity Logging of Face Imagery for Video Surveillance
* 2012: Real-time hand status recognition from RGB-D imagery
* 2013: Coloring Action Recognition in Still Images
* 2013: Document Classification and Page Stream Segmentation for Digital Mailroom Applications
* 2013: Multi-target Data Association Using Sparse Reconstruction
* 2013: Passive Profiling and Natural Interaction Metaphors for Personalized Multimedia Museum Experiences
* 2013: Using 3D Models to Recognize 2D Faces in the Wild
* 2014: Fisher Vectors over Random Density Forests for Object Recognition
* 2014: Leveraging local neighborhood topology for large scale person re-identification
* 2014: Local Pyramidal Descriptors for Image Recognition
* 2014: Multimodal page classification in administrative document image streams
* 2014: Real-time people counting from depth imagery of crowded environments
* 2014: Scale Coding Bag-of-Words for Action Recognition
* 2014: Unsupervised Scene Adaptation for Faster Multi-scale Pedestrian Detection
* 2015: MORF: Multi-Objective Random Forests for face characteristic estimation
* 2015: Person Re-Identification by Iterative Re-Weighted Sparse Ranking
* 2015: Recognizing Actions Through Action-Specific Person Detection
* 2015: Sparse radial sampling LBP for writer identification
* 2016: Hierarchical part detection with deep neural networks
* 2017: Bandwidth Limited Object Recognition in High Resolution Imagery
* 2017: Domain-Adaptive Deep Network Compression
* 2017: RankIQA: Learning from Rankings for No-Reference Image Quality Assessment
* 2017: Reading Text in the Wild from Compressed Images
* 2018: Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
* 2018: Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
* 2018: Scale coding bag of deep features for human attribute and action recognition
* 2018: Word Spotting in Scene Images Based on Character Recognition
* 2019: Domain Adaptation for Privacy-Preserving Pedestrian Detection in Thermal Imagery
* 2019: Exploiting Unlabeled Data in CNNs by Self-Supervised Learning to Rank
* 2019: FAST: Facilitated and Accurate Scene Text Proposals through FCN Guided Pruning
* 2019: GADA: Generative Adversarial Data Augmentation for Image Quality Assessment
* 2019: Webly-supervised zero-shot learning for artwork instance recognition
* 2020: Generative Feature Replay For Class-Incremental Learning
* 2020: Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery
* 2021: Robust pedestrian detection in thermal imagery using synthesized images
* 2022: Continually Learning Self-Supervised Representations with Projected Functional Regularization
* 2022: Long-Tailed Class Incremental Learning
* 2023: Class-Incremental Learning: Survey and Performance Evaluation on Image Classification
* 2023: Masked Autoencoders are Efficient Class Incremental Learners
* 2024: Continual learning for adaptive social network identification
Includes: Bagdanov, A.D. Bagdanov, A.D.[Andrew D.]
69 for Bagdanov, A.D.
Bagdazian, R.
* 1984: Optimal Fourier Coding of Image Boundaries
* 1985: Texture Synthsis and Compression Using Gaussian-Markov Random Field Models