IEEE TPAMI 2016

295 papers
The 2016 edition of IEEE Transactions on Pattern Analysis and Machine Intelligence featured research focused heavily on sparse learning and optimization techniques. Key contributions addressed the efficiency of high-dimensional data processing through safe screening rules, pathwise optimization, and memory-efficient sparse learning. Research also explored spatial aggregation methods and the reduction of bounding box dependencies in visual recognition tasks. Prolific authors contributing to this volume included Xiaogang Wang, Cewu Lu, and Richard Szeliski. Applied research during this period covered diverse areas such as person re-identification via saliency learning, crowd analysis using $L_0$ regularized stationary-time estimation, and large-scale image retrieval. The publication also featured work on heterogeneous transfer learning across disparate feature spaces and efficient activity detection in untrimmed video using max-subgraph search. Additionally, a special section was dedicated to research from CVPR 2013, highlighting advancements in computer vision and pattern recognition methodologies.

Top Research Directions

Research directions most represented by IEEE TPAMI 2016 papers.

Jointly Optimizing Representations and Clusters 3
Overcoming Local Minima in Iterative Point Registration 3
Optimizing Partial Area Under the ROC Curve 2
Global Optimization in High Dimensional Transformation Spaces 2
Overcoming the Gaussian Assumption in High-Dimensional Learning 2
Hierarchical Feature Learning via Deep Convolutional Networks 2
Generalizing to Unseen Categories via Shared Semantic Spaces 2
Mitigating the Computational Overhead of Deep Ensembles 2
The Upstream Detection Bottleneck in Multi Object Tracking 2
Scalable Non-Linear Manifold Learning 2
Resolving Depth Ambiguity in Monocular 3D Reconstruction 2
Analyzing Dynamical Systems through Phase Space Geometry 1
Diagnostic Attribute Slicing for Computer Vision Evaluation 1
Global Cycle Consistency for Multi Object Alignment 1
Globally Optimal Point Cloud Registration Without Initialization 1

Top Authors

AuthorPapers
Shuicheng YAN8
Chunhua Shen6
Zhouchen Lin6
Dacheng Tao5
Shaogang Gong5
Fernando De la Torre4
Ming-Hsuan Yang4
Shiguang Shan4
Tao Xiang4
Xiaofei He4
Bernt Schiele3
Bodo Rosenhahn3
Chen Change Loy3
Cordelia Schmid3
Elisa Ricci3
Hongdong Li3
Jitendra Malik3
Junbin Gao3
Kaiming He3
Ling Shao3

Impactful Papers

Papers from IEEE TPAMI 2016 that shaped research clusters.

Influential

Papers

Title
Infinite Factorial Unbounded-State Hidden Markov Model
Information-Theoretic Compressive Measurement Design
Interacting Multiview Tracker
Interferences in Match Kernels.
Intrinsic Scene Properties from a Single RGB-D Image
Isotonic Modeling with Non-Differentiable Loss Functions with Application to Lasso Regularization.
Joint Binary Classifier Learning for ECOC-Based Multi-Class Classification
Joint Binary Classifier Learning for ECOC-Based Multi-Class Classification.
Joint Color-Spatial-Directional Clustering and Region Merging (JCSD-RM) for Unsupervised RGB-D Image Segmentation
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval.
Joint Head Pose/Soft Label Estimation for Human Recognition <italic>In-The-Wild</italic>
Joint Image Clustering and Labeling by Matrix Factorization
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition
Kronecker-Markov Prior for Dynamic 3D Reconstruction
Label-Embedding for Image Classification
Label-Embedding for Image Classification.
Laplace Approximation for Divisive Gaussian Processes for Nonstationary Regression
Laplace Approximation for Divisive Gaussian Processes for Nonstationary Regression.
Laplacian Regularized Low-Rank Representation and Its Applications
Laplacian Regularized Low-Rank Representation and Its Applications.
Learning a Deep Model for Human Action Recognition from Novel Viewpoints
Learning a Deep Model for Human Action Recognition from Novel Viewpoints.
Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
Learning Deep Representation for Face Alignment with Auxiliary Attributes
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields.
Learning Discriminative Bayesian Networks from High-Dimensional Continuous Neuroimaging Data.
Learning Support Correlation Filters for Visual Tracking
Learning SVM in Kreĭn Spaces
Learning to Deblur
Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis
Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis.
Learn on Source, Refine on Target: A Model Transfer Learning Framework with Random Forests
Leveraging the Wisdom of the Crowd for Fine-Grained Recognition.
Lifting Object Detection Datasets into 3D
Local Feature Discriminant Projection
Local Feature Discriminant Projection.
Local Submodularization for Binary Pairwise Energies
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
Making Trillion Correlations Feasible in Feature Grouping and Selection
Map-Based Probabilistic Visual Self-Localization
Map-Based Probabilistic Visual Self-Localization.
Max-Margin Action Prediction Machine
Max-Margin Deep Generative Models for (Semi-)Supervised Learning
Minimum Entropy Rate Simplification of Stochastic Processes.
Mixture of Switching Linear Dynamics to Discover Behavior Patterns in Object Tracks.
ModDrop: Adaptive Multi-Modal Gesture Recognition
Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization

« prev Page 4/6 next »