IEEE TPAMI 2017

288 papers
The 2017 edition of IEEE Transactions on Pattern Analysis and Machine Intelligence featured 54 papers focusing on 3D reconstruction, manifold learning, and adaptive algorithms. Research themes included hierarchical coarse-to-fine 3D reconstruction, geometric shape descriptors for medical phenotyping, and methods for overcoming topological constraints in mesh reconstruction. Theoretical advancements were made in subspace clustering via vanishing polynomials and solving the pre-image problem in manifold learning. The volume also emphasized real-time inference and online adaptation, with studies on non-stationary data streams and evolving target representations for visual tracking. Specific technical contributions included the generalization of pooling functions in convolutional neural networks and the development of Kendall and Mallows kernels for permutations. Prolific authors for the year included Qi Tian, Fernando De la Torre, and Jean Ponce. Application-oriented research covered diverse areas such as face recognition through collaborative representation and 3D fingerprint identification using colored LED illumination.

Top Research Directions

Research directions most represented by IEEE TPAMI 2017 papers.

Shared Feature Map Computation for Efficient Visual Recognition 3
Bridging the Weakly Supervised Localization Gap 3
Bridging the Modality Gap in Cross Spectral Vision 3
Online Appearance Adaptation for Visual Tracking 3
Iterative Pseudo Label Refinement for Weakly Supervised Learning 3
Learnable Upsampling for Dense Spatial Prediction 2
Training Models via Progressive Task Complexity 2
Overcoming the Latency Bottleneck of Online Model Adaptation 2
From Fractional Solutions to Discrete Decisions 2
Semidefinite Relaxation for Non-Convex Engineering Optimization 2
Loss Weighting via Predictive Uncertainty 2
The Computational Overhead of Iterative Training Loops 2
Compressing Deep Learning Representations with PCA 2
Overcoming the Scalability Bottleneck in Semidefinite Programming 2
Test Time Adaptation for Distribution Shift 2

Top Authors

AuthorPapers
Shuicheng YAN8
Stephen Maybank8
Jitendra Malik7
Anton van den Hengel6
Ming-Hsuan Yang6
Chunhua Shen5
Guo-Jun Qi5
Bing Li4
Lingqiao Liu4
Minh N. Do4
Tao Xiang4
Xiaogang Wang4
Andrew Zisserman3
Dacheng Tao3
Filipe Rodrigues3
Francisco C. Pereira3
Haibin Ling3
Houwen Peng3
In So Kweon3
Jinhui Tang3

Impactful Papers

Papers from IEEE TPAMI 2017 that shaped research clusters.

Foundational

Influential

Papers

Title
Squeeze-and-Excitation Networks
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
State of the Journal
Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation.
Structured Low-Rank Matrix Factorization: Global Optimality, Algorithms, and Applications
Submodular Attribute Selection for Visual Recognition
Summarizing Unconstrained Videos Using Salient Montages.
Super Normal Vector for Human Activity Recognition with Depth Cameras
SurfCut: Surfaces of Minimal Paths from Topological Structures.
Template Matching via Densities on the Roto-Translation Group
Temporal Segment Networks for Action Recognition in Videos
Tetrahedron Based Fast 3D Fingerprint Identification Using Colored LEDs Illumination
The Kendall and Mallows Kernels for Permutations
The Manhattan Frame Model—Manhattan World Inference in the Space of Surface Normals
Top-Down Visual Saliency via Joint CRF and Dictionary Learning
Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation
Transformations Based on Continuous Piecewise-Affine Velocity Fields
Tri-Clustered Tensor Completion for Social-Aware Image Tag Refinement
Tri-Clustered Tensor Completion for Social-Aware Image Tag Refinement.
Two-Class Weather Classification
Variance Reduced Methods for Non-Convex Composition Optimization
Video2vec Embeddings Recognize Events When Examples Are Scarce
Video Object Discovery and Co-Segmentation with Extremely Weak Supervision
Video Object Segmentation Without Temporal Information
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning.
Visually Grounded Meaning Representations
Visual Vibrometry: Estimating Material Properties from Small Motions in Video
Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes
Weakly-Supervised Image Annotation and Segmentation with Objects and Attributes.
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning.
Write a Classifier: Predicting Visual Classifiers from Unstructured Text
Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly
局所対数Euclid多変量Gauss記述子とその応用画像分類【Powered by NICT】
物体再構成のためのカテゴリー特異的変形可能な3Dモデルの学習【Powered by NICT】
線特徴を用いたマイクロレンズベース光場カメラの幾何学的キャリブレーション【Powered by NICT】

« prev Page 6/6