IEEE TPAMI

7,373 papers3,087 directions
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is a peer-reviewed journal that publishes research in computer vision, pattern recognition, and machine learning. Between 2024 and 2026, the venue has featured work that integrates theoretical optimization with practical computational tasks. The journal serves as a repository for detailed methodological studies, ranging from foundational mathematical strategies to the development of specialized imaging systems. Research published in TPAMI frequently explores complex optimization frameworks, such as bi-level optimization, hierarchical learning, and constraint learning strategies. The venue also hosts studies on advanced hardware-software integration, including the use of event cameras and Single-Photon Avalanche Diodes (SPADs) for high-speed, low-bandwidth imaging. Other areas of focus include video processing techniques, such as bidirectional temporal feature fusion for exemplar-based colorization. Prolific authors contributing to these developments include Risheng Liu, Jin Zhang, Davide Scaramuzza, and Ramesh Raskar. In the machine learning and artificial intelligence community, TPAMI functions as a venue for research that bridges the gap between sensor-level data acquisition and high-level semantic interpretation. By documenting advancements in value-function-based minimization and semantic image priors, the journal supports the development of algorithmic solutions for pattern analysis. Its role is centered on providing a technical foundation for both the theoretical evolution of learning strategies and the practical implementation of intelligent vision systems.

Papers by Year

2026 568
2025 967
2024 776
2023 1,070
2022 825
2021 502
2020 408
2019 380
2018 350
2017 288
2016 295
2015 262
2014 243
2013 236
2012 198
2011 198
2010 150
2009 136
2008 140
2007 126
2006 110
2005 90
2004 83
2003 89
2002 72
2001 57
2000 49
1999 51
1998 49
1997 53
1996 38
1995 44
1994 29
1993 30
1992 27
1991 31
1990 17
1989 29
1988 7
1987 12
1986 13
1985 4
1984 12
1983 2
1982 5
1981 3
1980 1
1979 1

Top Research Directions

Research directions most represented by papers from this venue.

Generalizing from Synthetic Data to the Real World 24
The Cross Modal Representation Gap 18
Bypassing the Computational Bottleneck of Adversarial Training 16
Hierarchical Temporal Modeling for Long Video Understanding 15
Generalizing Deep Learning Methods Beyond Image Classification 15
Hyperparameter Sensitivity in Complex Machine Learning Frameworks 14
The Hyperparameter Tuning Burden in Specialized Machine Learning Models 14
Clean Accuracy Degradation in Machine Learning Defenses 14
Accelerating Neural Architecture Search Without Full Model Training 13
Preserving Tiny Features Against Spatial Resolution Degradation 13
3D Convolutions for Spatiotemporal Feature Learning 13
Reconstructing Complete Geometry from Partial Point Clouds 13
Knowledge Retention in Continual Deep Learning 13
Test Time Adaptation for Distribution Shift 13
Adversarial Training for Domain Invariant Representations 12

Top Authors

AuthorPapers
Dacheng Tao92
Shuicheng YAN86
Ming-Hsuan Yang78
Luc Van Gool59
Xuelong Li58
Chunhua Shen54
Rama Chellappa54
Ming-Ming Cheng49
Nicu Sebe46
Song-Chun Zhu46
Ling Shao45
Jie Zhou42
Zhouchen Lin42
Xiaochun Cao41
Pascal Fua39
Yi Yang39
Qingming Huang38
Stephen Maybank38
Wanli Ouyang38
Alex Pentland37

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
NVDS$^{\mathbf{+}}$+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation2025
OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation2025
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians2025
OffsetNet: Towards Efficient Multiple Object Tracking, Detection, and Segmentation2025
OmniFuse: Composite Degradation-Robust Image Fusion With Language-Driven Semantics2025
OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection2025
One-for-All: Towards Universal Domain Translation With a Single StyleGAN2025
One Neuron Saved is One Neuron Earned: On Parametric Efficiency of Quadratic Networks2025
Online Learning Under a Separable Stochastic Approximation Framework2025
On Nonconvex SGD Under Unbounded Noise With Weak Gradient Lipschitz and Delayed Stochastic Gradient2025
ONNXPruner: ONNX-Based General Model Pruning Adapter2025
On Positive-Unlabeled Classification From Corrupted Data in GANs2025
On Structuring Hyperspherical Manifold for Probing Novel Biomedical Entities2025
On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media2025
On-the-Fly Modulation for Balanced Multimodal Learning2025
On the Trade-Off Between Flatness and Optimization in Distributed Learning2025
On the Value of Myopic Behavior in Policy Reuse2025
OpenCIR: Conditional Image Repainting With Open Condition Mixture2025
Open-CRB: Toward Open World Active Learning for 3D Object Detection2025
OpenGait: A Comprehensive Benchmark Study for Gait Recognition Toward Better Practicality2025
OpenGAN: Open-Set Recognition via Open Data Generation2025
Optimization of Rank Losses for Image Retrieval2025
Optimizing Latent Variables in Integrating Transfer and Query Based Attack Framework2025
Ordinal Unsupervised Domain Adaptation With Recursively Conditional Gaussian Imposed Variational Disentanglement2025
Otter: A Multi-Modal Model With In-Context Instruction Tuning2025
Out-of-Distribution Generalization on Graphs: A Survey2025
PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes2025
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning2025
Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding2025
Partial Distribution Matching via Partial Wasserstein Adversarial Networks2025
Partial Scene Text Retrieval2025
PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning2025
PATNAS: A Path-Based Training-Free Neural Architecture Search2025
PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations2025
PDPP: Projected Diffusion for Procedure Planning in Instructional Videos2025
Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling2025
Physically Based Facial Texture Generation in the Wild2025
Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging2025
PhysMLE: Generalizable and Priors-Inclusive Multi-Task Remote Physiological Measurement2025
PIT: A Plug-and-Play Image Translator for Making Off-the-Shelf Models Adapt to Corruptions2025
Pixel2Pixel: A Pixelwise Approach for Zero-Shot Single Image Denoising2025
Pixel-Inconsistency Modeling for Image Manipulation Localization2025
Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection2025
Pixel-Perfect Structure-From-Motion With Featuremetric Refinement2025
Planner3D: LLM-enhanced Graph Prior Meets 3D Indoor Scene Explicit Regularization2025
PointLLM-V2: Empowering Large Language Models to Better Understand Point Clouds2025
PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimation2025
PonderV2: Improved 3D Representation With a Universal Pre-Training Paradigm2025
PoseScript: Linking 3D Human Poses and Natural Language2025
Practical Compact Deep Compressed Sensing2025

« prev Page 22/148 next »