Signal Processing papers
Pofolia’s corpus holds 86 papers from Signal Processing (2012–2025), each with a short summary. Below, the 20 most-cited, then the most recently added.
At a glance
- Most cited: Data mining: concepts and techniques (2012, 28,876 citations).
- The 20 papers listed have 105,308 citations between them.
- 4 of the 5 with a known journal quartile appeared in a Q1 journal.
- 9 have a free full text (open access).
- Most frequent journals: arXiv (Cornell University), Proceedings of the AAAI Conference on Artificial Intelligence, ACM Transactions on Database Systems.
- Published between 2012 and 2023.
Most cited
Ranked by citation count. Because citations accumulate over time, this list naturally leans towards work published a few years ago; for where the field is now, see “recently added”. How to read the signals
Data mining: concepts and techniques
Choice Reviews Online · 2012 · 28,876 citations
This book's second edition significantly updates concepts and techniques for discovering patterns in large datasets, reflecting recent advancements in mining complex data types.
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
arXiv (Cornell University) · 2014 · 10,809 citations · Open access
Gated recurrent units (GRUs) and Long Short-Term Memory (LSTM) networks significantly outperform traditional recurrent units like tanh for sequence modeling tasks, with GRUs showing comparable performance to LSTMs.
Overview of the High Efficiency Video Coding (HEVC) Standard
IEEE Transactions on Circuits and Systems for Video Technology · 2012 · Q1 · SJR 2.00 · FWCI 440.13 · 8,131 citations
The upcoming High Efficiency Video Coding (HEVC) standard aims to achieve approximately 50% bit-rate reduction for the same perceptual video quality compared to existing standards.
LSTM: A Search Space Odyssey
IEEE Transactions on Neural Networks and Learning Systems · 2016 · Q1 · SJR 3.00 · FWCI 383.53 · 6,889 citations · Open access
A large-scale analysis of eight Long Short-Term Memory (LSTM) variants found that none significantly outperform the standard LSTM architecture, highlighting the forget gate and output activation function as its most critical components.
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Proceedings of the AAAI Conference on Artificial Intelligence · 2021 · SJR 1.00 · 6,292 citations · Open access
Informer, a new transformer-based model, significantly improves long sequence time-series forecasting (LSTF) by addressing Transformer's quadratic complexity and memory issues.
Stochastic Geometry and its Applications
Wiley series in probability and statistics · 2013 · FWCI 65.27 · 4,516 citations
This is an updated edition of a classic text on stochastic geometry and spatial statistics, a field crucial to physics, materials science, engineering, biology, and environmental sciences.
Empirical Analysis of Predictive Algorithms for Collaborative Filtering
arXiv (Cornell University) · 2013 · 4,515 citations · Open access
Bayesian networks with decision trees and correlation methods outperform Bayesian-clustering and vector-similarity methods in collaborative filtering tasks across various conditions.
Multimodal Machine Learning: A Survey and Taxonomy
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2018 · Q1 · SJR 4.00 · FWCI 153.08 · 4,343 citations
This survey introduces a novel taxonomy for multimodal machine learning, moving beyond simple fusion categories to identify core challenges like representation, translation, alignment, fusion, and co-learning.
WaveNet: A Generative Model for Raw Audio
arXiv (Cornell University) · 2016 · 3,622 citations · Open access
WaveNet, a deep neural network, generates raw audio waveforms by predicting each sample based on all previous ones, achieving state-of-the-art naturalness in text-to-speech synthesis.
Audio Set: An ontology and human-labeled dataset for audio events
2017 · 3,003 citations
A new large-scale dataset, Audio Set, has been created with 632 audio event classes, manually annotated from YouTube videos, to address the data gap in audio event recognition research.
librosa: Audio and Music Signal Analysis in Python
Proceedings of the Python in Science Conferences · 2015 · 2,971 citations · Open access
Librosa, a Python package for audio and music signal processing, has released version 0.4.0, offering implementations for common music information retrieval tasks.
Are Transformers Effective for Time Series Forecasting?
Proceedings of the AAAI Conference on Artificial Intelligence · 2023 · SJR 1.00 · 2,709 citations · Open access
Simple one-layer linear models (LTSF-Linear) surprisingly outperform complex Transformer-based models on long-term time series forecasting tasks across nine real-world datasets.
DBSCAN Revisited, Revisited
ACM Transactions on Database Systems · 2017 · Q2 · FWCI 70.42 · 2,652 citations
This paper argues that a previous critique of the DBSCAN algorithm was misdirected, attributing performance issues to spatial index assumptions rather than the algorithm itself.
CNN architectures for large-scale audio classification
2017 · 2,478 citations
Convolutional Neural Networks (CNNs) adapted from image classification achieve strong performance on a massive audio classification task involving 70 million training videos.
WaveNet: A Generative Model for Raw Audio
arXiv (Cornell University) · 2016 · 2,472 citations
WaveNet is a novel deep neural network that generates raw audio waveforms by predicting each audio sample based on all previous ones, achieving state-of-the-art naturalness in text-to-speech synthesis.
Drebin: Effective and Explainable Detection of Android Malware in Your Pocket
2014 · 2,302 citations
Drebin is a new lightweight method that detects Android malware directly on smartphones using broad static analysis, identifying 94% of malware with few false alarms.
A Tutorial on Principal Component Analysis
arXiv (Cornell University) · 2014 · 2,272 citations · Open access
This tutorial aims to demystify Principal Component Analysis (PCA), a widely used but often poorly understood data analysis technique, by building intuition and deriving its underlying mathematics from simple concepts.
Recurrent Neural Networks for Multivariate Time Series with Missing Values
Scientific Reports · 2018 · Q1 · FWCI 134.56 · 2,163 citations · Open access
A novel deep learning model, GRU-D, effectively utilizes missing data patterns to improve multivariate time series prediction, outperforming existing methods.
Dissecting Android Malware: Characterization and Evolution
2012 · 2,149 citations
Researchers characterized over 1,200 Android malware samples collected between August 2010 and October 2011, revealing rapid evolution that circumvents current antivirus software.
VoxCeleb: A Large-Scale Speaker Identification Dataset
2017 · 2,144 citations
A fully automated pipeline using computer vision techniques has been developed to create VoxCeleb, a large-scale, in-the-wild speaker identification dataset featuring hundreds of thousands of utterances from over 1,000 celebrities.
Recently added
Large Language Models for Cyber Security: A Systematic Literature Review
ACM Transactions on Software Engineering and Methodology · 2025 · Q1 · SJR 1.00 · FWCI 13.56 · 136 citations
A systematic review of 185 papers reveals Large Language Models (LLMs) are increasingly applied to cybersecurity tasks like vulnerability detection and malware analysis, with a significant trend towards autonomous agents for complex workflows.
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025 · Q1 · SJR 4.00 · FWCI 31.66 · 64 citations
ViewCrafter synthesizes high-fidelity novel views from single or sparse images by leveraging video diffusion models and point-based 3D clues, achieving improved camera pose control and generation range.
Transformers in Time Series: A Survey
2023 · 1,020 citations · Open access
This survey systematically reviews Transformer models adapted for time series analysis, highlighting their strengths in capturing long-range dependencies and their applications in forecasting, anomaly detection, and classification.
Are Transformers Effective for Time Series Forecasting?
Proceedings of the AAAI Conference on Artificial Intelligence · 2023 · SJR 1.00 · 2,709 citations · Open access
Simple one-layer linear models (LTSF-Linear) surprisingly outperform complex Transformer-based models on long-term time series forecasting tasks across nine real-world datasets.
A Survey on Metaverse: Fundamentals, Security, and Privacy
IEEE Communications Surveys & Tutorials · 2022 · Q1 · SJR 14.00 · FWCI 133.02 · 1,230 citations
This survey identifies fundamental challenges and security/privacy threats in the emerging metaverse, proposing a novel distributed architecture with ternary-world interactions to address issues like scalability and interoperability.
AST: Audio Spectrogram Transformer
2021 · 1,006 citations
The Audio Spectrogram Transformer (AST) is the first purely attention-based model for audio classification, achieving new state-of-the-art results: 0.485 mAP on AudioSet, 95.6% accuracy on ESC-50, and 98.1% accuracy on Speech Commands V2.
Overview of the Versatile Video Coding (VVC) Standard and its Applications
IEEE Transactions on Circuits and Systems for Video Technology · 2021 · Q1 · SJR 2.00 · FWCI 147.63 · 1,650 citations · Open access
The Versatile Video Coding (VVC) standard, finalized in July 2020, achieves ~50% bit rate reduction over HEVC and ~75% over AVC for equal quality, supporting diverse applications like HDR, 360° video, and screen content.
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Proceedings of the AAAI Conference on Artificial Intelligence · 2021 · SJR 1.00 · 6,292 citations · Open access
Informer, a new transformer-based model, significantly improves long sequence time-series forecasting (LSTF) by addressing Transformer's quadratic complexity and memory issues.
Journals in this field
The journals that publish most of this field’s papers. Quartile (Q1–Q4), SJR and h-index are from SCImago Journal Rank; “in this field” is how many of the journal’s pooled papers belong here. What is a Q1 journal? · What is the h-index?
| Journal | Quartile | SJR | h-index | In this field | Summaries |
|---|---|---|---|---|---|
| IEEE/ACM Transactions on Audio Speech and Language Processing | Q1 | — | 104 | 7 | 7 |
| IEEE Transactions on Circuits and Systems for Video Technology | Q1 | 2.00 | 206 | 3 | 7 |
| ACM Computing Surveys | Q1 | 5.00 | 260 | 2 | 17 |
| IEEE Transactions on Pattern Analysis and Machine Intelligence | Q1 | 4.00 | 460 | 2 | 27 |
| IEEE Transactions on Signal Processing | Q1 | 1.00 | 328 | 2 | 9 |
| Proceedings of the AAAI Conference on Artificial Intelligence | — | 1.00 | 56 | 2 | 13 |
| IEEE Signal Processing Letters | Q1 | — | 173 | 2 | 4 |
| IEEE Communications Surveys and Tutorials | Q1 | 14.00 | 314 | 1 | 19 |
Every journal in Signal Processing (Q1–Q4) →
Add this field to your daily feed
Pick your interests and new work in your area arrives every day, summarised. Full summaries live in the app.
Open the appOther subfields in Computer Science
- Computer Networks and Communications
- Computer Science Applications
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Information Systems
- Hardware and Architecture
- Computational Theory and Mathematics
- Human-Computer Interaction
- Artificial Intelligence
- Software