mlsanityData to 7 Oct 2026

Effects of padding on LSTMs and CNNs

arXiv 1903.07288 ↗First posted 18 Mar 2019cs.LG cs.CL cs.IRcited by 22

Not on the map. Why?

Abstract (arXiv)

Long Short-Term Memory (LSTM) Networks and Convolutional Neural Networks (CNN) have become very common and are used in many fields as they were effective in solving many problems where the general neural networks were inefficient. They were applied to various problems mostly related to images and sequences. Since LSTMs and CNNs take inputs of the same length and dimension, input images and sequences are padded to maximum length while testing and training. This padding can affect the way the networks function and can make a great deal when it comes to performance and accuracies. This paper studies this and suggests the best way to pad an input sequence. This paper uses a simple sentiment analysis task for this purpose. We use the same dataset on both the networks with various padding to show the difference. This paper also discusses some preprocessing techniques done on the data to ensure effective analysis of the data.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 3; 2024: 2; 2025: 6; 2026: 2.

22 papers.

Sort:

  1. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  2. 2024Clustering in pure-attention hardmax transformers and its role in sentiment analysiscited by 15
  3. 2022Deep-Learning-based Vulnerability Detection in Binary Executablescited by 6
  4. 2023Table Tennis Stroke Detection and Recognition Using Ball Trajectory Datacited by 5
  5. 2022Similarity Learning based Few Shot Learning for ECG Time Series Classificationcited by 3
  6. 2025Transformer-Based Power Optimization for Max-Min Fairness in Cell-Free Massive MIMOcited by 3
  7. 2022Influential Recommender Systemcited by 2
  8. 2021LSTM Hyper-Parameter Selection for Malware Detection: Interaction Effects and Hierarchical Selection Approachcited by 1
  9. 2022Short Paper: Static and Microarchitectural ML-Based Approaches For Detecting Spectre Vulnerabilities and Attackscited by 1
  10. 2022Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languagescited by 1
  11. 2023Q-fid: Quantum Circuit Fidelity Improvement with LSTM Networkscited by 1
  12. 2025Likelihood-Free Estimation for Spatiotemporal Hawkes processes with missing data and application to predictive policingcited by 1
10 more
  1. 2025Tiny Neural Networks for Multi-Object Tracking in a Modular Kalman Frameworkcited by 1
  2. 2025Linear Attention for Joint Power Optimization and User-Centric Clustering in Cell-Free Networkscited by 1
  3. 2021Artificial intelligence prediction of stock prices using social mediacited by 0
  4. 2021User-click Modelling for Predicting Purchase Intentcited by 0
  5. 2022On Mini-Batch Training with Varying Length Time Seriescited by 0
  6. 2023A new transformation for embedded convolutional neural network approach toward real-time servo motor overload fault-detectioncited by 0
  7. 2025On the Shape of Latent Variables in a Denoising VAE-MoG: A Posterior Sampling-Based Studycited by 0
  8. 2025A Systematic Reproducibility Study of BSARec for Sequential Recommendationcited by 0
  9. 2026Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Criticscited by 0
  10. 2026Linear Models, Variable Selection, Artificial Intelligencecited by 0