Sequential Image Classification

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 38 papers with code (44 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
  4 Mar 2018 35 repositories listed Syntology ran 2 of 10 samples · 8 unverified · 1 pointer-only (licence)
  Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory.
• Resurrecting Recurrent Neural Networks for Long Sequences
  11 Mar 2023 11 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train.
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
  13 Mar 2018 11 repositories listed Syntology ran 1 of 5 samples · 4 unverified · 1 pointer-only (licence)
  Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained…
• Efficiently Modeling Long Sequences with Structured State Spaces
  31 Oct 2021 8 repositories listed Syntology ran 28 of 55 samples · 27 unverified · 3 pointer-only (licence)
  A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies.
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
  3 Apr 2015 6 repositories listed
  Learning long term dependencies in recurrent networks is difficult due to vanishing and exploding gradients.
• Recurrent Highway Networks with Grouped Auxiliary Memory
  13 Dec 2019 4 repositories listed
  In this paper, we address these issues by proposing a novel RNN architecture based on RHN, namely the Recurrent Highway Network with Grouped Auxiliary Memory (GAM-RHN).
• Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
  25 Nov 2019 3 repositories listed
  We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
• Recurrent Batch Normalization
  30 Mar 2016 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks.
• Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
  26 Oct 2021 2 repositories listed Syntology ran 19 of 53 samples · 34 unverified
  Recurrent neural networks (RNNs), temporal convolutions, and neural differential equations (NDEs) are popular families of deep learning models for time-series data, each with unique strengths and tradeoffs in modeling…
• Parallelizing Legendre Memory Unit Training
  22 Feb 2021 2 repositories listed
  For instance, our LMU sets a new state-of-the-art result on psMNIST, and uses half the parameters while outperforming DistilBERT and LSTM models on IMDB sentiment analysis.
• HiPPO: Recurrent Memory with Optimal Polynomial Projections
  17 Aug 2020 2 repositories listed Syntology ran 6 of 12 samples · 6 unverified · 2 pointer-only (licence)
  A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed.
• Learning Long-Term Dependencies in Irregularly-Sampled Time Series
  8 Jun 2020 2 repositories listed
  These models, however, face difficulties when the input data possess long-term dependencies.
• Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
  1 Dec 2019 2 repositories listed
  Backpropagation through the ODE solver allows each layer to adapt its internal time-step, enabling the network to learn task-relevant time-scales.
• R-Transformer: Recurrent Neural Network Enhanced Transformer
  12 Jul 2019 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Recurrent Neural Networks have long been the dominating choice for sequence modeling.
• Long short-term memory and learning-to-learn in networks of spiking neurons
  26 Mar 2018 2 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 5 pointer-only (licence)
  Recurrent networks of spiking neurons (RSNNs) underlie the astounding computing and learning capabilities of the brain.
• Dilated Recurrent Neural Networks
  5 Oct 2017 2 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing…
• Full-Capacity Unitary Recurrent Neural Networks
  31 Oct 2016 2 repositories listed
  To address this question, we propose full-capacity uRNNs that optimize their recurrence matrix over all unitary matrices, leading to significantly improved performance over uRNNs that use a restricted-capacity…
• Unitary Evolution Recurrent Neural Networks
  20 Nov 2015 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and exploding gradients, especially when trying to…
• Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate
  23 Oct 2023 1 repository listed
  Recurrent Neural Networks (RNNs) are widely recognized for their proficiency in modeling temporal dependencies, making them highly prevalent in sequential data processing applications.
• Traveling Waves Encode the Recent Past and Enhance Sequence Learning
  3 Sep 2023 1 repository listed
  Traveling waves of neural activity have been observed throughout the brain at a diversity of regions and scales; however, their precise computational role is still debated.
• Sequence Modeling with Multiresolution Convolutional Memory
  2 May 2023 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  Popular approaches in the space tradeoff between the memory burden of brute-force enumeration and comparison, as in transformers, the computational burden of complicated sequential dependencies, as in recurrent neural…
• SMPConv: Self-moving Point Representations for Continuous Convolution
  5 Apr 2023 1 repository listed Syntology ran 2 of 9 samples · 7 unverified
  This paper suggests an alternative approach to building a continuous convolution without neural networks, resulting in more computationally efficient and improved performance.
• Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
  13 Jun 2022 1 repository listed
  However, there is still a need to bridge the gap between what RNNs are capable of in terms of efficiency and performance and real-world application requirements.
• FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
  15 Oct 2021 1 repository listed
  In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost.
• Long Expressive Memory for Sequence Modeling
  10 Oct 2021 1 repository listed Syntology ran 1 of 10 samples · 9 unverified · 1 pointer-only (licence)
  We propose a novel method called Long Expressive Memory (LEM) for learning long-term sequential dependencies.
• RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks
  16 Jun 2021 1 repository listed
  Recurrent neural networks (RNNs) are widely used throughout neuroscience as models of local neural activity.
• UnICORNN: A recurrent model for learning very long time dependencies
  9 Mar 2021 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  The design of recurrent neural networks (RNNs) to accurately process sequential inputs with long-time dependencies is very challenging on account of the exploding and vanishing gradient problem.
• Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition
  2 Mar 2021 1 repository listed
  Sequential matching using hand-crafted heuristics has been standard practice in route-based place recognition for enhancing pairwise similarity results for nearly a decade.
• CKConv: Continuous Kernel Convolution For Sequential Data
  4 Feb 2021 1 repository listed
  Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori.
• DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition
  17 Nov 2020 1 repository listed
  Sequence-based place recognition methods for all-weather navigation are well-known for producing state-of-the-art results under challenging day-night or summer-winter transitions.

Syntology lines on 15 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.