{"url":"/task/sequential-image-classification","name":"Sequential Image Classification","slug":"sequential-image-classification","description_markdown":"Sequential image classification is the task of classifying a sequence of images.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [TensorFlow-101](https://github.com/sjchoi86/tensorflow-101/blob/master/notebooks/rnn_mnist_simple.ipynb) )</span>","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":44,"papers_with_code":38,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/sequential-image-classification-on-sequential","slug":"sequential-image-classification-on-sequential","dataset":"Sequential MNIST","dataset_url":"/dataset/mnist","rows_in_archive":30,"metrics":["Permuted Accuracy","Unpermuted Accuracy"],"first_row_in_archive_order":{"model":"SMPConv","paper_title":"SMPConv: Self-moving Point Representations for Continuous Convolution","paper_url":"/paper/smpconv-self-moving-point-representations-for","paper_date":"2023-04-05","arxiv_id":"2304.02330","code_links":[{"title":"sangnekim/smpconv","url":"https://github.com/sangnekim/smpconv"}],"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/sequential-image-classification-on-sequential-1","slug":"sequential-image-classification-on-sequential-1","dataset":"Sequential CIFAR-10","dataset_url":null,"rows_in_archive":13,"metrics":["Unpermuted Accuracy"],"first_row_in_archive_order":{"model":"MultiresConv","paper_title":"Sequence Modeling with Multiresolution Convolutional Memory","paper_url":"/paper/sequence-modeling-with-multiresolution","paper_date":"2023-05-02","arxiv_id":"2305.01638","code_links":[{"title":"thjashin/multires-conv","url":"https://github.com/thjashin/multires-conv"}],"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/sequential-image-classification-on-noise","slug":"sequential-image-classification-on-noise","dataset":"noise padded CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":7,"metrics":["% Test Accuracy"],"first_row_in_archive_order":{"model":"FlexTCN-6","paper_title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","paper_url":"/paper/flexconv-continuous-kernel-convolutions-with-1","paper_date":"2021-10-15","arxiv_id":"2110.08059","code_links":[{"title":"rjbruin/flexconv","url":"https://github.com/rjbruin/flexconv"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/mudestreda","name":"Mudestreda","full_name":"Mudestreda Multimodal Device State Recognition Dataset","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":38,"tagged_in_all":44,"items":[{"url":"/paper/an-empirical-evaluation-of-generic","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","date":"2018-03-04","arxiv_id":"1803.01271","repositories_listed":35,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/resurrecting-recurrent-neural-networks-for","title":"Resurrecting Recurrent Neural Networks for Long Sequences","date":"2023-03-11","arxiv_id":"2303.06349","repositories_listed":11,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/independently-recurrent-neural-network-indrnn","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","date":"2018-03-13","arxiv_id":"1803.04831","repositories_listed":11,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/efficiently-modeling-long-sequences-with-1","title":"Efficiently Modeling Long Sequences with Structured State Spaces","date":"2021-10-31","arxiv_id":"2111.00396","repositories_listed":8,"syntology":{"n":55,"n_ran":28,"n_unverified":27,"n_pointer_only":3}},{"url":"/paper/a-simple-way-to-initialize-recurrent-networks","title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","date":"2015-04-03","arxiv_id":"1504.00941","repositories_listed":6,"syntology":null},{"url":"/paper/recurrent-highway-networks-with-grouped","title":"Recurrent Highway Networks with Grouped Auxiliary Memory","date":"2019-12-13","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/gating-revisited-deep-multi-layer-rnns-that-1","title":"Gating Revisited: Deep Multi-layer RNNs That Can Be Trained","date":"2019-11-25","arxiv_id":"1911.11033","repositories_listed":3,"syntology":null},{"url":"/paper/recurrent-batch-normalization","title":"Recurrent Batch Normalization","date":"2016-03-30","arxiv_id":"1603.09025","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/combining-recurrent-convolutional-and","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","date":"2021-10-26","arxiv_id":"2110.13985","repositories_listed":2,"syntology":{"n":53,"n_ran":19,"n_unverified":34,"n_pointer_only":0}},{"url":"/paper/parallelizing-legendre-memory-unit-training","title":"Parallelizing Legendre Memory Unit Training","date":"2021-02-22","arxiv_id":"2102.11417","repositories_listed":2,"syntology":null},{"url":"/paper/hippo-recurrent-memory-with-optimal","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","date":"2020-08-17","arxiv_id":"2008.07669","repositories_listed":2,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/learning-long-term-dependencies-in","title":"Learning Long-Term Dependencies in Irregularly-Sampled Time Series","date":"2020-06-08","arxiv_id":"2006.04418","repositories_listed":2,"syntology":null},{"url":"/paper/legendre-memory-units-continuous-time","title":"Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks","date":"2019-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/r-transformer-recurrent-neural-network","title":"R-Transformer: Recurrent Neural Network Enhanced Transformer","date":"2019-07-12","arxiv_id":"1907.05572","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/long-short-term-memory-and-learning-to-learn","title":"Long short-term memory and learning-to-learn in networks of spiking neurons","date":"2018-03-26","arxiv_id":"1803.09574","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/dilated-recurrent-neural-networks","title":"Dilated Recurrent Neural Networks","date":"2017-10-05","arxiv_id":"1710.02224","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/full-capacity-unitary-recurrent-neural","title":"Full-Capacity Unitary Recurrent Neural Networks","date":"2016-10-31","arxiv_id":"1611.00035","repositories_listed":2,"syntology":null},{"url":"/paper/unitary-evolution-recurrent-neural-networks","title":"Unitary Evolution Recurrent Neural Networks","date":"2015-11-20","arxiv_id":"1511.06464","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/delayed-memory-unit-modelling-temporal","title":"Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate","date":"2023-10-23","arxiv_id":"2310.14982","repositories_listed":1,"syntology":null},{"url":"/paper/traveling-waves-encode-the-recent-past-and","title":"Traveling Waves Encode the Recent Past and Enhance Sequence Learning","date":"2023-09-03","arxiv_id":"2309.08045","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-modeling-with-multiresolution","title":"Sequence Modeling with Multiresolution Convolutional Memory","date":"2023-05-02","arxiv_id":"2305.01638","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/smpconv-self-moving-point-representations-for","title":"SMPConv: Self-moving Point Representations for Continuous Convolution","date":"2023-04-05","arxiv_id":"2304.02330","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/egru-event-based-gru-for-activity-sparse","title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","date":"2022-06-13","arxiv_id":"2206.06178","repositories_listed":1,"syntology":null},{"url":"/paper/flexconv-continuous-kernel-convolutions-with-1","title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","date":"2021-10-15","arxiv_id":"2110.08059","repositories_listed":1,"syntology":null},{"url":"/paper/long-expressive-memory-for-sequence-modeling-1","title":"Long Expressive Memory for Sequence Modeling","date":"2021-10-10","arxiv_id":"2110.04744","repositories_listed":1,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/recursive-construction-of-stable-assemblies","title":"RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks","date":"2021-06-16","arxiv_id":"2106.08928","repositories_listed":1,"syntology":null},{"url":"/paper/unicornn-a-recurrent-model-for-learning-very","title":"UnICORNN: A recurrent model for learning very long time dependencies","date":"2021-03-09","arxiv_id":"2103.05487","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/sequential-place-learning-heuristic-free-high","title":"Sequential Place Learning: Heuristic-Free High-Performance Long-Term Place Recognition","date":"2021-03-02","arxiv_id":"2103.02074","repositories_listed":1,"syntology":null},{"url":"/paper/ckconv-continuous-kernel-convolution-for","title":"CKConv: Continuous Kernel Convolution For Sequential Data","date":"2021-02-04","arxiv_id":"2102.02611","repositories_listed":1,"syntology":null},{"url":"/paper/deepseqslam-a-trainable-cnn-rnn-for-joint","title":"DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition","date":"2020-11-17","arxiv_id":"2011.08518","repositories_listed":1,"syntology":null}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}