{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/temporal-wise-attention-spiking-neural","title":"Temporal-wise Attention Spiking Neural Networks for Event Streams Classification","arxiv_id":"2107.11711","date":"2021-07-25","proceeding":"ICCV 2021 10","authors":["Man Yao","Huanhuan Gao","Guangshe Zhao","Dingheng Wang","Yihan Lin","ZhaoXu Yang","Guoqi Li"],"abstract":"How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications. Spiking neural network (SNN), as one of the brain-inspired event-triggered computing models, has the potential to extract effective spatio-temporal features from the event streams. However, when aggregating individual events into frames with a new higher temporal resolution, existing SNN models do not attach importance to that the serial frames have different signal-to-noise ratios since event streams are sparse and non-uniform. This situation interferes with the performance of existing SNNs. In this work, we propose a temporal-wise attention SNN (TA-SNN) model to learn frame-based representation for processing event streams. Concretely, we extend the attention concept to temporal-wise input to judge the significance of frames for the final decision at the training stage, and discard the irrelevant frames at the inference stage. We demonstrate that TA-SNN models improve the accuracy of event streams classification tasks. We also study the impact of multiple-scale temporal resolutions for frame-based representation. Our approach is tested on three different classification tasks: gesture recognition, image classification, and spoken digit recognition. We report the state-of-the-art results on these tasks, and get the essential improvement of accuracy (almost 19\\%) for gesture recognition with only 60 ms.","url_abs":"https://arxiv.org/abs/2107.11711v1","url_pdf":"https://arxiv.org/pdf/2107.11711v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-shd","task":"Audio Classification","dataset":"SHD","model":"SNN with temporal-wise attention","rank_in_archive_order":6,"of":11,"metrics":{"Percentage correct":"91.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.11711","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}