{"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/ecsnet-spatio-temporal-feature-learning-for","title":"Ecsnet: Spatio-temporal feature learning for event camera","arxiv_id":null,"date":"2022-08-29","proceeding":"IEEE Transactions on Circuits and Systems for Video Technology 2022 8","authors":["Zhiwen Chen","Jinjian Wu","Junhui Hou","Leida Li","Weisheng Dong","Guangming Shi"],"abstract":"The neuromorphic event cameras can efficiently sense the latent geometric structures and motion clues of a scene by generating asynchronous and sparse event signals. Due to the irregular layout of the event signals, how to leverage their plentiful spatio-temporal information for recognition tasks remains a significant challenge. Existing methods tend\r\nto treat events as dense image-like or point-serie representations. However, they either suffer from severe destruction on\r\nthe sparsity of event data or fail to encode robust spatial cues. To fully exploit their inherent sparsity with reconciling\r\nthe spatio-temporal information, we introduce a compact event representation, namely 2D-1T event cloud sequence (2D-1T ECS). We couple this representation with a novel light-weight spatiotemporal learning framework (ECSNet) that accommodates both object classification and action recognition tasks. The core of our framework is a hierarchical spatial relation module. Equipped with specially designed surface-event-based sampling unit and local event normalization unit to enhance the inter-event relation encoding, this module learns robust geometric features from the 2D event clouds. And we propose a motion attention module for efficiently capturing long-term temporal context evolving with the 1T cloud sequence. Empirically, the experiments show that our framework achieves par or even better state-of-the-art\r\nperformance. Importantly, our approach cooperates well with the sparsity of event data without any sophisticated operations, hence leading to low computational costs and prominent inference speeds.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9869656","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9869656","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":[{"paper_slug":"ecsnet-spatio-temporal-feature-learning-for","repo_url":"https://github.com/happychenpipi/ECSNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"event-data-classification","task_name":"Event data classification"},{"task_slug":"event-based-vision","task_name":"Event-based vision"},{"task_slug":"gesture-generation","task_name":"Gesture Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/event-data-classification-on-cifar10-dvs-1","task":"Event data classification","dataset":"CIFAR10-DVS","model":"ECSNet","rank_in_archive_order":5,"of":7,"metrics":{"Accuracy":"72.7"},"uses_additional_data":false},{"leaderboard":"/sota/event-data-classification-on-n-caltech-101","task":"Event data classification","dataset":"N-Caltech 101","model":"ECSNet","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy (% )":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/gesture-generation-on-dvs128-gesture","task":"Gesture Generation","dataset":"DVS128 Gesture","model":"ECSNet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (% )":"98.61"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}