{"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/recurrent-vision-transformers-for-object","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","arxiv_id":"2212.05598","date":"2022-12-11","proceeding":"CVPR 2023 1","authors":["Mathias Gehrig","Davide Scaramuzza"],"abstract":"We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at a high-dynamic range and with strong robustness against motion blur. These unique properties offer great potential for low-latency object detection and tracking in time-critical scenarios. Prior work in event-based vision has achieved outstanding detection performance but at the cost of substantial inference time, typically beyond 40 milliseconds. By revisiting the high-level design of recurrent vision backbones, we reduce inference time by a factor of 6 while retaining similar performance. To achieve this, we explore a multi-stage design that utilizes three key concepts in each stage: First, a convolutional prior that can be regarded as a conditional positional embedding. Second, local and dilated global self-attention for spatial feature interaction. Third, recurrent temporal feature aggregation to minimize latency while retaining temporal information. RVTs can be trained from scratch to reach state-of-the-art performance on event-based object detection - achieving an mAP of 47.2% on the Gen1 automotive dataset. At the same time, RVTs offer fast inference (<12 ms on a T4 GPU) and favorable parameter efficiency (5 times fewer than prior art). Our study brings new insights into effective design choices that can be fruitful for research beyond event-based vision.","url_abs":"https://arxiv.org/abs/2212.05598v3","url_pdf":"https://arxiv.org/pdf/2212.05598v3.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":[{"paper_slug":"recurrent-vision-transformers-for-object","repo_url":"https://github.com/uzh-rpg/rvt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"event-based-vision","task_name":"Event-based vision"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-gen1-detection","task":"Object Detection","dataset":"GEN1 Detection","model":"RVT-B","rank_in_archive_order":4,"of":11,"metrics":{"Params":"18.5","mAP":"47.2"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-gen1-detection","task":"Object Detection","dataset":"GEN1 Detection","model":"RVT-S","rank_in_archive_order":6,"of":11,"metrics":{"Params":"9.9","mAP":"46.5"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-gen1-detection","task":"Object Detection","dataset":"GEN1 Detection","model":"RVT-T","rank_in_archive_order":8,"of":11,"metrics":{"Params":"4.4","mAP":"44.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.05598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05598"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uzh-rpg/rvt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"787722d08c206878","entry":"get_ckpt_callback","repo":"uzh-rpg/rvt","repo_kind":"official","path":"callbacks/custom.py","file_url":"https://github.com/uzh-rpg/rvt/blob/HEAD/callbacks/custom.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"787722d08c206878"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}