{"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/learning-bottleneck-transformer-for-event","title":"Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classification","arxiv_id":"2308.11937","date":"2023-08-23","proceeding":null,"authors":["Chengguo Yuan","Yu Jin","Zongzhen Wu","Fanting Wei","Yangzirui Wang","Lan Chen","Xiao Wang"],"abstract":"Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using various deep neural networks. Their final results may be limited by the following factors: monotonous modal expressions and the design of the network structure. To address the aforementioned challenges, this paper proposes a novel dual-stream framework for event representation, extraction, and fusion. This framework simultaneously models two common representations: event images and event voxels. By utilizing Transformer and Structured Graph Neural Network (GNN) architectures, spatial information and three-dimensional stereo information can be learned separately. Additionally, a bottleneck Transformer is introduced to facilitate the fusion of the dual-stream information. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on two widely used event-based classification datasets. The source code of this work is available at: \\url{https://github.com/Event-AHU/EFV_event_classification}","url_abs":"https://arxiv.org/abs/2308.11937v1","url_pdf":"https://arxiv.org/pdf/2308.11937v1.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":"learning-bottleneck-transformer-for-event","repo_url":"https://github.com/event-ahu/efv_event_classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"bottleneck-transformer","method_name":"Bottleneck Transformer"},{"method_slug":"bottleneck-transformer-block","method_name":"Bottleneck Transformer Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.11937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11937"}},"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/event-ahu/efv_event_classification","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"6d20d0ebd12d4c8f","entry":"calculate_edges","repo":"event-ahu/efv_event_classification","repo_kind":"official","path":"generate_graph/voxel2graph.py","file_url":"https://github.com/event-ahu/efv_event_classification/blob/HEAD/generate_graph/voxel2graph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d20d0ebd12d4c8f"}},{"code_sha256_prefix":"2a80220dabcb742a","entry":"conv1x1","repo":"event-ahu/efv_event_classification","repo_kind":"official","path":"model/torchvision_resnet.py","file_url":"https://github.com/event-ahu/efv_event_classification/blob/HEAD/model/torchvision_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"event-ahu/efv_event_classification","repo_kind":"official","path":"model/torchvision_resnet.py","file_url":"https://github.com/event-ahu/efv_event_classification/blob/HEAD/model/torchvision_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"600ff2c45e0de056"}},{"code_sha256_prefix":"134bbc852e3845bb","entry":"files_exist","repo":"event-ahu/efv_event_classification","repo_kind":"official","path":"datasets/img_voxel_dataset.py","file_url":"https://github.com/event-ahu/efv_event_classification/blob/HEAD/datasets/img_voxel_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"134bbc852e3845bb"}},{"code_sha256_prefix":"386009ae53c1e784","entry":"generate_graph","repo":"event-ahu/efv_event_classification","repo_kind":"official","path":"generate_graph/voxel2graph.py","file_url":"https://github.com/event-ahu/efv_event_classification/blob/HEAD/generate_graph/voxel2graph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"386009ae53c1e784"}},{"code_sha256_prefix":"50ec921058214df9","entry":"resnet18","repo":"event-ahu/efv_event_classification","repo_kind":"official","path":"model/torchvision_resnet.py","file_url":"https://github.com/event-ahu/efv_event_classification/blob/HEAD/model/torchvision_resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50ec921058214df9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}