{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VEGHGSTTH2IRG6DW7CWRSB6LH5","short_pith_number":"pith:VEGHGSTT","schema_version":"1.0","canonical_sha256":"a90c734a733e91137876f8ad1907cb3f4d3e03bfba731ae01d2e4cd485dbbd05","source":{"kind":"arxiv","id":"2405.18955","version":1},"attestation_state":"computed","paper":{"title":"RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haorui Zeng, Hongjuan Liu, Jiaqi Liu, Jinzhong Wang, Shun Dai, Tao Zhuo, Xiuwei Zhang, Xuetao Tian, Yanning Zhang","submitted_at":"2024-05-29T10:11:36Z","abstract_excerpt":"Multispectral object detection, utilizing both visible (RGB) and thermal infrared (T) modals, has garnered significant attention for its robust performance across diverse weather and lighting conditions. However, effectively exploiting the complementarity between RGB-T modals while maintaining efficiency remains a critical challenge. In this paper, a very simple Group Shuffled Multi-receptive Attention (GSMA) module is proposed to extract and combine multi-scale RGB and thermal features. Then, the extracted multi-modal features are directly integrated with a multi-level path aggregation neck, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.18955","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-29T10:11:36Z","cross_cats_sorted":[],"title_canon_sha256":"ee44857aee06c2e9db6f30d8e0f82801a3fef99665d11d0aaa800d34201e7e82","abstract_canon_sha256":"bb76682f9315daf0ed768a6081595beb9863d36c3ebf0a6c050094dde09c7da9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:45.912659Z","signature_b64":"ny2Qk7h1PpVYlSwsgPtdU2m6TWSVvINITGlATOihhx6RNQGzGpTosnb5gsPrYhkwCkWArWSBxY06SY2Jy544Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a90c734a733e91137876f8ad1907cb3f4d3e03bfba731ae01d2e4cd485dbbd05","last_reissued_at":"2026-07-05T08:24:45.912166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:45.912166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haorui Zeng, Hongjuan Liu, Jiaqi Liu, Jinzhong Wang, Shun Dai, Tao Zhuo, Xiuwei Zhang, Xuetao Tian, Yanning Zhang","submitted_at":"2024-05-29T10:11:36Z","abstract_excerpt":"Multispectral object detection, utilizing both visible (RGB) and thermal infrared (T) modals, has garnered significant attention for its robust performance across diverse weather and lighting conditions. However, effectively exploiting the complementarity between RGB-T modals while maintaining efficiency remains a critical challenge. In this paper, a very simple Group Shuffled Multi-receptive Attention (GSMA) module is proposed to extract and combine multi-scale RGB and thermal features. Then, the extracted multi-modal features are directly integrated with a multi-level path aggregation neck, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18955","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.18955/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.18955","created_at":"2026-07-05T08:24:45.912223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18955v1","created_at":"2026-07-05T08:24:45.912223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18955","created_at":"2026-07-05T08:24:45.912223+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEGHGSTTH2IR","created_at":"2026-07-05T08:24:45.912223+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEGHGSTTH2IRG6DW","created_at":"2026-07-05T08:24:45.912223+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEGHGSTT","created_at":"2026-07-05T08:24:45.912223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21018","citing_title":"LASFNet: A Lightweight Attention-Guided Self-Modulation Feature Fusion Network for Multimodal Object Detection","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5","json":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5.json","graph_json":"https://pith.science/api/pith-number/VEGHGSTTH2IRG6DW7CWRSB6LH5/graph.json","events_json":"https://pith.science/api/pith-number/VEGHGSTTH2IRG6DW7CWRSB6LH5/events.json","paper":"https://pith.science/paper/VEGHGSTT"},"agent_actions":{"view_html":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5","download_json":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5.json","view_paper":"https://pith.science/paper/VEGHGSTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18955&json=true","fetch_graph":"https://pith.science/api/pith-number/VEGHGSTTH2IRG6DW7CWRSB6LH5/graph.json","fetch_events":"https://pith.science/api/pith-number/VEGHGSTTH2IRG6DW7CWRSB6LH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5/action/storage_attestation","attest_author":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5/action/author_attestation","sign_citation":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5/action/citation_signature","submit_replication":"https://pith.science/pith/VEGHGSTTH2IRG6DW7CWRSB6LH5/action/replication_record"}},"created_at":"2026-07-05T08:24:45.912223+00:00","updated_at":"2026-07-05T08:24:45.912223+00:00"}