{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TCFSNQFSLKZJE66ZMNXH77FQUA","short_pith_number":"pith:TCFSNQFS","schema_version":"1.0","canonical_sha256":"988b26c0b25ab2927bd9636e7ffcb0a03f4d2a3dcea18d36105c2d2a3d1ac587","source":{"kind":"arxiv","id":"2005.04437","version":5},"attestation_state":"computed","paper":{"title":"Understanding Dynamic Scenes using Graph Convolution Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Namboodiri, Balaraman Ravindran, K Madhava Krishna, Mahtab Sandhu, Priyesh Vijayan, Sravan Mylavarapu","submitted_at":"2020-05-09T13:05:06Z","abstract_excerpt":"We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a multi-relational graph where the graph's nodes represent the active and passive agents/objects in the scene, and the bidirectional edges that connect every pair of nodes are encodings of their Spatio-temporal relations. We show that this proposed explicit encoding and usage of an intermediate spatio-temporal interaction graph to be well suited for our tasks over le"},"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":"2005.04437","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-05-09T13:05:06Z","cross_cats_sorted":[],"title_canon_sha256":"f5c85c3935607685c4c41214b376848fd66c178f0bd7d4bb7890599efde07ec9","abstract_canon_sha256":"65cec313549ece4eb8134012c7cc3926edc480396544968615118df23f9e9c60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:03.423802Z","signature_b64":"rnNzBpalXxlBW8HRU9MRc3GkJfnwG9N5g+ahmzJY9SchZzqb0ntG/dkM31N+JtG+kCpS1ZIzWJVZ1bup/lgeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"988b26c0b25ab2927bd9636e7ffcb0a03f4d2a3dcea18d36105c2d2a3d1ac587","last_reissued_at":"2026-07-05T01:27:03.423395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:03.423395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Dynamic Scenes using Graph Convolution Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anoop Namboodiri, Balaraman Ravindran, K Madhava Krishna, Mahtab Sandhu, Priyesh Vijayan, Sravan Mylavarapu","submitted_at":"2020-05-09T13:05:06Z","abstract_excerpt":"We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera. The input to MRGCN is a multi-relational graph where the graph's nodes represent the active and passive agents/objects in the scene, and the bidirectional edges that connect every pair of nodes are encodings of their Spatio-temporal relations. We show that this proposed explicit encoding and usage of an intermediate spatio-temporal interaction graph to be well suited for our tasks over le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04437","kind":"arxiv","version":5},"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/2005.04437/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":"2005.04437","created_at":"2026-07-05T01:27:03.423453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04437v5","created_at":"2026-07-05T01:27:03.423453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04437","created_at":"2026-07-05T01:27:03.423453+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCFSNQFSLKZJ","created_at":"2026-07-05T01:27:03.423453+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCFSNQFSLKZJE66Z","created_at":"2026-07-05T01:27:03.423453+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCFSNQFS","created_at":"2026-07-05T01:27:03.423453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA","json":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA.json","graph_json":"https://pith.science/api/pith-number/TCFSNQFSLKZJE66ZMNXH77FQUA/graph.json","events_json":"https://pith.science/api/pith-number/TCFSNQFSLKZJE66ZMNXH77FQUA/events.json","paper":"https://pith.science/paper/TCFSNQFS"},"agent_actions":{"view_html":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA","download_json":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA.json","view_paper":"https://pith.science/paper/TCFSNQFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04437&json=true","fetch_graph":"https://pith.science/api/pith-number/TCFSNQFSLKZJE66ZMNXH77FQUA/graph.json","fetch_events":"https://pith.science/api/pith-number/TCFSNQFSLKZJE66ZMNXH77FQUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA/action/storage_attestation","attest_author":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA/action/author_attestation","sign_citation":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA/action/citation_signature","submit_replication":"https://pith.science/pith/TCFSNQFSLKZJE66ZMNXH77FQUA/action/replication_record"}},"created_at":"2026-07-05T01:27:03.423453+00:00","updated_at":"2026-07-05T01:27:03.423453+00:00"}