{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:74OYSOPBC4OGPQQCHBOYNUEKVV","short_pith_number":"pith:74OYSOPB","canonical_record":{"source":{"id":"1712.06317","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T10:02:23Z","cross_cats_sorted":[],"title_canon_sha256":"01c64595198d2ea047d7771d36f6ed46c64dd44556d20177e34d1780de298420","abstract_canon_sha256":"35da966465aa2e4179aca7aa3469817118fc0db72030d368cee99e2ff5872644"},"schema_version":"1.0"},"canonical_sha256":"ff1d8939e1171c67c202385d86d08aad6a72b7b22957c8e911e952f77a8c1e66","source":{"kind":"arxiv","id":"1712.06317","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06317","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06317v3","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06317","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"74OYSOPBC4OG","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"74OYSOPBC4OGPQQC","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"74OYSOPB","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:74OYSOPBC4OGPQQCHBOYNUEKVV","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06317","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T10:02:23Z","cross_cats_sorted":[],"title_canon_sha256":"01c64595198d2ea047d7771d36f6ed46c64dd44556d20177e34d1780de298420","abstract_canon_sha256":"35da966465aa2e4179aca7aa3469817118fc0db72030d368cee99e2ff5872644"},"schema_version":"1.0"},"canonical_sha256":"ff1d8939e1171c67c202385d86d08aad6a72b7b22957c8e911e952f77a8c1e66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:41.886857Z","signature_b64":"6qNYkY0Y7dtXo/CSsfgRJekEHY7WzjG1+B3eh1jtAzpIioxrUbckHnu3PBj6Hd0zFw8TO0l4INTmdtJwNEb9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1d8939e1171c67c202385d86d08aad6a72b7b22957c8e911e952f77a8c1e66","last_reissued_at":"2026-05-18T00:09:41.886115Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:41.886115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06317","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qjER00Eb6k009tYLWuq3u/GnFQG5fFPr9UlVHnOgQW2keQmk8/wJbsZp6te46AiKsDUQiajBn1yxicp5IvkMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T08:08:46.256697Z"},"content_sha256":"df773381cdb970e9d9889ce7b85bae659f78225ab7040988a094f98eebabfbbe","schema_version":"1.0","event_id":"sha256:df773381cdb970e9d9889ce7b85bae659f78225ab7040988a094f98eebabfbbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:74OYSOPBC4OGPQQCHBOYNUEKVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Object Detection with an Aligned Spatial-Temporal Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanyi Xiao, Yong Jae Lee","submitted_at":"2017-12-18T10:02:23Z","abstract_excerpt":"We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The STMM's design enables full integration of pretrained backbone CNN weights, which we find to be critical for accurate detection. Furthermore, in order to tackle object motion in videos, we propose a novel MatchTrans module to align the spatial-temporal memory from frame to frame. Our method produces state-of-the-art results on the benchmark ImageNet VID dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06317","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2vcbWTy1DJwTEFDdevkiAR+UTZtCnXQ5ZqmRvwrfeX1GqFF5P2ur/JAR58rFbv5mWRvDeFf0nrW1hKMyjG/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-24T08:08:46.257150Z"},"content_sha256":"bd1502715d167738b7ed4f1cb7f99380d9246f33432aaef5df8aeff33b30d5ec","schema_version":"1.0","event_id":"sha256:bd1502715d167738b7ed4f1cb7f99380d9246f33432aaef5df8aeff33b30d5ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74OYSOPBC4OGPQQCHBOYNUEKVV/bundle.json","state_url":"https://pith.science/pith/74OYSOPBC4OGPQQCHBOYNUEKVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74OYSOPBC4OGPQQCHBOYNUEKVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-24T08:08:46Z","links":{"resolver":"https://pith.science/pith/74OYSOPBC4OGPQQCHBOYNUEKVV","bundle":"https://pith.science/pith/74OYSOPBC4OGPQQCHBOYNUEKVV/bundle.json","state":"https://pith.science/pith/74OYSOPBC4OGPQQCHBOYNUEKVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74OYSOPBC4OGPQQCHBOYNUEKVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:74OYSOPBC4OGPQQCHBOYNUEKVV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"35da966465aa2e4179aca7aa3469817118fc0db72030d368cee99e2ff5872644","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T10:02:23Z","title_canon_sha256":"01c64595198d2ea047d7771d36f6ed46c64dd44556d20177e34d1780de298420"},"schema_version":"1.0","source":{"id":"1712.06317","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06317","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06317v3","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06317","created_at":"2026-05-18T00:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"74OYSOPBC4OG","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"74OYSOPBC4OGPQQC","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"74OYSOPB","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:bd1502715d167738b7ed4f1cb7f99380d9246f33432aaef5df8aeff33b30d5ec","target":"graph","created_at":"2026-05-18T00:09:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The STMM's design enables full integration of pretrained backbone CNN weights, which we find to be critical for accurate detection. Furthermore, in order to tackle object motion in videos, we propose a novel MatchTrans module to align the spatial-temporal memory from frame to frame. Our method produces state-of-the-art results on the benchmark ImageNet VID dataset","authors_text":"Fanyi Xiao, Yong Jae Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T10:02:23Z","title":"Video Object Detection with an Aligned Spatial-Temporal Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06317","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:df773381cdb970e9d9889ce7b85bae659f78225ab7040988a094f98eebabfbbe","target":"record","created_at":"2026-05-18T00:09:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"35da966465aa2e4179aca7aa3469817118fc0db72030d368cee99e2ff5872644","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-18T10:02:23Z","title_canon_sha256":"01c64595198d2ea047d7771d36f6ed46c64dd44556d20177e34d1780de298420"},"schema_version":"1.0","source":{"id":"1712.06317","kind":"arxiv","version":3}},"canonical_sha256":"ff1d8939e1171c67c202385d86d08aad6a72b7b22957c8e911e952f77a8c1e66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff1d8939e1171c67c202385d86d08aad6a72b7b22957c8e911e952f77a8c1e66","first_computed_at":"2026-05-18T00:09:41.886115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:41.886115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6qNYkY0Y7dtXo/CSsfgRJekEHY7WzjG1+B3eh1jtAzpIioxrUbckHnu3PBj6Hd0zFw8TO0l4INTmdtJwNEb9BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:41.886857Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06317","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df773381cdb970e9d9889ce7b85bae659f78225ab7040988a094f98eebabfbbe","sha256:bd1502715d167738b7ed4f1cb7f99380d9246f33432aaef5df8aeff33b30d5ec"],"state_sha256":"95c444d33d97cae23c9f88bb9caeaf5cd86330423ce38f3f0623bc66f4657ca4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rE8PhUQDNNjK3zCSbqSQI+8pgShosmcvHJPOpfJXK3Zcf/Ov7c8y6LXxbswslqBTsT6S9qhCK7Mswzf+TjJMDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-24T08:08:46.259645Z","bundle_sha256":"00a5d6b8306a148495950d41e3022f94f84c98dcfe4e07280d8a1411753c48e9"}}