{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:W3AUFMZM3QG4OEJJD2QUI2CJN7","short_pith_number":"pith:W3AUFMZM","canonical_record":{"source":{"id":"1905.13388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-31T02:48:21Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"8e8ceda24058bff04aca2a09d4d1c5175cc546fe5da3768f16c32f515aeb0c72","abstract_canon_sha256":"77496437335e127ed39e1e9650dce114ae7ee302c0cc14df8109d5aad5536eeb"},"schema_version":"1.0"},"canonical_sha256":"b6c142b32cdc0dc711291ea14468496fc1dcf4e756d90f6dd6fa5fba97444009","source":{"kind":"arxiv","id":"1905.13388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13388","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13388v1","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13388","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"W3AUFMZM3QG4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"W3AUFMZM3QG4OEJJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"W3AUFMZM","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:W3AUFMZM3QG4OEJJD2QUI2CJN7","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-31T02:48:21Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"8e8ceda24058bff04aca2a09d4d1c5175cc546fe5da3768f16c32f515aeb0c72","abstract_canon_sha256":"77496437335e127ed39e1e9650dce114ae7ee302c0cc14df8109d5aad5536eeb"},"schema_version":"1.0"},"canonical_sha256":"b6c142b32cdc0dc711291ea14468496fc1dcf4e756d90f6dd6fa5fba97444009","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.053943Z","signature_b64":"lhMQJzn4Nc5MTh5wJi4wyAq+oeFHNt2LDMpqggj/tu/q/Dtqad7MS5xg4sK7qvNqA/so3CwaH7Kz8b0dbIinAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6c142b32cdc0dc711291ea14468496fc1dcf4e756d90f6dd6fa5fba97444009","last_reissued_at":"2026-05-17T23:44:35.053429Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.053429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13388","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4SIYnY6BaPYrHQNuBsuPRTi+UqxbauNVKXcx596joWT7aZmsnVR2Mu82B1mgNE161JsRFVK1RFy0sf2KSmJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:37:51.457453Z"},"content_sha256":"97b238f8a17beedb2c1fc1bfeefe01c28635d6788dc0594c580e59a89945dd74","schema_version":"1.0","event_id":"sha256:97b238f8a17beedb2c1fc1bfeefe01c28635d6788dc0594c580e59a89945dd74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:W3AUFMZM3QG4OEJJD2QUI2CJN7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Haonan Wang, Jun Lin, Zhongfeng Wang","submitted_at":"2019-05-31T02:48:21Z","abstract_excerpt":"Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory access and computing power prohibit it from being used in resource-constrained scenarios, such as portable and edge devices. So in this paper, we first propose a two-stage Fully Separable Block (FSB) to significantly compress the model sizes of 3D ConvNets. Then a feature enhancement approach named Temporal Residual Gradient (TRG) is developed to improve the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13388","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":""},"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":"2026-05-17T23:44:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ntKG3zcpxQUp00A3h5xe2y6hjJKFrU68cHtf8DXWbBEReEa6AjjlmXmS9RSfmr5CbCX/bLINvRwIz1DKTLevAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:37:51.458103Z"},"content_sha256":"99f67d4c3279fdfaa9b49fb7333bfa278afa0d32fd0570d7c51c68b74b59c780","schema_version":"1.0","event_id":"sha256:99f67d4c3279fdfaa9b49fb7333bfa278afa0d32fd0570d7c51c68b74b59c780"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7/bundle.json","state_url":"https://pith.science/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7/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":"2026-06-05T06:37:51Z","links":{"resolver":"https://pith.science/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7","bundle":"https://pith.science/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7/bundle.json","state":"https://pith.science/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3AUFMZM3QG4OEJJD2QUI2CJN7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:W3AUFMZM3QG4OEJJD2QUI2CJN7","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":"77496437335e127ed39e1e9650dce114ae7ee302c0cc14df8109d5aad5536eeb","cross_cats_sorted":["eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-31T02:48:21Z","title_canon_sha256":"8e8ceda24058bff04aca2a09d4d1c5175cc546fe5da3768f16c32f515aeb0c72"},"schema_version":"1.0","source":{"id":"1905.13388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13388","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13388v1","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13388","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"W3AUFMZM3QG4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"W3AUFMZM3QG4OEJJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"W3AUFMZM","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:99f67d4c3279fdfaa9b49fb7333bfa278afa0d32fd0570d7c51c68b74b59c780","target":"graph","created_at":"2026-05-17T23:44:35Z","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":"Deep 3-dimensional (3D) Convolutional Network (ConvNet) has shown promising performance on video recognition tasks because of its powerful spatio-temporal information fusion ability. However, the extremely intensive requirements on memory access and computing power prohibit it from being used in resource-constrained scenarios, such as portable and edge devices. So in this paper, we first propose a two-stage Fully Separable Block (FSB) to significantly compress the model sizes of 3D ConvNets. Then a feature enhancement approach named Temporal Residual Gradient (TRG) is developed to improve the ","authors_text":"Haonan Wang, Jun Lin, Zhongfeng Wang","cross_cats":["eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-31T02:48:21Z","title":"Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13388","kind":"arxiv","version":1},"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":"sha256:97b238f8a17beedb2c1fc1bfeefe01c28635d6788dc0594c580e59a89945dd74","target":"record","created_at":"2026-05-17T23:44:35Z","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":"77496437335e127ed39e1e9650dce114ae7ee302c0cc14df8109d5aad5536eeb","cross_cats_sorted":["eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-31T02:48:21Z","title_canon_sha256":"8e8ceda24058bff04aca2a09d4d1c5175cc546fe5da3768f16c32f515aeb0c72"},"schema_version":"1.0","source":{"id":"1905.13388","kind":"arxiv","version":1}},"canonical_sha256":"b6c142b32cdc0dc711291ea14468496fc1dcf4e756d90f6dd6fa5fba97444009","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6c142b32cdc0dc711291ea14468496fc1dcf4e756d90f6dd6fa5fba97444009","first_computed_at":"2026-05-17T23:44:35.053429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:35.053429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lhMQJzn4Nc5MTh5wJi4wyAq+oeFHNt2LDMpqggj/tu/q/Dtqad7MS5xg4sK7qvNqA/so3CwaH7Kz8b0dbIinAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:35.053943Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97b238f8a17beedb2c1fc1bfeefe01c28635d6788dc0594c580e59a89945dd74","sha256:99f67d4c3279fdfaa9b49fb7333bfa278afa0d32fd0570d7c51c68b74b59c780"],"state_sha256":"a5f72e7c2d31c33ca7790c5c312ae9d83a9a4f7b537efecfb644772732e26ae8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Po9jdhR/oZm6FggYLV2jpx6tovpskUMz+2VvF6Cbl6pZsSkEUDfeBpgipdjY5YWnKzv1PKRKgxCTZfToQuT/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T06:37:51.461386Z","bundle_sha256":"bce8f7242b35721fa3b9a56d2c267e0b236b0a1c1346cc8b877e5f7f1b9b412b"}}