{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LQPDTGPEK5HDFRKC7KCLU6OTPF","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":"9f7ed73f8c18cdd00b6cc80393584c524ed683807554da0f02ba3273c23391de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-03T22:57:22Z","title_canon_sha256":"a7727da33e929b1de02a461db7d1ffb2bc1bf598d36bc7facfc323b34f36f9ed"},"schema_version":"1.0","source":{"id":"2008.01232","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.01232","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"arxiv_version","alias_value":"2008.01232v3","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01232","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"pith_short_12","alias_value":"LQPDTGPEK5HD","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"pith_short_16","alias_value":"LQPDTGPEK5HDFRKC","created_at":"2026-07-05T01:36:18Z"},{"alias_kind":"pith_short_8","alias_value":"LQPDTGPE","created_at":"2026-07-05T01:36:18Z"}],"graph_snapshots":[{"event_id":"sha256:a11a604819431b1054a3069726e5f82f724378b2c8a9e5967ae2e195b4f90790","target":"graph","created_at":"2026-07-05T01:36:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.01232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we combine 3D convolution with late temporal modeling for action recognition. For this aim, we replace the conventional Temporal Global Average Pooling (TGAP) layer at the end of 3D convolutional architecture with the Bidirectional Encoder Representations from Transformers (BERT) layer in order to better utilize the temporal information with BERT's attention mechanism. We show that this replacement improves the performances of many popular 3D convolution architectures for action recognition, including ResNeXt, I3D, SlowFast and R(2+1)D. Moreover, we provide the-state-of-the-art r","authors_text":"A. Aydin Alatan, M. Esat Kalfaoglu, Sinan Kalkan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-03T22:57:22Z","title":"Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01232","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:fe67f654dac987299a2b268aea36c21575c04bc542843a5bc15c5833612c3d2c","target":"record","created_at":"2026-07-05T01:36:18Z","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":"9f7ed73f8c18cdd00b6cc80393584c524ed683807554da0f02ba3273c23391de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-03T22:57:22Z","title_canon_sha256":"a7727da33e929b1de02a461db7d1ffb2bc1bf598d36bc7facfc323b34f36f9ed"},"schema_version":"1.0","source":{"id":"2008.01232","kind":"arxiv","version":3}},"canonical_sha256":"5c1e3999e4574e32c542fa84ba79d379695d2ad071b984dd42813cc052447f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c1e3999e4574e32c542fa84ba79d379695d2ad071b984dd42813cc052447f51","first_computed_at":"2026-07-05T01:36:18.610340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:18.610340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IEp9l1cmn9Y4EZWzOJJD4e8BT2N/twT2bFxLL1H0ZXiMDfh+H4QXzpulrjm/BqM0G0KccMXSHhBufgUy0BkeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:18.610752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.01232","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe67f654dac987299a2b268aea36c21575c04bc542843a5bc15c5833612c3d2c","sha256:a11a604819431b1054a3069726e5f82f724378b2c8a9e5967ae2e195b4f90790"],"state_sha256":"2d1b32b5a8a869a5c4858cfad191a4a5f2efdb16f488daebd05c136548806b04"}