{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XTUJO4EJHDAZN4J74Y74RL2DSC","short_pith_number":"pith:XTUJO4EJ","canonical_record":{"source":{"id":"1808.07272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-22T08:29:38Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"efbeb56ccc68b0b043a04e1e2df4d6d0cf8e22c688a61cf00647136a97afdeb0","abstract_canon_sha256":"c766e7179abf0d065377d5fbc8d4a4d0634df313caf5d36c2ff870f440a93047"},"schema_version":"1.0"},"canonical_sha256":"bce897708938c196f13fe63fc8af4390b15b373c50f2da9bf112562f6975fd92","source":{"kind":"arxiv","id":"1808.07272","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07272","created_at":"2026-05-18T00:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07272v1","created_at":"2026-05-18T00:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07272","created_at":"2026-05-18T00:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"XTUJO4EJHDAZ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XTUJO4EJHDAZN4J7","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XTUJO4EJ","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XTUJO4EJHDAZN4J74Y74RL2DSC","target":"record","payload":{"canonical_record":{"source":{"id":"1808.07272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-22T08:29:38Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"efbeb56ccc68b0b043a04e1e2df4d6d0cf8e22c688a61cf00647136a97afdeb0","abstract_canon_sha256":"c766e7179abf0d065377d5fbc8d4a4d0634df313caf5d36c2ff870f440a93047"},"schema_version":"1.0"},"canonical_sha256":"bce897708938c196f13fe63fc8af4390b15b373c50f2da9bf112562f6975fd92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:29.367944Z","signature_b64":"9GBjqQGDlN/rAAtbfMDp3RxnE5idLIYLy9ZwAr/77g5syEAo6UH902FB+Z8e1lOCmI3pRt2DiJEbhNxz/VhxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce897708938c196f13fe63fc8af4390b15b373c50f2da9bf112562f6975fd92","last_reissued_at":"2026-05-18T00:07:29.367179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:29.367179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.07272","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":"2026-05-18T00:07:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xWDfwZcd/x6EQcLrDjPhJnQA94/9G5LiLzJ/8Dc0MMvtJjhGnGq3dqUrjB+Fg7XacQCvuEAfQSpduh+ZkZdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:06:37.954372Z"},"content_sha256":"83ade495fb103dee7f117322aebb7fe48c35dd3ffd1ea1bdcc519922a6f2db21","schema_version":"1.0","event_id":"sha256:83ade495fb103dee7f117322aebb7fe48c35dd3ffd1ea1bdcc519922a6f2db21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XTUJO4EJHDAZN4J74Y74RL2DSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Adaptive Temporal Pooling for Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bappaditya Mandal, Ngai-Man Cheung, Sibo Song, Vijay Chandrasekhar","submitted_at":"2018-08-22T08:29:38Z","abstract_excerpt":"Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of different temporal segments in a video. To address this problem, we propose a learnable and differentiable module: Deep Adaptive Temporal Pooling (DATP). DATP applies a self-attention mechanism to adaptively pool the classification scores of different video segments. Specifically, using frame-level features, DATP regresses importance of different temporal segments a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07272","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":"2026-05-18T00:07:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfkoxWOQtWz03v7shP/uN9Y53S22sm/FrbveTFTfhgm5MiJ428b5q6iOAq5EBS/Icy+SNycDK5e1KBJeq5qSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:06:37.954735Z"},"content_sha256":"b3444f05a5c53515b79d472527c8407ba7112a0fda5e79f2a6111f74be958f65","schema_version":"1.0","event_id":"sha256:b3444f05a5c53515b79d472527c8407ba7112a0fda5e79f2a6111f74be958f65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTUJO4EJHDAZN4J74Y74RL2DSC/bundle.json","state_url":"https://pith.science/pith/XTUJO4EJHDAZN4J74Y74RL2DSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTUJO4EJHDAZN4J74Y74RL2DSC/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":"2026-06-02T21:06:37Z","links":{"resolver":"https://pith.science/pith/XTUJO4EJHDAZN4J74Y74RL2DSC","bundle":"https://pith.science/pith/XTUJO4EJHDAZN4J74Y74RL2DSC/bundle.json","state":"https://pith.science/pith/XTUJO4EJHDAZN4J74Y74RL2DSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTUJO4EJHDAZN4J74Y74RL2DSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XTUJO4EJHDAZN4J74Y74RL2DSC","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":"c766e7179abf0d065377d5fbc8d4a4d0634df313caf5d36c2ff870f440a93047","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-22T08:29:38Z","title_canon_sha256":"efbeb56ccc68b0b043a04e1e2df4d6d0cf8e22c688a61cf00647136a97afdeb0"},"schema_version":"1.0","source":{"id":"1808.07272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07272","created_at":"2026-05-18T00:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07272v1","created_at":"2026-05-18T00:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07272","created_at":"2026-05-18T00:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"XTUJO4EJHDAZ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XTUJO4EJHDAZN4J7","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XTUJO4EJ","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:b3444f05a5c53515b79d472527c8407ba7112a0fda5e79f2a6111f74be958f65","target":"graph","created_at":"2026-05-18T00:07:29Z","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 neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of different temporal segments in a video. To address this problem, we propose a learnable and differentiable module: Deep Adaptive Temporal Pooling (DATP). DATP applies a self-attention mechanism to adaptively pool the classification scores of different video segments. Specifically, using frame-level features, DATP regresses importance of different temporal segments a","authors_text":"Bappaditya Mandal, Ngai-Man Cheung, Sibo Song, Vijay Chandrasekhar","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-22T08:29:38Z","title":"Deep Adaptive Temporal Pooling for Activity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07272","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":"sha256:83ade495fb103dee7f117322aebb7fe48c35dd3ffd1ea1bdcc519922a6f2db21","target":"record","created_at":"2026-05-18T00:07:29Z","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":"c766e7179abf0d065377d5fbc8d4a4d0634df313caf5d36c2ff870f440a93047","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-22T08:29:38Z","title_canon_sha256":"efbeb56ccc68b0b043a04e1e2df4d6d0cf8e22c688a61cf00647136a97afdeb0"},"schema_version":"1.0","source":{"id":"1808.07272","kind":"arxiv","version":1}},"canonical_sha256":"bce897708938c196f13fe63fc8af4390b15b373c50f2da9bf112562f6975fd92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bce897708938c196f13fe63fc8af4390b15b373c50f2da9bf112562f6975fd92","first_computed_at":"2026-05-18T00:07:29.367179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:29.367179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9GBjqQGDlN/rAAtbfMDp3RxnE5idLIYLy9ZwAr/77g5syEAo6UH902FB+Z8e1lOCmI3pRt2DiJEbhNxz/VhxAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:29.367944Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83ade495fb103dee7f117322aebb7fe48c35dd3ffd1ea1bdcc519922a6f2db21","sha256:b3444f05a5c53515b79d472527c8407ba7112a0fda5e79f2a6111f74be958f65"],"state_sha256":"bcd64dc5ef926acb67688973c536907bf607e371fe82d790b3094cc7eaf5651a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rj8ypCcYfiQnEADnnDWrZvh5iTFRZkMzdz3Bj7zF5arjLZDhQhMeNbmzFvPz2EquBhdrxBVYD66imehoQUMeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:06:37.956728Z","bundle_sha256":"e53c89131dffbff54dd8884f819551c39f1215197e53aca58094d13289d292d2"}}