{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4OFYZPYX5ARLAFUZGQTZB6C4UT","short_pith_number":"pith:4OFYZPYX","canonical_record":{"source":{"id":"1908.04121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:39:28Z","cross_cats_sorted":[],"title_canon_sha256":"98ceafafd08f036cb382f72e9dd89bf0251bc4637926f908f361a755d561b1c2","abstract_canon_sha256":"52093032b01fb1864d6abc11a88c8ffe13a078136bf3f184a3283d94963494a0"},"schema_version":"1.0"},"canonical_sha256":"e38b8cbf17e822b01699342790f85ca4cb11db9c38a6c20fb4090e6e7b3fdaa9","source":{"kind":"arxiv","id":"1908.04121","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04121","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04121v1","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04121","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"pith_short_12","alias_value":"4OFYZPYX5ARL","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"pith_short_16","alias_value":"4OFYZPYX5ARLAFUZ","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"pith_short_8","alias_value":"4OFYZPYX","created_at":"2026-07-04T23:53:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4OFYZPYX5ARLAFUZGQTZB6C4UT","target":"record","payload":{"canonical_record":{"source":{"id":"1908.04121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:39:28Z","cross_cats_sorted":[],"title_canon_sha256":"98ceafafd08f036cb382f72e9dd89bf0251bc4637926f908f361a755d561b1c2","abstract_canon_sha256":"52093032b01fb1864d6abc11a88c8ffe13a078136bf3f184a3283d94963494a0"},"schema_version":"1.0"},"canonical_sha256":"e38b8cbf17e822b01699342790f85ca4cb11db9c38a6c20fb4090e6e7b3fdaa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:20.934717Z","signature_b64":"Y54jTVMKZBqWdb8Fjp8GHEkQB35D0p7zdDfOh/uyW1XMScaVrs3waG+ZkNFXEOCnftihbuzg+y6vXSgYM6qUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e38b8cbf17e822b01699342790f85ca4cb11db9c38a6c20fb4090e6e7b3fdaa9","last_reissued_at":"2026-07-04T23:53:20.934289Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:20.934289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.04121","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":"2026-07-04T23:53:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8148P2FH73CTgd+hVuqYwBzx43rdacLBS1FIZA+ImBOlucZBG5ft8pJ1coilTuQuX2bsTRqmNRdSS1f6gpvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:42:58.228573Z"},"content_sha256":"dc5c3bc515100f0e02622bd542ffd3722b7d2e3a5730d70e209f7cd3fa31775b","schema_version":"1.0","event_id":"sha256:dc5c3bc515100f0e02622bd542ffd3722b7d2e3a5730d70e209f7cd3fa31775b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4OFYZPYX5ARLAFUZGQTZB6C4UT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhanced 3D convolutional networks for crowd counting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huiliang Shao, Pan Zhou, Wei Wei, Xiaoye Qu, Zhikang Zou","submitted_at":"2019-08-12T12:39:28Z","abstract_excerpt":"Recently, convolutional neural networks (CNNs) are the leading defacto method for crowd counting. However, when dealing with video datasets, CNN-based methods still process each video frame independently, thus ignoring the powerful temporal information between consecutive frames. In this work, we propose a novel architecture termed as \"temporal channel-aware\" (TCA) block, which achieves the capability of exploiting the temporal interdependencies among video sequences. Specifically, we incorporate 3D convolution kernels to encode local spatio-temporal features. Furthermore, the global contextua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04121","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.04121/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:53:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FrlpBuITKiSuXEv77a6RVk0jhQWuD3NET0wP7NBRE1hZqqvSPBaS7LlNQPSDO2rm+K8Vu2itrIi5F/Yee4RZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:42:58.229285Z"},"content_sha256":"a1d8bd624eb3b8820126681f4eb8ef9203520535e77e1233c5878137c40107b2","schema_version":"1.0","event_id":"sha256:a1d8bd624eb3b8820126681f4eb8ef9203520535e77e1233c5878137c40107b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/bundle.json","state_url":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/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":"2026-08-16T16:42:58Z","links":{"resolver":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT","bundle":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/bundle.json","state":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4OFYZPYX5ARLAFUZGQTZB6C4UT","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":"52093032b01fb1864d6abc11a88c8ffe13a078136bf3f184a3283d94963494a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:39:28Z","title_canon_sha256":"98ceafafd08f036cb382f72e9dd89bf0251bc4637926f908f361a755d561b1c2"},"schema_version":"1.0","source":{"id":"1908.04121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04121","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04121v1","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04121","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"pith_short_12","alias_value":"4OFYZPYX5ARL","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"pith_short_16","alias_value":"4OFYZPYX5ARLAFUZ","created_at":"2026-07-04T23:53:20Z"},{"alias_kind":"pith_short_8","alias_value":"4OFYZPYX","created_at":"2026-07-04T23:53:20Z"}],"graph_snapshots":[{"event_id":"sha256:a1d8bd624eb3b8820126681f4eb8ef9203520535e77e1233c5878137c40107b2","target":"graph","created_at":"2026-07-04T23:53:20Z","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/1908.04121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, convolutional neural networks (CNNs) are the leading defacto method for crowd counting. However, when dealing with video datasets, CNN-based methods still process each video frame independently, thus ignoring the powerful temporal information between consecutive frames. In this work, we propose a novel architecture termed as \"temporal channel-aware\" (TCA) block, which achieves the capability of exploiting the temporal interdependencies among video sequences. Specifically, we incorporate 3D convolution kernels to encode local spatio-temporal features. Furthermore, the global contextua","authors_text":"Huiliang Shao, Pan Zhou, Wei Wei, Xiaoye Qu, Zhikang Zou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:39:28Z","title":"Enhanced 3D convolutional networks for crowd counting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04121","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:dc5c3bc515100f0e02622bd542ffd3722b7d2e3a5730d70e209f7cd3fa31775b","target":"record","created_at":"2026-07-04T23:53:20Z","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":"52093032b01fb1864d6abc11a88c8ffe13a078136bf3f184a3283d94963494a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T12:39:28Z","title_canon_sha256":"98ceafafd08f036cb382f72e9dd89bf0251bc4637926f908f361a755d561b1c2"},"schema_version":"1.0","source":{"id":"1908.04121","kind":"arxiv","version":1}},"canonical_sha256":"e38b8cbf17e822b01699342790f85ca4cb11db9c38a6c20fb4090e6e7b3fdaa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e38b8cbf17e822b01699342790f85ca4cb11db9c38a6c20fb4090e6e7b3fdaa9","first_computed_at":"2026-07-04T23:53:20.934289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:53:20.934289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y54jTVMKZBqWdb8Fjp8GHEkQB35D0p7zdDfOh/uyW1XMScaVrs3waG+ZkNFXEOCnftihbuzg+y6vXSgYM6qUCw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:53:20.934717Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc5c3bc515100f0e02622bd542ffd3722b7d2e3a5730d70e209f7cd3fa31775b","sha256:a1d8bd624eb3b8820126681f4eb8ef9203520535e77e1233c5878137c40107b2"],"state_sha256":"52da8deb34c012f9529fb6c8c68450c1f682bf8b18b5f5e5eb6fc5f3e0e99770"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YPr9dD8t+sqs/rz7/UPSWlq6QyvtjQcC8s7zKopL1cfr8qfzH01SRPZEf7xVqEpQrgGrnc72dyG7V6Dk5yYTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T16:42:58.239748Z","bundle_sha256":"26bd4aa3750d9c532c5c7e8a225dd162b4ed05a754ce9fdea49863258abb37cd"}}