{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4OFYZPYX5ARLAFUZGQTZB6C4UT","short_pith_number":"pith:4OFYZPYX","schema_version":"1.0","canonical_sha256":"e38b8cbf17e822b01699342790f85ca4cb11db9c38a6c20fb4090e6e7b3fdaa9","source":{"kind":"arxiv","id":"1908.04121","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1908.04121","created_at":"2026-07-04T23:53:20.934357+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04121v1","created_at":"2026-07-04T23:53:20.934357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04121","created_at":"2026-07-04T23:53:20.934357+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OFYZPYX5ARL","created_at":"2026-07-04T23:53:20.934357+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OFYZPYX5ARLAFUZ","created_at":"2026-07-04T23:53:20.934357+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OFYZPYX","created_at":"2026-07-04T23:53:20.934357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13056","citing_title":"Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT","json":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT.json","graph_json":"https://pith.science/api/pith-number/4OFYZPYX5ARLAFUZGQTZB6C4UT/graph.json","events_json":"https://pith.science/api/pith-number/4OFYZPYX5ARLAFUZGQTZB6C4UT/events.json","paper":"https://pith.science/paper/4OFYZPYX"},"agent_actions":{"view_html":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT","download_json":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT.json","view_paper":"https://pith.science/paper/4OFYZPYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04121&json=true","fetch_graph":"https://pith.science/api/pith-number/4OFYZPYX5ARLAFUZGQTZB6C4UT/graph.json","fetch_events":"https://pith.science/api/pith-number/4OFYZPYX5ARLAFUZGQTZB6C4UT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/action/storage_attestation","attest_author":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/action/author_attestation","sign_citation":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/action/citation_signature","submit_replication":"https://pith.science/pith/4OFYZPYX5ARLAFUZGQTZB6C4UT/action/replication_record"}},"created_at":"2026-07-04T23:53:20.934357+00:00","updated_at":"2026-07-04T23:53:20.934357+00:00"}