{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YKFDGGSXSKKF3DDV524REKSQGT","short_pith_number":"pith:YKFDGGSX","schema_version":"1.0","canonical_sha256":"c28a331a5792945d8c75eeb9122a5034fa46aa4dbf511f96f6c8deab6120c782","source":{"kind":"arxiv","id":"2006.07744","version":1},"attestation_state":"computed","paper":{"title":"Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Sanchez-Caballero, Cristina Losada-Guti\\'errez, David Fuentes-Jimenez","submitted_at":"2020-06-13T23:35:59Z","abstract_excerpt":"As in many other different fields, deep learning has become the main approach in most computer vision applications, such as scene understanding, object recognition, computer-human interaction or human action recognition (HAR). Research efforts within HAR have mainly focused on how to efficiently extract and process both spatial and temporal dependencies of video sequences. In this paper, we propose and compare, two neural networks based on the convolutional long short-term memory unit, namely ConvLSTM, with differences in the architecture and the long-term learning strategy. The former uses a "},"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":"2006.07744","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-06-13T23:35:59Z","cross_cats_sorted":[],"title_canon_sha256":"7d5cd2ad583acc0b396cfc9012a971dc3f47fa41b0b856def05bc22866e807ac","abstract_canon_sha256":"87a4308362c7c0a7a0c559c5016a02d2bcfff3631c580e8496f0ed9f5a7f40c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:02.941308Z","signature_b64":"t6JY8G20YoZouEnvOt11mvRnPerJSOqBnA3LbldWbCaj3kX6slxbJvsa98XF131BPx4/ouTmK06zfwgScF4GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c28a331a5792945d8c75eeb9122a5034fa46aa4dbf511f96f6c8deab6120c782","last_reissued_at":"2026-07-05T01:10:02.940918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:02.940918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrian Sanchez-Caballero, Cristina Losada-Guti\\'errez, David Fuentes-Jimenez","submitted_at":"2020-06-13T23:35:59Z","abstract_excerpt":"As in many other different fields, deep learning has become the main approach in most computer vision applications, such as scene understanding, object recognition, computer-human interaction or human action recognition (HAR). Research efforts within HAR have mainly focused on how to efficiently extract and process both spatial and temporal dependencies of video sequences. In this paper, we propose and compare, two neural networks based on the convolutional long short-term memory unit, namely ConvLSTM, with differences in the architecture and the long-term learning strategy. The former uses a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07744","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/2006.07744/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":"2006.07744","created_at":"2026-07-05T01:10:02.940975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07744v1","created_at":"2026-07-05T01:10:02.940975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07744","created_at":"2026-07-05T01:10:02.940975+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKFDGGSXSKKF","created_at":"2026-07-05T01:10:02.940975+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKFDGGSXSKKF3DDV","created_at":"2026-07-05T01:10:02.940975+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKFDGGSX","created_at":"2026-07-05T01:10:02.940975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01743","citing_title":"An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT","json":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT.json","graph_json":"https://pith.science/api/pith-number/YKFDGGSXSKKF3DDV524REKSQGT/graph.json","events_json":"https://pith.science/api/pith-number/YKFDGGSXSKKF3DDV524REKSQGT/events.json","paper":"https://pith.science/paper/YKFDGGSX"},"agent_actions":{"view_html":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT","download_json":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT.json","view_paper":"https://pith.science/paper/YKFDGGSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07744&json=true","fetch_graph":"https://pith.science/api/pith-number/YKFDGGSXSKKF3DDV524REKSQGT/graph.json","fetch_events":"https://pith.science/api/pith-number/YKFDGGSXSKKF3DDV524REKSQGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT/action/storage_attestation","attest_author":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT/action/author_attestation","sign_citation":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT/action/citation_signature","submit_replication":"https://pith.science/pith/YKFDGGSXSKKF3DDV524REKSQGT/action/replication_record"}},"created_at":"2026-07-05T01:10:02.940975+00:00","updated_at":"2026-07-05T01:10:02.940975+00:00"}