{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y7CFLSMPZODNFEAFDNBJ2VB5TV","short_pith_number":"pith:Y7CFLSMP","schema_version":"1.0","canonical_sha256":"c7c455c98fcb86d290051b429d543d9d5f1ff9f4babcaab2201c6ff6c276532e","source":{"kind":"arxiv","id":"1810.04511","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Spatio-temporal Attention for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Chang, Bo Zhao, Frederich Tung, Gao Huang, Leonid Sigal, Lili Meng, Wei Sun","submitted_at":"2018-10-01T04:23:35Z","abstract_excerpt":"Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus on the most salient parts of the feature maps. For temporal attention, we employ a convolutional LSTM based attention mechanism to identify the most relevant frames from an input video. Further, we propose a set of regularizers to ensure that our attention mechanism attends to c"},"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":"1810.04511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T04:23:35Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bbfb3d998d1de19adf80986b727572236de89773780afc4a9540351206ac079b","abstract_canon_sha256":"47e62180956a3090446ee7e84a42d95871894647919a3aa6e84c749027c63b94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:30.157431Z","signature_b64":"gVfuul0RA/VEX8o5fj/pBrKs20EVmHCO3RCnh94iUBlQWwd+MF+APf0ezKLQlu/ULkauH4Xcp19l2JanMBeYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c455c98fcb86d290051b429d543d9d5f1ff9f4babcaab2201c6ff6c276532e","last_reissued_at":"2026-05-17T23:44:30.156678Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:30.156678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Spatio-temporal Attention for Video Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bo Chang, Bo Zhao, Frederich Tung, Gao Huang, Leonid Sigal, Lili Meng, Wei Sun","submitted_at":"2018-10-01T04:23:35Z","abstract_excerpt":"Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus on the most salient parts of the feature maps. For temporal attention, we employ a convolutional LSTM based attention mechanism to identify the most relevant frames from an input video. Further, we propose a set of regularizers to ensure that our attention mechanism attends to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04511","kind":"arxiv","version":2},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1810.04511","created_at":"2026-05-17T23:44:30.156786+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.04511v2","created_at":"2026-05-17T23:44:30.156786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04511","created_at":"2026-05-17T23:44:30.156786+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7CFLSMPZODN","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7CFLSMPZODNFEAF","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7CFLSMP","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV","json":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV.json","graph_json":"https://pith.science/api/pith-number/Y7CFLSMPZODNFEAFDNBJ2VB5TV/graph.json","events_json":"https://pith.science/api/pith-number/Y7CFLSMPZODNFEAFDNBJ2VB5TV/events.json","paper":"https://pith.science/paper/Y7CFLSMP"},"agent_actions":{"view_html":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV","download_json":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV.json","view_paper":"https://pith.science/paper/Y7CFLSMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.04511&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7CFLSMPZODNFEAFDNBJ2VB5TV/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7CFLSMPZODNFEAFDNBJ2VB5TV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/action/storage_attestation","attest_author":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/action/author_attestation","sign_citation":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/action/citation_signature","submit_replication":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/action/replication_record"}},"created_at":"2026-05-17T23:44:30.156786+00:00","updated_at":"2026-05-17T23:44:30.156786+00:00"}