{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Y7CFLSMPZODNFEAFDNBJ2VB5TV","short_pith_number":"pith:Y7CFLSMP","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"},"canonical_sha256":"c7c455c98fcb86d290051b429d543d9d5f1ff9f4babcaab2201c6ff6c276532e","source":{"kind":"arxiv","id":"1810.04511","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04511","created_at":"2026-05-17T23:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04511v2","created_at":"2026-05-17T23:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04511","created_at":"2026-05-17T23:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"Y7CFLSMPZODN","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y7CFLSMPZODNFEAF","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y7CFLSMP","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Y7CFLSMPZODNFEAFDNBJ2VB5TV","target":"record","payload":{"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"},"canonical_sha256":"c7c455c98fcb86d290051b429d543d9d5f1ff9f4babcaab2201c6ff6c276532e","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"},"source_kind":"arxiv","source_id":"1810.04511","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7m61B0CrysZc5ptMR1k4u3Cg1q8wP7CCtqbajhrULua6lg9I+FwzPnk4eLDRtPUVk9O3BsRr7nfD2j3sbFmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:58:34.459490Z"},"content_sha256":"d61eb6fb30d0d7e16f9dabe854ba86e2ea59d13afe10853fab19cf01f8597f7c","schema_version":"1.0","event_id":"sha256:d61eb6fb30d0d7e16f9dabe854ba86e2ea59d13afe10853fab19cf01f8597f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Y7CFLSMPZODNFEAFDNBJ2VB5TV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmK5qlNvXa8TWbWCB7Sp2jRv4dmYOyrf/i1VdaQBZYF1+/NKh1PFIiq5Q8vH6SBC/En30wQ1QaG/6JoIQfrCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:58:34.459836Z"},"content_sha256":"1551ce6d9d0028d7f836e614c387048f432570c35ca43fdc8069f9f3dc15d4c7","schema_version":"1.0","event_id":"sha256:1551ce6d9d0028d7f836e614c387048f432570c35ca43fdc8069f9f3dc15d4c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/bundle.json","state_url":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/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":"2026-05-28T03:58:34Z","links":{"resolver":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV","bundle":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/bundle.json","state":"https://pith.science/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7CFLSMPZODNFEAFDNBJ2VB5TV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y7CFLSMPZODNFEAFDNBJ2VB5TV","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":"47e62180956a3090446ee7e84a42d95871894647919a3aa6e84c749027c63b94","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T04:23:35Z","title_canon_sha256":"bbfb3d998d1de19adf80986b727572236de89773780afc4a9540351206ac079b"},"schema_version":"1.0","source":{"id":"1810.04511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04511","created_at":"2026-05-17T23:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04511v2","created_at":"2026-05-17T23:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04511","created_at":"2026-05-17T23:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"Y7CFLSMPZODN","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y7CFLSMPZODNFEAF","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y7CFLSMP","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:1551ce6d9d0028d7f836e614c387048f432570c35ca43fdc8069f9f3dc15d4c7","target":"graph","created_at":"2026-05-17T23:44:30Z","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":"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","authors_text":"Bo Chang, Bo Zhao, Frederich Tung, Gao Huang, Leonid Sigal, Lili Meng, Wei Sun","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T04:23:35Z","title":"Interpretable Spatio-temporal Attention for Video Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04511","kind":"arxiv","version":2},"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:d61eb6fb30d0d7e16f9dabe854ba86e2ea59d13afe10853fab19cf01f8597f7c","target":"record","created_at":"2026-05-17T23:44:30Z","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":"47e62180956a3090446ee7e84a42d95871894647919a3aa6e84c749027c63b94","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-01T04:23:35Z","title_canon_sha256":"bbfb3d998d1de19adf80986b727572236de89773780afc4a9540351206ac079b"},"schema_version":"1.0","source":{"id":"1810.04511","kind":"arxiv","version":2}},"canonical_sha256":"c7c455c98fcb86d290051b429d543d9d5f1ff9f4babcaab2201c6ff6c276532e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7c455c98fcb86d290051b429d543d9d5f1ff9f4babcaab2201c6ff6c276532e","first_computed_at":"2026-05-17T23:44:30.156678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:30.156678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gVfuul0RA/VEX8o5fj/pBrKs20EVmHCO3RCnh94iUBlQWwd+MF+APf0ezKLQlu/ULkauH4Xcp19l2JanMBeYDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:30.157431Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d61eb6fb30d0d7e16f9dabe854ba86e2ea59d13afe10853fab19cf01f8597f7c","sha256:1551ce6d9d0028d7f836e614c387048f432570c35ca43fdc8069f9f3dc15d4c7"],"state_sha256":"afa575f7528ab3bebe132bc24bb7a03fd5fc60c85209b935773607c0bf2ca9ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqBNt6lScCiGOlaCJtMcxKHw/Zrvpcgoc1xFs2UZx/ZyZHH50MoD/3MQXLbA3RM2grgD5ixUQzHwWWTc5a+iDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T03:58:34.461823Z","bundle_sha256":"fc8e321f1d5c83da781f8da861bd6440ad738e10d7018a43f78a669faa035c65"}}