{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:RHV7E7OJRKYM6ZE2NNMW75LES5","short_pith_number":"pith:RHV7E7OJ","schema_version":"1.0","canonical_sha256":"89ebf27dc98ab0cf649a6b596ff56497788fa4ca2d50ff9bd8791b7c901eb18a","source":{"kind":"arxiv","id":"1511.04119","version":3},"attestation_state":"computed","paper":{"title":"Action Recognition using Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ruslan Salakhutdinov, Ryan Kiros, Shikhar Sharma","submitted_at":"2015-11-12T23:06:42Z","abstract_excerpt":"We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units which are deep both spatially and temporally. Our model learns to focus selectively on parts of the video frames and classifies videos after taking a few glimpses. The model essentially learns which parts in the frames are relevant for the task at hand and attaches higher importance to them. We evaluate the model on UCF-11 (YouTube Action), HMDB-51 and Hollywood2 datasets and analyze how the model focuses its attent"},"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":"1511.04119","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-12T23:06:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4cb18f8df3e198a32925e392dfb811f12ca01ad2efc650b77a2d6095a9b138a0","abstract_canon_sha256":"82cfcb30ac886879a1fddf664c98c2a4bfc944b3ca3464d9d118348df5aad2f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:50.180610Z","signature_b64":"D2i/QyWGiHtMcHdfilIXLwMjgnOFouFc80/0H7i32iTY6ouIkPHxadfjdA7xI7PhbYNC8l5gv13ObyVtYnPBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ebf27dc98ab0cf649a6b596ff56497788fa4ca2d50ff9bd8791b7c901eb18a","last_reissued_at":"2026-05-18T01:20:50.180132Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:50.180132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action Recognition using Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ruslan Salakhutdinov, Ryan Kiros, Shikhar Sharma","submitted_at":"2015-11-12T23:06:42Z","abstract_excerpt":"We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units which are deep both spatially and temporally. Our model learns to focus selectively on parts of the video frames and classifies videos after taking a few glimpses. The model essentially learns which parts in the frames are relevant for the task at hand and attaches higher importance to them. We evaluate the model on UCF-11 (YouTube Action), HMDB-51 and Hollywood2 datasets and analyze how the model focuses its attent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04119","kind":"arxiv","version":3},"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":"1511.04119","created_at":"2026-05-18T01:20:50.180209+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.04119v3","created_at":"2026-05-18T01:20:50.180209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04119","created_at":"2026-05-18T01:20:50.180209+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHV7E7OJRKYM","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHV7E7OJRKYM6ZE2","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHV7E7OJ","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01193","citing_title":"Inverse Attention Guided Deep Crowd Counting Network","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5","json":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5.json","graph_json":"https://pith.science/api/pith-number/RHV7E7OJRKYM6ZE2NNMW75LES5/graph.json","events_json":"https://pith.science/api/pith-number/RHV7E7OJRKYM6ZE2NNMW75LES5/events.json","paper":"https://pith.science/paper/RHV7E7OJ"},"agent_actions":{"view_html":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5","download_json":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5.json","view_paper":"https://pith.science/paper/RHV7E7OJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.04119&json=true","fetch_graph":"https://pith.science/api/pith-number/RHV7E7OJRKYM6ZE2NNMW75LES5/graph.json","fetch_events":"https://pith.science/api/pith-number/RHV7E7OJRKYM6ZE2NNMW75LES5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5/action/storage_attestation","attest_author":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5/action/author_attestation","sign_citation":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5/action/citation_signature","submit_replication":"https://pith.science/pith/RHV7E7OJRKYM6ZE2NNMW75LES5/action/replication_record"}},"created_at":"2026-05-18T01:20:50.180209+00:00","updated_at":"2026-05-18T01:20:50.180209+00:00"}