{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VZ2UFGLRYPUECLZIHYNFC7YMYT","short_pith_number":"pith:VZ2UFGLR","schema_version":"1.0","canonical_sha256":"ae75429971c3e8412f283e1a517f0cc4c81bdebf690f35f351feb5916f9462dd","source":{"kind":"arxiv","id":"1808.09892","version":1},"attestation_state":"computed","paper":{"title":"Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Oswald Lanz, Swathikiran Sudhakaran","submitted_at":"2018-08-29T15:41:36Z","abstract_excerpt":"Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be capable of suppressing irrelevant scene background and extract the representation from the most discriminative part of the video. Our contribution builds on the observation that spatio-temporal patterns characterizing actions in videos are highly correlated with objects and their location in the video. We propose Top-down Attention Action VLAD (TA-VLAD), a deep"},"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":"1808.09892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-29T15:41:36Z","cross_cats_sorted":[],"title_canon_sha256":"343bfc6e6ce5608d37bded9c884eebf81c86b3294aae8eecd6cbfccdafc64a21","abstract_canon_sha256":"23d760866bc396b01737a477ce4f76967a3ce52b9beaaf12ebf5129f506ab517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:54.067826Z","signature_b64":"9SUACeMdq9OCYm6SusFXk3iVnzjQYSNbYa75JwjW5SmOFZTU+W/kUIDeoUGN+4AEmXfyZeX3YDpM6EtlTHFsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae75429971c3e8412f283e1a517f0cc4c81bdebf690f35f351feb5916f9462dd","last_reissued_at":"2026-05-18T00:06:54.067371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:54.067371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Oswald Lanz, Swathikiran Sudhakaran","submitted_at":"2018-08-29T15:41:36Z","abstract_excerpt":"Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be capable of suppressing irrelevant scene background and extract the representation from the most discriminative part of the video. Our contribution builds on the observation that spatio-temporal patterns characterizing actions in videos are highly correlated with objects and their location in the video. We propose Top-down Attention Action VLAD (TA-VLAD), a deep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09892","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":""},"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":"1808.09892","created_at":"2026-05-18T00:06:54.067443+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09892v1","created_at":"2026-05-18T00:06:54.067443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09892","created_at":"2026-05-18T00:06:54.067443+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZ2UFGLRYPUE","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZ2UFGLRYPUECLZI","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZ2UFGLR","created_at":"2026-05-18T12:32:59.047623+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/VZ2UFGLRYPUECLZIHYNFC7YMYT","json":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT.json","graph_json":"https://pith.science/api/pith-number/VZ2UFGLRYPUECLZIHYNFC7YMYT/graph.json","events_json":"https://pith.science/api/pith-number/VZ2UFGLRYPUECLZIHYNFC7YMYT/events.json","paper":"https://pith.science/paper/VZ2UFGLR"},"agent_actions":{"view_html":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT","download_json":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT.json","view_paper":"https://pith.science/paper/VZ2UFGLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09892&json=true","fetch_graph":"https://pith.science/api/pith-number/VZ2UFGLRYPUECLZIHYNFC7YMYT/graph.json","fetch_events":"https://pith.science/api/pith-number/VZ2UFGLRYPUECLZIHYNFC7YMYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT/action/storage_attestation","attest_author":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT/action/author_attestation","sign_citation":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT/action/citation_signature","submit_replication":"https://pith.science/pith/VZ2UFGLRYPUECLZIHYNFC7YMYT/action/replication_record"}},"created_at":"2026-05-18T00:06:54.067443+00:00","updated_at":"2026-05-18T00:06:54.067443+00:00"}