{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:H2RSVLL3FJORWG2FSVGADNW4DK","short_pith_number":"pith:H2RSVLL3","schema_version":"1.0","canonical_sha256":"3ea32aad7b2a5d1b1b45954c01b6dc1ab3f6cf37e71b3425f0e0c6866a933500","source":{"kind":"arxiv","id":"2105.03245","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Focus for Efficient Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gao Huang, Haojun Jiang, Shiji Song, Yizeng Han, Yulin Wang, Zhaoxi Chen","submitted_at":"2021-05-07T13:24:47Z","abstract_excerpt":"In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which shifts smoothly across frames. Therefore, we model the patch localization problem as a sequential decision task, and propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus). In specific, a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent"},"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":"2105.03245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-07T13:24:47Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"dbb315e1e0221f7d011c6a17b3baa58baf1aa4c35eae57394a5e28371efb3c83","abstract_canon_sha256":"a79dc7fab79158b520d86d11112940dff7f0e71ed186836d06c9ed8da83d85f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:46.776231Z","signature_b64":"zUgEXVxv71tvIDY0Fa67VnSiIvbvw62waSp4tAU6s6GoeIejUUFzBwBm8rFU24uLgfnxuBvuC224WylgryUACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ea32aad7b2a5d1b1b45954c01b6dc1ab3f6cf37e71b3425f0e0c6866a933500","last_reissued_at":"2026-07-05T03:06:46.775709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:46.775709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Focus for Efficient Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Gao Huang, Haojun Jiang, Shiji Song, Yizeng Han, Yulin Wang, Zhaoxi Chen","submitted_at":"2021-05-07T13:24:47Z","abstract_excerpt":"In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which shifts smoothly across frames. Therefore, we model the patch localization problem as a sequential decision task, and propose a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus). In specific, a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03245","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.03245/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":"2105.03245","created_at":"2026-07-05T03:06:46.775776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03245v2","created_at":"2026-07-05T03:06:46.775776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03245","created_at":"2026-07-05T03:06:46.775776+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2RSVLL3FJOR","created_at":"2026-07-05T03:06:46.775776+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2RSVLL3FJORWG2F","created_at":"2026-07-05T03:06:46.775776+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2RSVLL3","created_at":"2026-07-05T03:06:46.775776+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/H2RSVLL3FJORWG2FSVGADNW4DK","json":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK.json","graph_json":"https://pith.science/api/pith-number/H2RSVLL3FJORWG2FSVGADNW4DK/graph.json","events_json":"https://pith.science/api/pith-number/H2RSVLL3FJORWG2FSVGADNW4DK/events.json","paper":"https://pith.science/paper/H2RSVLL3"},"agent_actions":{"view_html":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK","download_json":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK.json","view_paper":"https://pith.science/paper/H2RSVLL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03245&json=true","fetch_graph":"https://pith.science/api/pith-number/H2RSVLL3FJORWG2FSVGADNW4DK/graph.json","fetch_events":"https://pith.science/api/pith-number/H2RSVLL3FJORWG2FSVGADNW4DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK/action/storage_attestation","attest_author":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK/action/author_attestation","sign_citation":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK/action/citation_signature","submit_replication":"https://pith.science/pith/H2RSVLL3FJORWG2FSVGADNW4DK/action/replication_record"}},"created_at":"2026-07-05T03:06:46.775776+00:00","updated_at":"2026-07-05T03:06:46.775776+00:00"}