{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IXTCT6GHIIV4N5QCD7DZJWAFSU","short_pith_number":"pith:IXTCT6GH","schema_version":"1.0","canonical_sha256":"45e629f8c7422bc6f6021fc794d805951f7a41502a9489da1a0b8f534a9182ae","source":{"kind":"arxiv","id":"2108.08990","version":1},"attestation_state":"computed","paper":{"title":"Few Shot Activity Recognition Using Variational Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Neeraj Kumar, Siddhansh Narang","submitted_at":"2021-08-20T03:57:58Z","abstract_excerpt":"There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel action categories which are represented by few instances in the training data. We propose a novel variational inference based architectural framework (HF-AR) for few shot activity recognition. Our framework leverages volume-preserving Householder Flow to learn a flexible posterior distribution of the novel classes. This results in better performance as compar"},"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":"2108.08990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T03:57:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3df303d015b1bd3a1f431d9ee06e1ddc1a24c67af0967f45f2ea00ad09c908e","abstract_canon_sha256":"b938f7a8d3b6c8a9fb56a56933f3f63d0d70640a8adb541a1750680ad55c2ddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:32.594081Z","signature_b64":"KvDowQXBmW5C65qMEc1RVSvyGms9Esjbo+S0r0zmBnKfWeL0jSLCZptae+QhB3vKFQT3JH/hQkJpJoZFyaYVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e629f8c7422bc6f6021fc794d805951f7a41502a9489da1a0b8f534a9182ae","last_reissued_at":"2026-07-05T03:07:32.593655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:32.593655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few Shot Activity Recognition Using Variational Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Neeraj Kumar, Siddhansh Narang","submitted_at":"2021-08-20T03:57:58Z","abstract_excerpt":"There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel action categories which are represented by few instances in the training data. We propose a novel variational inference based architectural framework (HF-AR) for few shot activity recognition. Our framework leverages volume-preserving Householder Flow to learn a flexible posterior distribution of the novel classes. This results in better performance as compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08990","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.08990/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":"2108.08990","created_at":"2026-07-05T03:07:32.593709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08990v1","created_at":"2026-07-05T03:07:32.593709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08990","created_at":"2026-07-05T03:07:32.593709+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXTCT6GHIIV4","created_at":"2026-07-05T03:07:32.593709+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXTCT6GHIIV4N5QC","created_at":"2026-07-05T03:07:32.593709+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXTCT6GH","created_at":"2026-07-05T03:07:32.593709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10443","citing_title":"SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU","json":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU.json","graph_json":"https://pith.science/api/pith-number/IXTCT6GHIIV4N5QCD7DZJWAFSU/graph.json","events_json":"https://pith.science/api/pith-number/IXTCT6GHIIV4N5QCD7DZJWAFSU/events.json","paper":"https://pith.science/paper/IXTCT6GH"},"agent_actions":{"view_html":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU","download_json":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU.json","view_paper":"https://pith.science/paper/IXTCT6GH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08990&json=true","fetch_graph":"https://pith.science/api/pith-number/IXTCT6GHIIV4N5QCD7DZJWAFSU/graph.json","fetch_events":"https://pith.science/api/pith-number/IXTCT6GHIIV4N5QCD7DZJWAFSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU/action/storage_attestation","attest_author":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU/action/author_attestation","sign_citation":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU/action/citation_signature","submit_replication":"https://pith.science/pith/IXTCT6GHIIV4N5QCD7DZJWAFSU/action/replication_record"}},"created_at":"2026-07-05T03:07:32.593709+00:00","updated_at":"2026-07-05T03:07:32.593709+00:00"}