{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2LUBQSI5LJ2DTQYCGTEINCBUTJ","short_pith_number":"pith:2LUBQSI5","schema_version":"1.0","canonical_sha256":"d2e818491d5a7439c30234c88688349a5a8756f4f829222997a47382af7ebf76","source":{"kind":"arxiv","id":"2303.09055","version":1},"attestation_state":"computed","paper":{"title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kwanghoon Sohn, Kwonyoung Kim, Tuan N. Tang","submitted_at":"2023-03-16T03:11:26Z","abstract_excerpt":"Temporal Action Localization (TAL) is a challenging task in video understanding that aims to identify and localize actions within a video sequence. Recent studies have emphasized the importance of applying long-term temporal context modeling (TCM) blocks to the extracted video clip features such as employing complex self-attention mechanisms. In this paper, we present the simplest method ever to address this task and argue that the extracted video clip features are already informative to achieve outstanding performance without sophisticated architectures. To this end, we introduce TemporalMaxe"},"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":"2303.09055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T03:11:26Z","cross_cats_sorted":[],"title_canon_sha256":"27936a549fcbb130dc971372d201cc29f3681eec1eda53223f8b036b3c0e0428","abstract_canon_sha256":"05e978c3c985337f950b537aa29289deff5b0d41f7fd8fe0a46565e719272851"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:48.177227Z","signature_b64":"IHGNvfb1uyJC7H+03WqWti9C0D4Gm8Y273tFiBD0/Epmb5NjfoytIpXnXy/2qHB1tzuhiQ7IaWRJ5fzVSrERCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e818491d5a7439c30234c88688349a5a8756f4f829222997a47382af7ebf76","last_reissued_at":"2026-07-05T05:51:48.176894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:48.176894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kwanghoon Sohn, Kwonyoung Kim, Tuan N. Tang","submitted_at":"2023-03-16T03:11:26Z","abstract_excerpt":"Temporal Action Localization (TAL) is a challenging task in video understanding that aims to identify and localize actions within a video sequence. Recent studies have emphasized the importance of applying long-term temporal context modeling (TCM) blocks to the extracted video clip features such as employing complex self-attention mechanisms. In this paper, we present the simplest method ever to address this task and argue that the extracted video clip features are already informative to achieve outstanding performance without sophisticated architectures. To this end, we introduce TemporalMaxe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09055","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/2303.09055/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":"2303.09055","created_at":"2026-07-05T05:51:48.176949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09055v1","created_at":"2026-07-05T05:51:48.176949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09055","created_at":"2026-07-05T05:51:48.176949+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LUBQSI5LJ2D","created_at":"2026-07-05T05:51:48.176949+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LUBQSI5LJ2DTQYC","created_at":"2026-07-05T05:51:48.176949+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LUBQSI5","created_at":"2026-07-05T05:51:48.176949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12033","citing_title":"SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07355","citing_title":"Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31127","citing_title":"SkillSpotter: Pose-Aware Multi-View Skilled Action Detection and Grading in Ego-Exo Videos","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29858","citing_title":"Masked Diffusion Vision-Language Models for Temporal Action Localization","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09164","citing_title":"Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18274","citing_title":"LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20574","citing_title":"Where are they looking in the operating room?","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ","json":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ.json","graph_json":"https://pith.science/api/pith-number/2LUBQSI5LJ2DTQYCGTEINCBUTJ/graph.json","events_json":"https://pith.science/api/pith-number/2LUBQSI5LJ2DTQYCGTEINCBUTJ/events.json","paper":"https://pith.science/paper/2LUBQSI5"},"agent_actions":{"view_html":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ","download_json":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ.json","view_paper":"https://pith.science/paper/2LUBQSI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09055&json=true","fetch_graph":"https://pith.science/api/pith-number/2LUBQSI5LJ2DTQYCGTEINCBUTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2LUBQSI5LJ2DTQYCGTEINCBUTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ/action/storage_attestation","attest_author":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ/action/author_attestation","sign_citation":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ/action/citation_signature","submit_replication":"https://pith.science/pith/2LUBQSI5LJ2DTQYCGTEINCBUTJ/action/replication_record"}},"created_at":"2026-07-05T05:51:48.176949+00:00","updated_at":"2026-07-05T05:51:48.176949+00:00"}