{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3OIT6SL3SGRAH25YNSL7NKUEQS","short_pith_number":"pith:3OIT6SL3","canonical_record":{"source":{"id":"2404.17929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T14:43:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d6b2f442f71ee16b88e5db95b8db233e7cbf10da4828401a485496dcea723bf1","abstract_canon_sha256":"e1ddd6ab20ca93ec97eabb58d2b51f6d6be2b34249c12b26000d0b83f7b8e252"},"schema_version":"1.0"},"canonical_sha256":"db913f497b91a203ebb86c97f6aa84848f068a5fabc03bd257de6923634cd85d","source":{"kind":"arxiv","id":"2404.17929","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17929","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17929v1","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17929","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"3OIT6SL3SGRA","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"3OIT6SL3SGRAH25Y","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"3OIT6SL3","created_at":"2026-07-05T08:12:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3OIT6SL3SGRAH25YNSL7NKUEQS","target":"record","payload":{"canonical_record":{"source":{"id":"2404.17929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T14:43:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d6b2f442f71ee16b88e5db95b8db233e7cbf10da4828401a485496dcea723bf1","abstract_canon_sha256":"e1ddd6ab20ca93ec97eabb58d2b51f6d6be2b34249c12b26000d0b83f7b8e252"},"schema_version":"1.0"},"canonical_sha256":"db913f497b91a203ebb86c97f6aa84848f068a5fabc03bd257de6923634cd85d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:55.922844Z","signature_b64":"HacHTtP1lCv2MF8wokopjmmzpHaI0seRqrrXS+Oj/aG9FCfXIt9pHStxdMw+l2xa4J1li/74PXVRbWviXEryCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db913f497b91a203ebb86c97f6aa84848f068a5fabc03bd257de6923634cd85d","last_reissued_at":"2026-07-05T08:12:55.922384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:55.922384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.17929","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WSf58UMwUsVr2b4l3RIT2yrdaBozS2aXONvLiK95eRIYIpbkd6qrYITK/vmoRA9/Sq78h0YvGz/HksK9UtcUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:25:47.224978Z"},"content_sha256":"e77899d94d57b8a0838cd39e468ec0f47cd7140386165a29bbab6b3052f2b251","schema_version":"1.0","event_id":"sha256:e77899d94d57b8a0838cd39e468ec0f47cd7140386165a29bbab6b3052f2b251"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3OIT6SL3SGRAH25YNSL7NKUEQS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Futian Wang, Jiandong Jin, Jun Zhu, Qian Zhu, Xiao Wang, Yaowei Wang, Yonghong Tian","submitted_at":"2024-04-27T14:43:32Z","abstract_excerpt":"Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to understand human attributes using video frames that can fully use temporal information by fine-tuning a pre-trained multi-modal foundation model efficiently. Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract the visual features. More importantly, we propose a novel spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17929","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/2404.17929/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yf3lYKpw3FKcRHpNvprJJjz4xwbP94Uuxcmqp0VJTa/2kMyFeoet4wUnqdXIChy9HV3adMo9kbmjKl542O3/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:25:47.225295Z"},"content_sha256":"5545a83f350937da21cfbb1062f8ca6127360ff64729f265b56675c77fa0c15b","schema_version":"1.0","event_id":"sha256:5545a83f350937da21cfbb1062f8ca6127360ff64729f265b56675c77fa0c15b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OIT6SL3SGRAH25YNSL7NKUEQS/bundle.json","state_url":"https://pith.science/pith/3OIT6SL3SGRAH25YNSL7NKUEQS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OIT6SL3SGRAH25YNSL7NKUEQS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T08:25:47Z","links":{"resolver":"https://pith.science/pith/3OIT6SL3SGRAH25YNSL7NKUEQS","bundle":"https://pith.science/pith/3OIT6SL3SGRAH25YNSL7NKUEQS/bundle.json","state":"https://pith.science/pith/3OIT6SL3SGRAH25YNSL7NKUEQS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OIT6SL3SGRAH25YNSL7NKUEQS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3OIT6SL3SGRAH25YNSL7NKUEQS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e1ddd6ab20ca93ec97eabb58d2b51f6d6be2b34249c12b26000d0b83f7b8e252","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T14:43:32Z","title_canon_sha256":"d6b2f442f71ee16b88e5db95b8db233e7cbf10da4828401a485496dcea723bf1"},"schema_version":"1.0","source":{"id":"2404.17929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17929","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17929v1","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17929","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"3OIT6SL3SGRA","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"3OIT6SL3SGRAH25Y","created_at":"2026-07-05T08:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"3OIT6SL3","created_at":"2026-07-05T08:12:55Z"}],"graph_snapshots":[{"event_id":"sha256:5545a83f350937da21cfbb1062f8ca6127360ff64729f265b56675c77fa0c15b","target":"graph","created_at":"2026-07-05T08:12:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.17929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to understand human attributes using video frames that can fully use temporal information by fine-tuning a pre-trained multi-modal foundation model efficiently. Specifically, we formulate the video-based PAR as a vision-language fusion problem and adopt a pre-trained foundation model CLIP to extract the visual features. More importantly, we propose a novel spa","authors_text":"Bo Jiang, Futian Wang, Jiandong Jin, Jun Zhu, Qian Zhu, Xiao Wang, Yaowei Wang, Yonghong Tian","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T14:43:32Z","title":"Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17929","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e77899d94d57b8a0838cd39e468ec0f47cd7140386165a29bbab6b3052f2b251","target":"record","created_at":"2026-07-05T08:12:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e1ddd6ab20ca93ec97eabb58d2b51f6d6be2b34249c12b26000d0b83f7b8e252","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-27T14:43:32Z","title_canon_sha256":"d6b2f442f71ee16b88e5db95b8db233e7cbf10da4828401a485496dcea723bf1"},"schema_version":"1.0","source":{"id":"2404.17929","kind":"arxiv","version":1}},"canonical_sha256":"db913f497b91a203ebb86c97f6aa84848f068a5fabc03bd257de6923634cd85d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db913f497b91a203ebb86c97f6aa84848f068a5fabc03bd257de6923634cd85d","first_computed_at":"2026-07-05T08:12:55.922384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:55.922384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HacHTtP1lCv2MF8wokopjmmzpHaI0seRqrrXS+Oj/aG9FCfXIt9pHStxdMw+l2xa4J1li/74PXVRbWviXEryCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:55.922844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e77899d94d57b8a0838cd39e468ec0f47cd7140386165a29bbab6b3052f2b251","sha256:5545a83f350937da21cfbb1062f8ca6127360ff64729f265b56675c77fa0c15b"],"state_sha256":"0ea6945c100a3dd8326d8915a5ad1567328062e3549037275c0af5cccc63ca71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4VtwRvRzOZSbNpKyV3630bKECgjMUFoYWNbeyVgSe2DjRuvyoM1kyqf/E7u6R4uhH1wArzMPoi1q3N9EUgGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:25:47.228476Z","bundle_sha256":"48bd4125e2e795b58dc1ec348cc3fbdcaa264862db98dd072e92682671e3b08f"}}