{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XB7EJWLZQSBYGCU2F4NTKW3VSY","short_pith_number":"pith:XB7EJWLZ","schema_version":"1.0","canonical_sha256":"b87e44d9798483830a9a2f1b355b7596083941d272ff06b1be1a17c810c07f2c","source":{"kind":"arxiv","id":"2103.17260","version":2},"attestation_state":"computed","paper":{"title":"Learning by Aligning Videos in Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrey Konin, Huseyin Coskun, Muhammad Zeeshan Zia, Quoc-Huy Tran, Sanjay Haresh, Sateesh Kumar, Shahram Najam Syed","submitted_at":"2021-03-31T17:55:52Z","abstract_excerpt":"We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment loss and temporal regularization terms, which can be used as supervision signals for training an encoder network. Specifically, the temporal alignment loss (i.e., Soft-DTW) aims for the minimum cost for temporally aligning videos in the embedding space. However, optimizing solely for this term leads to trivial solutions, particularly, one where all frames ge"},"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":"2103.17260","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T17:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"3ee7b83d6ea73502f6edcce651400ebc093c9f07fcffd83009d4419fe732a79b","abstract_canon_sha256":"75478c8ae8a592d8def9a98e050e0cea8c1e0abf71f8e57cf3846a1c3ed5b4a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:01.189562Z","signature_b64":"ckfnoobccp4loMFMZ7Esf6mdeC26Ey9R5RvFT04EooQY+a4uj/ysBkjzEuc5LFy0qDm0abuxXiuelSgkGMxFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b87e44d9798483830a9a2f1b355b7596083941d272ff06b1be1a17c810c07f2c","last_reissued_at":"2026-07-05T06:42:01.189052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:01.189052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning by Aligning Videos in Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrey Konin, Huseyin Coskun, Muhammad Zeeshan Zia, Quoc-Huy Tran, Sanjay Haresh, Sateesh Kumar, Shahram Najam Syed","submitted_at":"2021-03-31T17:55:52Z","abstract_excerpt":"We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment loss and temporal regularization terms, which can be used as supervision signals for training an encoder network. Specifically, the temporal alignment loss (i.e., Soft-DTW) aims for the minimum cost for temporally aligning videos in the embedding space. However, optimizing solely for this term leads to trivial solutions, particularly, one where all frames ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.17260","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/2103.17260/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":"2103.17260","created_at":"2026-07-05T06:42:01.189109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.17260v2","created_at":"2026-07-05T06:42:01.189109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.17260","created_at":"2026-07-05T06:42:01.189109+00:00"},{"alias_kind":"pith_short_12","alias_value":"XB7EJWLZQSBY","created_at":"2026-07-05T06:42:01.189109+00:00"},{"alias_kind":"pith_short_16","alias_value":"XB7EJWLZQSBYGCU2","created_at":"2026-07-05T06:42:01.189109+00:00"},{"alias_kind":"pith_short_8","alias_value":"XB7EJWLZ","created_at":"2026-07-05T06:42:01.189109+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/XB7EJWLZQSBYGCU2F4NTKW3VSY","json":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY.json","graph_json":"https://pith.science/api/pith-number/XB7EJWLZQSBYGCU2F4NTKW3VSY/graph.json","events_json":"https://pith.science/api/pith-number/XB7EJWLZQSBYGCU2F4NTKW3VSY/events.json","paper":"https://pith.science/paper/XB7EJWLZ"},"agent_actions":{"view_html":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY","download_json":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY.json","view_paper":"https://pith.science/paper/XB7EJWLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.17260&json=true","fetch_graph":"https://pith.science/api/pith-number/XB7EJWLZQSBYGCU2F4NTKW3VSY/graph.json","fetch_events":"https://pith.science/api/pith-number/XB7EJWLZQSBYGCU2F4NTKW3VSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY/action/storage_attestation","attest_author":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY/action/author_attestation","sign_citation":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY/action/citation_signature","submit_replication":"https://pith.science/pith/XB7EJWLZQSBYGCU2F4NTKW3VSY/action/replication_record"}},"created_at":"2026-07-05T06:42:01.189109+00:00","updated_at":"2026-07-05T06:42:01.189109+00:00"}