{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:F3W64KQE6BJCSHBR5UAYLORQXP","short_pith_number":"pith:F3W64KQE","schema_version":"1.0","canonical_sha256":"2eedee2a04f052291c31ed0185ba30bbdce1dc6b75ab2c7ed37869a488b545f1","source":{"kind":"arxiv","id":"1701.01821","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Learning of Long-Term Motion Dynamics for Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Boya Peng, De-An Huang, Li Fei-Fei, Zelun Luo","submitted_at":"2017-01-07T12:03:11Z","abstract_excerpt":"We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the complexity of the learning framework, we propose to describe the motion as a sequence of atomic 3D flows computed with RGB-D modality. We use a Recurrent Neural Network based Encoder-Decoder framework to predict these sequences of flows. We argue that in order for the decoder to reconstruct these sequences, the encoder must learn a robust video representation that c"},"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":"1701.01821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-07T12:03:11Z","cross_cats_sorted":[],"title_canon_sha256":"3f6a00ddecb74b17c05752209590102d0b55fb429ee4ab669367362512a8613d","abstract_canon_sha256":"cdf418bbb730361f7e4f47fcb018efbd3dbef23edf2c73d469a0642bf8f4fe5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:31.317078Z","signature_b64":"mqR3DgrNj84CZBY/5FheGsR0KNzA7sSR2vvixRN6GvUhkp0raAVHS3QCws+bUjABNfJXIJi2UFOeY1iP4rcqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eedee2a04f052291c31ed0185ba30bbdce1dc6b75ab2c7ed37869a488b545f1","last_reissued_at":"2026-05-18T00:46:31.316503Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:31.316503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learning of Long-Term Motion Dynamics for Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandre Alahi, Boya Peng, De-An Huang, Li Fei-Fei, Zelun Luo","submitted_at":"2017-01-07T12:03:11Z","abstract_excerpt":"We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the complexity of the learning framework, we propose to describe the motion as a sequence of atomic 3D flows computed with RGB-D modality. We use a Recurrent Neural Network based Encoder-Decoder framework to predict these sequences of flows. We argue that in order for the decoder to reconstruct these sequences, the encoder must learn a robust video representation that c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.01821","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1701.01821","created_at":"2026-05-18T00:46:31.316607+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.01821v3","created_at":"2026-05-18T00:46:31.316607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.01821","created_at":"2026-05-18T00:46:31.316607+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3W64KQE6BJC","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3W64KQE6BJCSHBR","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3W64KQE","created_at":"2026-05-18T12:31:15.632608+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/F3W64KQE6BJCSHBR5UAYLORQXP","json":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP.json","graph_json":"https://pith.science/api/pith-number/F3W64KQE6BJCSHBR5UAYLORQXP/graph.json","events_json":"https://pith.science/api/pith-number/F3W64KQE6BJCSHBR5UAYLORQXP/events.json","paper":"https://pith.science/paper/F3W64KQE"},"agent_actions":{"view_html":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP","download_json":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP.json","view_paper":"https://pith.science/paper/F3W64KQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.01821&json=true","fetch_graph":"https://pith.science/api/pith-number/F3W64KQE6BJCSHBR5UAYLORQXP/graph.json","fetch_events":"https://pith.science/api/pith-number/F3W64KQE6BJCSHBR5UAYLORQXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP/action/storage_attestation","attest_author":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP/action/author_attestation","sign_citation":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP/action/citation_signature","submit_replication":"https://pith.science/pith/F3W64KQE6BJCSHBR5UAYLORQXP/action/replication_record"}},"created_at":"2026-05-18T00:46:31.316607+00:00","updated_at":"2026-05-18T00:46:31.316607+00:00"}