{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:U2YSPGRZWWJUWKKCUCXQJ5ITWC","short_pith_number":"pith:U2YSPGRZ","canonical_record":{"source":{"id":"1902.10322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T03:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"9727db43912d063721b93ccf1f26f1e3e2a86b2be82451d5f57464103a2e9498","abstract_canon_sha256":"2d0f8d19754188cbf03093e7fe481e52a359fad13d9e5687719324b905de51bc"},"schema_version":"1.0"},"canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","source":{"kind":"arxiv","id":"1902.10322","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10322","created_at":"2026-05-17T23:47:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10322v2","created_at":"2026-05-17T23:47:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10322","created_at":"2026-05-17T23:47:35Z"},{"alias_kind":"pith_short_12","alias_value":"U2YSPGRZWWJU","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U2YSPGRZWWJUWKKC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U2YSPGRZ","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:U2YSPGRZWWJUWKKCUCXQJ5ITWC","target":"record","payload":{"canonical_record":{"source":{"id":"1902.10322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T03:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"9727db43912d063721b93ccf1f26f1e3e2a86b2be82451d5f57464103a2e9498","abstract_canon_sha256":"2d0f8d19754188cbf03093e7fe481e52a359fad13d9e5687719324b905de51bc"},"schema_version":"1.0"},"canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:35.717420Z","signature_b64":"7rx9FnaW9dRlCxIbpmCFDLaaktWTsJ7cZf9ZsANQfddObwK3w5YdNkxebQjTIyTbb/Ve+fsyyGqEdSBbX9GsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","last_reissued_at":"2026-05-17T23:47:35.716952Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:35.716952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.10322","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qq9hA6745Xrhdetq8MQwvQEs9kP7nh7qeTtPmWiVT2H6uZm8UCOPgVQHrsnOhldQhIwBhRrL9J+l7FG4RoJcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:24:21.903710Z"},"content_sha256":"aa559b47850e3d533d4cb45a7eafd4b42dc12f3304f819c82f8072ab6fdc4a38","schema_version":"1.0","event_id":"sha256:aa559b47850e3d533d4cb45a7eafd4b42dc12f3304f819c82f8072ab6fdc4a38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:U2YSPGRZWWJUWKKCUCXQJ5ITWC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajmal Mian, Naveed Akhtar, Nayyer Aafaq, Syed Zulqarnain Gilani, Wei Liu","submitted_at":"2019-02-27T03:52:08Z","abstract_excerpt":"Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods mainly focus on tailoring sequence learning through RNNs for better caption generation, whereas off-the-shelf visual features are borrowed from CNNs. We argue that careful designing of visual features for this task is equally important, and present a visual feature encoding technique to generate semantically rich captions using Gated Recurrent Units "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10322","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":""},"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":"2026-05-17T23:47:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uod0vderQqPrYFgF5mTLJTQ6kKoaEPb1JA27SbmyrNf9rF8MzeMusG/HF+NyLBqJUn7F9F0n1WXJ9Oa7iNObBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:24:21.904061Z"},"content_sha256":"a637c7669470345fc22bb79a09b506a3d4bf92b875dadb9592c60f6bd7921516","schema_version":"1.0","event_id":"sha256:a637c7669470345fc22bb79a09b506a3d4bf92b875dadb9592c60f6bd7921516"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/bundle.json","state_url":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/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":"2026-06-01T21:24:21Z","links":{"resolver":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC","bundle":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/bundle.json","state":"https://pith.science/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U2YSPGRZWWJUWKKCUCXQJ5ITWC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:U2YSPGRZWWJUWKKCUCXQJ5ITWC","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":"2d0f8d19754188cbf03093e7fe481e52a359fad13d9e5687719324b905de51bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T03:52:08Z","title_canon_sha256":"9727db43912d063721b93ccf1f26f1e3e2a86b2be82451d5f57464103a2e9498"},"schema_version":"1.0","source":{"id":"1902.10322","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10322","created_at":"2026-05-17T23:47:35Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10322v2","created_at":"2026-05-17T23:47:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10322","created_at":"2026-05-17T23:47:35Z"},{"alias_kind":"pith_short_12","alias_value":"U2YSPGRZWWJU","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"U2YSPGRZWWJUWKKC","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"U2YSPGRZ","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:a637c7669470345fc22bb79a09b506a3d4bf92b875dadb9592c60f6bd7921516","target":"graph","created_at":"2026-05-17T23:47:35Z","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"},"paper":{"abstract_excerpt":"Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods mainly focus on tailoring sequence learning through RNNs for better caption generation, whereas off-the-shelf visual features are borrowed from CNNs. We argue that careful designing of visual features for this task is equally important, and present a visual feature encoding technique to generate semantically rich captions using Gated Recurrent Units ","authors_text":"Ajmal Mian, Naveed Akhtar, Nayyer Aafaq, Syed Zulqarnain Gilani, Wei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T03:52:08Z","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10322","kind":"arxiv","version":2},"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:aa559b47850e3d533d4cb45a7eafd4b42dc12f3304f819c82f8072ab6fdc4a38","target":"record","created_at":"2026-05-17T23:47:35Z","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":"2d0f8d19754188cbf03093e7fe481e52a359fad13d9e5687719324b905de51bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T03:52:08Z","title_canon_sha256":"9727db43912d063721b93ccf1f26f1e3e2a86b2be82451d5f57464103a2e9498"},"schema_version":"1.0","source":{"id":"1902.10322","kind":"arxiv","version":2}},"canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6b1279a39b5934b2942a0af04f513b0999a9ac96e3132a45c4a5c8fa1babb10","first_computed_at":"2026-05-17T23:47:35.716952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:35.716952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7rx9FnaW9dRlCxIbpmCFDLaaktWTsJ7cZf9ZsANQfddObwK3w5YdNkxebQjTIyTbb/Ve+fsyyGqEdSBbX9GsAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:35.717420Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10322","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa559b47850e3d533d4cb45a7eafd4b42dc12f3304f819c82f8072ab6fdc4a38","sha256:a637c7669470345fc22bb79a09b506a3d4bf92b875dadb9592c60f6bd7921516"],"state_sha256":"152a29f24195beb858900ffac2b9977db3fb787c11884a12744853dccf947dfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cJnzQYZiyDacuPyAgSK5/MbVLdB9ISITRD9ktjMOSkQNewdWeecop2kxj3PYwAtqhKzYDTkTULlE2XSi5kEEAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:24:21.905997Z","bundle_sha256":"b3a33a3728f187a587872b42e4ffe38db7a5c0754120639bbb3d2daab92425c4"}}