{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E4EOFOD5BVMUL37J6UQN4D2YJC","short_pith_number":"pith:E4EOFOD5","schema_version":"1.0","canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","source":{"kind":"arxiv","id":"2103.12346","version":1},"attestation_state":"computed","paper":{"title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaying Liu, Shih-Fu Chang, Sijie Song, Xudong Lin, Zongming Guo","submitted_at":"2021-03-23T06:42:49Z","abstract_excerpt":"In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking, proposal-based matching), we tackle the problem from a novel perspective, \\textbf{co-grounding}, with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency with co-grounding feature learning. Semantic attention learning explicitly parses referring cues in "},"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":"2103.12346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T06:42:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb763581614b982ea53318a3d332710af7a86083cb3a1ef3a9b56c2346d3ba60","abstract_canon_sha256":"5dccc272e4b322cc5fcfd9af219fd1a69c64d1ea2e9f5a313e9061e42b0f04a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:45.736114Z","signature_b64":"gcJ7gGhRARXOpGhi5xTytoCplXiUiT9LQtEYB56fp2USxWJL25merMuyFMsR4MpACukL2BeykCIDrPUKe7cwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2708e2b87d0d5945efe9f520de0f5848a3143ce316d4fb5176250856bda3ec20","last_reissued_at":"2026-07-05T02:25:45.735534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:45.735534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-Grounding Networks with Semantic Attention for Referring Expression Comprehension in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaying Liu, Shih-Fu Chang, Sijie Song, Xudong Lin, Zongming Guo","submitted_at":"2021-03-23T06:42:49Z","abstract_excerpt":"In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking, proposal-based matching), we tackle the problem from a novel perspective, \\textbf{co-grounding}, with an elegant one-stage framework. We enhance the single-frame grounding accuracy by semantic attention learning and improve the cross-frame grounding consistency with co-grounding feature learning. Semantic attention learning explicitly parses referring cues in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12346","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/2103.12346/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":"2103.12346","created_at":"2026-07-05T02:25:45.735605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12346v1","created_at":"2026-07-05T02:25:45.735605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12346","created_at":"2026-07-05T02:25:45.735605+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4EOFOD5BVMU","created_at":"2026-07-05T02:25:45.735605+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4EOFOD5BVMUL37J","created_at":"2026-07-05T02:25:45.735605+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4EOFOD5","created_at":"2026-07-05T02:25:45.735605+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/E4EOFOD5BVMUL37J6UQN4D2YJC","json":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC.json","graph_json":"https://pith.science/api/pith-number/E4EOFOD5BVMUL37J6UQN4D2YJC/graph.json","events_json":"https://pith.science/api/pith-number/E4EOFOD5BVMUL37J6UQN4D2YJC/events.json","paper":"https://pith.science/paper/E4EOFOD5"},"agent_actions":{"view_html":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC","download_json":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC.json","view_paper":"https://pith.science/paper/E4EOFOD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12346&json=true","fetch_graph":"https://pith.science/api/pith-number/E4EOFOD5BVMUL37J6UQN4D2YJC/graph.json","fetch_events":"https://pith.science/api/pith-number/E4EOFOD5BVMUL37J6UQN4D2YJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/action/storage_attestation","attest_author":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/action/author_attestation","sign_citation":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/action/citation_signature","submit_replication":"https://pith.science/pith/E4EOFOD5BVMUL37J6UQN4D2YJC/action/replication_record"}},"created_at":"2026-07-05T02:25:45.735605+00:00","updated_at":"2026-07-05T02:25:45.735605+00:00"}