{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6TR7CJMUYHMRIDTENM7S3BUZDH","short_pith_number":"pith:6TR7CJMU","schema_version":"1.0","canonical_sha256":"f4e3f12594c1d9140e646b3f2d869919cf02115f8a5ed264c7b277919c376f73","source":{"kind":"arxiv","id":"2210.03941","version":1},"attestation_state":"computed","paper":{"title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bing-Chen Tsai, Hsin-Ying Lee, Hung-Ting Su, Jia-Fong Yeh, Tsung-Han Wu, Winston H. Hsu","submitted_at":"2022-10-08T07:03:31Z","abstract_excerpt":"While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities. To learn fine-grained visual understanding, we decouple spatial-temporal modeling and propose a hybrid pipeline, Decoupled Spatial-Temporal Encoders, integrating an image- and a video-language encoder. The former encodes spatial semantics from larger but sparsely sampled frames inde"},"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":"2210.03941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-08T07:03:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"63f93a7cca5cc4cf04cef9a9ec87457b8d73c7045e0788b26d28df87a362f29f","abstract_canon_sha256":"c7dcf778d9b7c6616366801d5b44be011c10b43d9547f9b4b00864bfcfa6e39c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:34.118627Z","signature_b64":"M48uT3snIDRp82thrACQfrG1HTOudO0aVjZIfhBIRryFCgGsNqu5s2G05n4E7m5MagyItIvdIsrWoHFNUrJgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4e3f12594c1d9140e646b3f2d869919cf02115f8a5ed264c7b277919c376f73","last_reissued_at":"2026-07-05T05:04:34.118198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:34.118198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bing-Chen Tsai, Hsin-Ying Lee, Hung-Ting Su, Jia-Fong Yeh, Tsung-Han Wu, Winston H. Hsu","submitted_at":"2022-10-08T07:03:31Z","abstract_excerpt":"While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities. To learn fine-grained visual understanding, we decouple spatial-temporal modeling and propose a hybrid pipeline, Decoupled Spatial-Temporal Encoders, integrating an image- and a video-language encoder. The former encodes spatial semantics from larger but sparsely sampled frames inde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03941","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/2210.03941/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":"2210.03941","created_at":"2026-07-05T05:04:34.118255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03941v1","created_at":"2026-07-05T05:04:34.118255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03941","created_at":"2026-07-05T05:04:34.118255+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TR7CJMUYHMR","created_at":"2026-07-05T05:04:34.118255+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TR7CJMUYHMRIDTE","created_at":"2026-07-05T05:04:34.118255+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TR7CJMU","created_at":"2026-07-05T05:04:34.118255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03581","citing_title":"DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH","json":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH.json","graph_json":"https://pith.science/api/pith-number/6TR7CJMUYHMRIDTENM7S3BUZDH/graph.json","events_json":"https://pith.science/api/pith-number/6TR7CJMUYHMRIDTENM7S3BUZDH/events.json","paper":"https://pith.science/paper/6TR7CJMU"},"agent_actions":{"view_html":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH","download_json":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH.json","view_paper":"https://pith.science/paper/6TR7CJMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03941&json=true","fetch_graph":"https://pith.science/api/pith-number/6TR7CJMUYHMRIDTENM7S3BUZDH/graph.json","fetch_events":"https://pith.science/api/pith-number/6TR7CJMUYHMRIDTENM7S3BUZDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH/action/storage_attestation","attest_author":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH/action/author_attestation","sign_citation":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH/action/citation_signature","submit_replication":"https://pith.science/pith/6TR7CJMUYHMRIDTENM7S3BUZDH/action/replication_record"}},"created_at":"2026-07-05T05:04:34.118255+00:00","updated_at":"2026-07-05T05:04:34.118255+00:00"}