{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LZIK7JY2XNBU5TOSFROM27RXZZ","short_pith_number":"pith:LZIK7JY2","schema_version":"1.0","canonical_sha256":"5e50afa71abb434ecdd22c5ccd7e37ce58ae7c4f82df40146757c9d6483dbecd","source":{"kind":"arxiv","id":"2009.06066","version":1},"attestation_state":"computed","paper":{"title":"Cosine meets Softmax: A tough-to-beat baseline for visual grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"K. Madhava Krishna, Nivedita Rufus, Unni Krishnan R Nair, Vineet Gandhi","submitted_at":"2020-09-13T19:35:43Z","abstract_excerpt":"In this paper, we present a simple baseline for visual grounding for autonomous driving which outperforms the state of the art methods, while retaining minimal design choices. Our framework minimizes the cross-entropy loss over the cosine distance between multiple image ROI features with a text embedding (representing the give sentence/phrase). We use pre-trained networks for obtaining the initial embeddings and learn a transformation layer on top of the text embedding. We perform experiments on the Talk2Car dataset and achieve 68.7% AP50 accuracy, improving upon the previous state of the art "},"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":"2009.06066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-13T19:35:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ed8cafb69e3a3d8ab57d9389a3e82bfa373b173cd3a52dda9fa85b23e4016f43","abstract_canon_sha256":"55768279c2f62cca1319e57ce352b54c6a8ca7855ad4db66c1a4c3f3b03fa70f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:04.342168Z","signature_b64":"pihqa7knaHIML39ZhjL6nYn+WYvyHgsGRo51/6IX5g8Bp6sjH7dbYNRZoA3FEvk946ZcCL+b6A+NG6JZlznAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e50afa71abb434ecdd22c5ccd7e37ce58ae7c4f82df40146757c9d6483dbecd","last_reissued_at":"2026-07-05T01:35:04.341733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:04.341733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cosine meets Softmax: A tough-to-beat baseline for visual grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"K. Madhava Krishna, Nivedita Rufus, Unni Krishnan R Nair, Vineet Gandhi","submitted_at":"2020-09-13T19:35:43Z","abstract_excerpt":"In this paper, we present a simple baseline for visual grounding for autonomous driving which outperforms the state of the art methods, while retaining minimal design choices. Our framework minimizes the cross-entropy loss over the cosine distance between multiple image ROI features with a text embedding (representing the give sentence/phrase). We use pre-trained networks for obtaining the initial embeddings and learn a transformation layer on top of the text embedding. We perform experiments on the Talk2Car dataset and achieve 68.7% AP50 accuracy, improving upon the previous state of the art "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06066","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/2009.06066/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":"2009.06066","created_at":"2026-07-05T01:35:04.341792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.06066v1","created_at":"2026-07-05T01:35:04.341792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06066","created_at":"2026-07-05T01:35:04.341792+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZIK7JY2XNBU","created_at":"2026-07-05T01:35:04.341792+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZIK7JY2XNBU5TOS","created_at":"2026-07-05T01:35:04.341792+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZIK7JY2","created_at":"2026-07-05T01:35:04.341792+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/LZIK7JY2XNBU5TOSFROM27RXZZ","json":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ.json","graph_json":"https://pith.science/api/pith-number/LZIK7JY2XNBU5TOSFROM27RXZZ/graph.json","events_json":"https://pith.science/api/pith-number/LZIK7JY2XNBU5TOSFROM27RXZZ/events.json","paper":"https://pith.science/paper/LZIK7JY2"},"agent_actions":{"view_html":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ","download_json":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ.json","view_paper":"https://pith.science/paper/LZIK7JY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.06066&json=true","fetch_graph":"https://pith.science/api/pith-number/LZIK7JY2XNBU5TOSFROM27RXZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZIK7JY2XNBU5TOSFROM27RXZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ/action/storage_attestation","attest_author":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ/action/author_attestation","sign_citation":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ/action/citation_signature","submit_replication":"https://pith.science/pith/LZIK7JY2XNBU5TOSFROM27RXZZ/action/replication_record"}},"created_at":"2026-07-05T01:35:04.341792+00:00","updated_at":"2026-07-05T01:35:04.341792+00:00"}