{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ELVBQ55ZDLACC7FAGQCLT2EHQ7","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":"dea3822fe837cc2ea578a0c0429f7dd7d23bb8bb4a9d3bdfe283c8a36d0cfba0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-03T16:38:24Z","title_canon_sha256":"1ce6ff1a59f46722fc44f8314a705098a8ea58370dc07da2ba76002878a4291e"},"schema_version":"1.0","source":{"id":"2207.01076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01076","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01076v1","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01076","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"pith_short_12","alias_value":"ELVBQ55ZDLAC","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"pith_short_16","alias_value":"ELVBQ55ZDLACC7FA","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"pith_short_8","alias_value":"ELVBQ55Z","created_at":"2026-07-05T04:37:07Z"}],"graph_snapshots":[{"event_id":"sha256:003e8b5e445cfc67ecf258ee321fd4979cf28cee0859ae05c533dbdaee6fb3c2","target":"graph","created_at":"2026-07-05T04:37:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2207.01076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making tracking increasingly expensive. In this paper, we demonstrate that the Transformer-reliance is not necessary and the pure ConvNets are still competitive and even better yet more economical and friendly in achieving SOTA tracking. Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets. The essence lies in learning ","authors_text":"Heng Fan, Liping Jing, Mingzhe Guo, Zhipeng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-03T16:38:24Z","title":"Divert More Attention to Vision-Language Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01076","kind":"arxiv","version":1},"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":"sha256:6d5c6d3c1cae76a67accc706d0c25887c506dbf2dc96b81b8d3fafe8071ae666","target":"record","created_at":"2026-07-05T04:37:07Z","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":"dea3822fe837cc2ea578a0c0429f7dd7d23bb8bb4a9d3bdfe283c8a36d0cfba0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-03T16:38:24Z","title_canon_sha256":"1ce6ff1a59f46722fc44f8314a705098a8ea58370dc07da2ba76002878a4291e"},"schema_version":"1.0","source":{"id":"2207.01076","kind":"arxiv","version":1}},"canonical_sha256":"22ea1877b91ac0217ca03404b9e88787f1cc6f8346b9fbea02793f062df518cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22ea1877b91ac0217ca03404b9e88787f1cc6f8346b9fbea02793f062df518cd","first_computed_at":"2026-07-05T04:37:07.645532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:07.645532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/j8stHzZq9pp2y9p9e2TxK6JiWYdQ0W4g2DS0r9z6XS/XMshUf+KZ7w6VyCCyCv2z4smlFglRGs/74AJ1vfoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:07.646034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.01076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d5c6d3c1cae76a67accc706d0c25887c506dbf2dc96b81b8d3fafe8071ae666","sha256:003e8b5e445cfc67ecf258ee321fd4979cf28cee0859ae05c533dbdaee6fb3c2"],"state_sha256":"b98b6c9a3b915483ca43a6adb3c544d12785885430ce3010adc260cd2f740874"}