{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SQPXLZ6PVT72KPFGUWBVXPBSJP","short_pith_number":"pith:SQPXLZ6P","canonical_record":{"source":{"id":"1708.02973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-09T19:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"b3d2376835a30c775bcec509bc17d843c00149ce043bf2c475acd5eed5007e86","abstract_canon_sha256":"05096f65a1b154813a628f33134946a5670de6901c8694e7337cd86f4fcfc98f"},"schema_version":"1.0"},"canonical_sha256":"941f75e7cfacffa53ca6a5835bbc324bd62899e7fb29bdd0fa4d028601e1458d","source":{"kind":"arxiv","id":"1708.02973","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02973","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02973v2","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02973","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"pith_short_12","alias_value":"SQPXLZ6PVT72","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SQPXLZ6PVT72KPFG","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SQPXLZ6P","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SQPXLZ6PVT72KPFGUWBVXPBSJP","target":"record","payload":{"canonical_record":{"source":{"id":"1708.02973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-09T19:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"b3d2376835a30c775bcec509bc17d843c00149ce043bf2c475acd5eed5007e86","abstract_canon_sha256":"05096f65a1b154813a628f33134946a5670de6901c8694e7337cd86f4fcfc98f"},"schema_version":"1.0"},"canonical_sha256":"941f75e7cfacffa53ca6a5835bbc324bd62899e7fb29bdd0fa4d028601e1458d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:13.504540Z","signature_b64":"dFrJfY00GenaB8BneGwH0/radW+lmCPp4WSboSGZkiftPuz+1Y35sBFXC7dAUMfZqOO4pDRBk4t5Rt8LbCIoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"941f75e7cfacffa53ca6a5835bbc324bd62899e7fb29bdd0fa4d028601e1458d","last_reissued_at":"2026-05-18T00:35:13.503931Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:13.503931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.02973","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":"2026-05-18T00:35:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxskEUGkaIXMQ4YxGXAt1Fb+2poBF9hzaA6atg2yEhhpEjxLNvdpbSqAqpeUWApirIVoisH732Urm+IJPbA/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:07:01.599387Z"},"content_sha256":"7dde2e8269daa98db51e2f37ce3abe6dbe239af27388a021cee03753665d9de7","schema_version":"1.0","event_id":"sha256:7dde2e8269daa98db51e2f37ce3abe6dbe239af27388a021cee03753665d9de7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SQPXLZ6PVT72KPFGUWBVXPBSJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Policies for Adaptive Tracking with Deep Feature Cascades","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Huang, Deva Ramanan, Simon Lucey","submitted_at":"2017-08-09T19:09:11Z","abstract_excerpt":"Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a high-end GPU. In this paper, we learn to improve the speed of deep trackers without losing accuracy. Our fundamental insight is to take an adaptive approach, where easy frames are processed with cheap features (such as pixel values), while challenging frames are processed with invariant but expensive deep features. We formulate the adaptive tracking problem as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02973","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":"2026-05-18T00:35:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxUNE8cBEN6hh5HdrVUOGApy0TKxyRSNs9mxAbTaf9vOkaO03qPaquOVvAQBV4nEMeeeZ2Qpb4VmcAkJAuGbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:07:01.600484Z"},"content_sha256":"7e01a40b57508b5f11806d9219db570f876573e79906ae03723896758cf6c0c5","schema_version":"1.0","event_id":"sha256:7e01a40b57508b5f11806d9219db570f876573e79906ae03723896758cf6c0c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP/bundle.json","state_url":"https://pith.science/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP/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":"2026-08-16T20:07:01Z","links":{"resolver":"https://pith.science/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP","bundle":"https://pith.science/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP/bundle.json","state":"https://pith.science/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQPXLZ6PVT72KPFGUWBVXPBSJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SQPXLZ6PVT72KPFGUWBVXPBSJP","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":"05096f65a1b154813a628f33134946a5670de6901c8694e7337cd86f4fcfc98f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-09T19:09:11Z","title_canon_sha256":"b3d2376835a30c775bcec509bc17d843c00149ce043bf2c475acd5eed5007e86"},"schema_version":"1.0","source":{"id":"1708.02973","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02973","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02973v2","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02973","created_at":"2026-05-18T00:35:13Z"},{"alias_kind":"pith_short_12","alias_value":"SQPXLZ6PVT72","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SQPXLZ6PVT72KPFG","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SQPXLZ6P","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:7e01a40b57508b5f11806d9219db570f876573e79906ae03723896758cf6c0c5","target":"graph","created_at":"2026-05-18T00:35:13Z","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":"Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a high-end GPU. In this paper, we learn to improve the speed of deep trackers without losing accuracy. Our fundamental insight is to take an adaptive approach, where easy frames are processed with cheap features (such as pixel values), while challenging frames are processed with invariant but expensive deep features. We formulate the adaptive tracking problem as ","authors_text":"Chen Huang, Deva Ramanan, Simon Lucey","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-09T19:09:11Z","title":"Learning Policies for Adaptive Tracking with Deep Feature Cascades"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02973","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":"sha256:7dde2e8269daa98db51e2f37ce3abe6dbe239af27388a021cee03753665d9de7","target":"record","created_at":"2026-05-18T00:35:13Z","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":"05096f65a1b154813a628f33134946a5670de6901c8694e7337cd86f4fcfc98f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-09T19:09:11Z","title_canon_sha256":"b3d2376835a30c775bcec509bc17d843c00149ce043bf2c475acd5eed5007e86"},"schema_version":"1.0","source":{"id":"1708.02973","kind":"arxiv","version":2}},"canonical_sha256":"941f75e7cfacffa53ca6a5835bbc324bd62899e7fb29bdd0fa4d028601e1458d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"941f75e7cfacffa53ca6a5835bbc324bd62899e7fb29bdd0fa4d028601e1458d","first_computed_at":"2026-05-18T00:35:13.503931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:13.503931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFrJfY00GenaB8BneGwH0/radW+lmCPp4WSboSGZkiftPuz+1Y35sBFXC7dAUMfZqOO4pDRBk4t5Rt8LbCIoAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:13.504540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.02973","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dde2e8269daa98db51e2f37ce3abe6dbe239af27388a021cee03753665d9de7","sha256:7e01a40b57508b5f11806d9219db570f876573e79906ae03723896758cf6c0c5"],"state_sha256":"25057d7709e7871b1278f39f4162cdfec63e52c6ee7d1215bd72883564c3e089"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/YGejrxUBNjI5ga0htQ63SbS/rhOInAvEdIO0u0hMha0ZFpOjTiesN44dQ3h5lCm2kqM/6LUIb1KkLcK/B4Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:07:01.605370Z","bundle_sha256":"1cd945011d6f2b196f8e640d34908c746d79e1920304e423e24fbb05268b175a"}}