{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WR74KRM3LLNY65HWUJ6GK76KJ5","short_pith_number":"pith:WR74KRM3","schema_version":"1.0","canonical_sha256":"b47fc5459b5adb8f74f6a27c657fca4f7b69fa54dd973265b0a78afa084beff3","source":{"kind":"arxiv","id":"1705.10561","version":3},"attestation_state":"computed","paper":{"title":"End-to-end Active Object Tracking via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangwei Zhong, Peng Sun, Tong Zhang, Wei Liu, Wenhan Luo, Yizhou Wang","submitted_at":"2017-05-30T11:44:50Z","abstract_excerpt":"We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly. It also incurs many human efforts for labeling and many expensive trial-and-errors in realworld. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-toaction predictio"},"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":"1705.10561","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-05-30T11:44:50Z","cross_cats_sorted":[],"title_canon_sha256":"81135855d2f91ff45a61cb513623467bc0fed6022cae215d13cdee1e928a913a","abstract_canon_sha256":"62e858131f8a5dab1e9257905c65103e0d900f84dc877382b62a27265065512f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:28.961375Z","signature_b64":"C0k68T2ntT/z8++p9mOePTNwvs4VAvDFAECBiKVdvjKz9yRgZ6VpChLE2Li78e7x6i4EZrYXR2DTvfEEevMbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47fc5459b5adb8f74f6a27c657fca4f7b69fa54dd973265b0a78afa084beff3","last_reissued_at":"2026-05-18T00:14:28.960694Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:28.960694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Active Object Tracking via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangwei Zhong, Peng Sun, Tong Zhang, Wei Liu, Wenhan Luo, Yizhou Wang","submitted_at":"2017-05-30T11:44:50Z","abstract_excerpt":"We study active object tracking, where a tracker takes as input the visual observation (i.e., frame sequence) and produces the camera control signal (e.g., move forward, turn left, etc.). Conventional methods tackle the tracking and the camera control separately, which is challenging to tune jointly. It also incurs many human efforts for labeling and many expensive trial-and-errors in realworld. To address these issues, we propose, in this paper, an end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-toaction predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10561","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.10561","created_at":"2026-05-18T00:14:28.960797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.10561v3","created_at":"2026-05-18T00:14:28.960797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10561","created_at":"2026-05-18T00:14:28.960797+00:00"},{"alias_kind":"pith_short_12","alias_value":"WR74KRM3LLNY","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WR74KRM3LLNY65HW","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WR74KRM3","created_at":"2026-05-18T12:31:53.515858+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/WR74KRM3LLNY65HWUJ6GK76KJ5","json":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5.json","graph_json":"https://pith.science/api/pith-number/WR74KRM3LLNY65HWUJ6GK76KJ5/graph.json","events_json":"https://pith.science/api/pith-number/WR74KRM3LLNY65HWUJ6GK76KJ5/events.json","paper":"https://pith.science/paper/WR74KRM3"},"agent_actions":{"view_html":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5","download_json":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5.json","view_paper":"https://pith.science/paper/WR74KRM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.10561&json=true","fetch_graph":"https://pith.science/api/pith-number/WR74KRM3LLNY65HWUJ6GK76KJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/WR74KRM3LLNY65HWUJ6GK76KJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5/action/storage_attestation","attest_author":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5/action/author_attestation","sign_citation":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5/action/citation_signature","submit_replication":"https://pith.science/pith/WR74KRM3LLNY65HWUJ6GK76KJ5/action/replication_record"}},"created_at":"2026-05-18T00:14:28.960797+00:00","updated_at":"2026-05-18T00:14:28.960797+00:00"}