{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OFQLECSGMJY3RL6LVBHD7GS3LF","short_pith_number":"pith:OFQLECSG","schema_version":"1.0","canonical_sha256":"7160b20a466271b8afcba84e3f9a5b597d717a1a38228784de616a12bd647468","source":{"kind":"arxiv","id":"1701.08936","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Visual Object Tracking in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Zhang, Hamid Maei, Xin Wang, Yuan-Fang Wang","submitted_at":"2017-01-31T07:48:56Z","abstract_excerpt":"In this paper we introduce a fully end-to-end approach for visual tracking in videos that learns to predict the bounding box locations of a target object at every frame. An important insight is that the tracking problem can be considered as a sequential decision-making process and historical semantics encode highly relevant information for future decisions. Based on this intuition, we formulate our model as a recurrent convolutional neural network agent that interacts with a video overtime, and our model can be trained with reinforcement learning (RL) algorithms to learn good tracking policies"},"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":"1701.08936","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-31T07:48:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37c1ec6481b76402a7dabe3b64b03cfe14f4ed2a7ec6981288a86d671e0aca47","abstract_canon_sha256":"a5d10a65fc08abcbd6b28acf5b31552bd2526ffa3d18e1749f901f2abe8618aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:37.743766Z","signature_b64":"eRDzg7tGtWRXMunVFbdWz6M0L8dNTVy2AimmAj8cg/EgWcOktxupG7mPV6cOHUx2uPHz7YyuNIIa+RKV5R3DDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7160b20a466271b8afcba84e3f9a5b597d717a1a38228784de616a12bd647468","last_reissued_at":"2026-05-18T00:46:37.743309Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:37.743309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Visual Object Tracking in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da Zhang, Hamid Maei, Xin Wang, Yuan-Fang Wang","submitted_at":"2017-01-31T07:48:56Z","abstract_excerpt":"In this paper we introduce a fully end-to-end approach for visual tracking in videos that learns to predict the bounding box locations of a target object at every frame. An important insight is that the tracking problem can be considered as a sequential decision-making process and historical semantics encode highly relevant information for future decisions. Based on this intuition, we formulate our model as a recurrent convolutional neural network agent that interacts with a video overtime, and our model can be trained with reinforcement learning (RL) algorithms to learn good tracking policies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.08936","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1701.08936","created_at":"2026-05-18T00:46:37.743388+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.08936v2","created_at":"2026-05-18T00:46:37.743388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.08936","created_at":"2026-05-18T00:46:37.743388+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFQLECSGMJY3","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFQLECSGMJY3RL6L","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFQLECSG","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17138","citing_title":"RAP: Runtime Adaptive Pruning for LLM Inference","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF","json":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF.json","graph_json":"https://pith.science/api/pith-number/OFQLECSGMJY3RL6LVBHD7GS3LF/graph.json","events_json":"https://pith.science/api/pith-number/OFQLECSGMJY3RL6LVBHD7GS3LF/events.json","paper":"https://pith.science/paper/OFQLECSG"},"agent_actions":{"view_html":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF","download_json":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF.json","view_paper":"https://pith.science/paper/OFQLECSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.08936&json=true","fetch_graph":"https://pith.science/api/pith-number/OFQLECSGMJY3RL6LVBHD7GS3LF/graph.json","fetch_events":"https://pith.science/api/pith-number/OFQLECSGMJY3RL6LVBHD7GS3LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF/action/storage_attestation","attest_author":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF/action/author_attestation","sign_citation":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF/action/citation_signature","submit_replication":"https://pith.science/pith/OFQLECSGMJY3RL6LVBHD7GS3LF/action/replication_record"}},"created_at":"2026-05-18T00:46:37.743388+00:00","updated_at":"2026-05-18T00:46:37.743388+00:00"}