{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RTSTVKUJVERGA7RPLFCYBQDFHR","short_pith_number":"pith:RTSTVKUJ","schema_version":"1.0","canonical_sha256":"8ce53aaa89a922607e2f594580c0653c5f747735e02562a7c8de6acd1b6f0286","source":{"kind":"arxiv","id":"1704.00675","version":3},"attestation_state":"computed","paper":{"title":"The 2017 DAVIS Challenge on Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The 2017 DAVIS Challenge introduces a dataset, benchmark, and competition to advance video object segmentation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Sorkine-Hornung, Federico Perazzi, Jordi Pont-Tuset, Luc Van Gool, Pablo Arbel\\'aez, Sergi Caelles","submitted_at":"2017-04-03T16:44:46Z","abstract_excerpt":"We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation. Following the footsteps of other successful initiatives, such as ILSVRC and PASCAL VOC, which established the avenue of research in the fields of scene classification and semantic segmentation, the DAVIS Challenge comprises a dataset, an evaluation methodology, and a public competition with a dedicated workshop co-located with CVPR 2017. The DAVIS Challenge follows up on the recent publication of DAVIS (Densely-Annotated"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"1704.00675","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-03T16:44:46Z","cross_cats_sorted":[],"title_canon_sha256":"ca41308a33c013addfbb5d5e358611e8da14cc20d7f5f47a53f1852bbf7fdb19","abstract_canon_sha256":"5d12ef75ea0da2af8b1acf5ce71b23d061bbcd2f5f62f5b2ae236acfb544184f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:32:29.313591Z","signature_b64":"tavLWRklk4YNrpbs461NXp3WfZbjudoV9AVJHlbcWWvf5zq2Xp2S/fNBTpHgkQm6ZRXCzEDV2GeChzqzzgF9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ce53aaa89a922607e2f594580c0653c5f747735e02562a7c8de6acd1b6f0286","last_reissued_at":"2026-05-18T03:32:29.312678Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:32:29.312678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The 2017 DAVIS Challenge on Video Object Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The 2017 DAVIS Challenge introduces a dataset, benchmark, and competition to advance video object segmentation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Sorkine-Hornung, Federico Perazzi, Jordi Pont-Tuset, Luc Van Gool, Pablo Arbel\\'aez, Sergi Caelles","submitted_at":"2017-04-03T16:44:46Z","abstract_excerpt":"We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation. Following the footsteps of other successful initiatives, such as ILSVRC and PASCAL VOC, which established the avenue of research in the fields of scene classification and semantic segmentation, the DAVIS Challenge comprises a dataset, an evaluation methodology, and a public competition with a dedicated workshop co-located with CVPR 2017. The DAVIS Challenge follows up on the recent publication of DAVIS (Densely-Annotated"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The chosen videos and metrics sufficiently represent the diversity and difficulty of real-world video object segmentation scenarios.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The 2017 DAVIS Challenge establishes a public dataset, evaluation metrics, and competition for video object segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The 2017 DAVIS Challenge introduces a dataset, benchmark, and competition to advance video object segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2ca4982a192b2313e7eda58039503d72d7b134b257eeba23b5df91f0e26c4dc9"},"source":{"id":"1704.00675","kind":"arxiv","version":3},"verdict":{"id":"27b946f1-b766-40e6-9f58-fe1e6a105798","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T23:50:24.954342Z","strongest_claim":"We present the 2017 DAVIS Challenge on Video Object Segmentation, a public dataset, benchmark, and competition specifically designed for the task of video object segmentation.","one_line_summary":"The 2017 DAVIS Challenge establishes a public dataset, evaluation metrics, and competition for video object segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The chosen videos and metrics sufficiently represent the diversity and difficulty of real-world video object segmentation scenarios.","pith_extraction_headline":"The 2017 DAVIS Challenge introduces a dataset, benchmark, and competition to advance video object segmentation."},"references":{"count":17,"sample":[{"doi":"","year":2015,"title":"ImageNet Large Scale Visual Recognition Challenge","work_id":"552fef66-9973-48f7-b1d7-ccabbd78b649","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","work_id":"0f11c9db-9e95-47e1-9465-913772fb3c30","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"A benchmark dataset and evaluation methodology for video object segmentation","work_id":"d5bf746b-73c7-440c-904a-c4fead850a2c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Microsoft COCO: Common Objects in Context","work_id":"ceb3505c-acbf-4176-98a7-d5b9c9cebb51","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"One-shot video object segmentation","work_id":"488f1fa4-558c-4104-b88d-1af65801e27c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"79809375886052f5da6340aa0ab3fb0c1513b4f604e119ee9e7f83bb8f569106","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"95cb96821a914bf28aa07ad2bf3d07fcbbc3092dc45194e9926a2f392f42404c"},"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":"1704.00675","created_at":"2026-05-18T03:32:29.312794+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00675v3","created_at":"2026-05-18T03:32:29.312794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00675","created_at":"2026-05-18T03:32:29.312794+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTSTVKUJVERG","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTSTVKUJVERGA7RP","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTSTVKUJ","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":49,"internal_anchor_count":49,"sample":[{"citing_arxiv_id":"1907.01203","citing_title":"Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23903","citing_title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06119","citing_title":"Understanding Deep Learning Techniques for Image Segmentation","ref_index":168,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08051","citing_title":"Self-supervised Training of Proposal-based Segmentation via Background Prediction","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22818","citing_title":"MotiMotion: Motion-Controlled Video Generation with Visual Reasoning","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2510.18822","citing_title":"SAM 2++: Tracking Anything at Any Granularity","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17472","citing_title":"Weighted Reverse Convolution for Feature Upsampling","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17584","citing_title":"VVitCutLER: Towards Unsupervised Object Detection and Segmentation in Videos","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17472","citing_title":"Weighted Reverse Convolution for Feature Upsampling","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17543","citing_title":"HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19786","citing_title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15533","citing_title":"Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2507.14137","citing_title":"Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2307.10373","citing_title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2511.20886","citing_title":"V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13684","citing_title":"Recurrent Video Masked Autoencoders","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2512.17012","citing_title":"4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2512.22046","citing_title":"Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2601.01955","citing_title":"MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2601.08831","citing_title":"3AM: 3egment Anything with Geometric Consistency in Videos","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2104.14294","citing_title":"Emerging Properties in Self-Supervised Vision Transformers","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR","json":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR.json","graph_json":"https://pith.science/api/pith-number/RTSTVKUJVERGA7RPLFCYBQDFHR/graph.json","events_json":"https://pith.science/api/pith-number/RTSTVKUJVERGA7RPLFCYBQDFHR/events.json","paper":"https://pith.science/paper/RTSTVKUJ"},"agent_actions":{"view_html":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR","download_json":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR.json","view_paper":"https://pith.science/paper/RTSTVKUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00675&json=true","fetch_graph":"https://pith.science/api/pith-number/RTSTVKUJVERGA7RPLFCYBQDFHR/graph.json","fetch_events":"https://pith.science/api/pith-number/RTSTVKUJVERGA7RPLFCYBQDFHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR/action/storage_attestation","attest_author":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR/action/author_attestation","sign_citation":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR/action/citation_signature","submit_replication":"https://pith.science/pith/RTSTVKUJVERGA7RPLFCYBQDFHR/action/replication_record"}},"created_at":"2026-05-18T03:32:29.312794+00:00","updated_at":"2026-05-18T03:32:29.312794+00:00"}