{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:EEDRWCGSYVJREUW2H4LHQAA33M","short_pith_number":"pith:EEDRWCGS","schema_version":"1.0","canonical_sha256":"21071b08d2c5531252da3f1678001bdb1e81604d06f3eab3210020c62a308445","source":{"kind":"arxiv","id":"1701.06659","version":1},"attestation_state":"computed","paper":{"title":"DSSD : Deconvolutional Single Shot Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander C. Berg, Ambrish Tyagi, Ananth Ranga, Cheng-Yang Fu, Wei Liu","submitted_at":"2017-01-23T22:33:35Z","abstract_excerpt":"The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection framework (SSD[18]). We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects, calling our resulting system DSSD for deconvolutional single shot detector. While these two contributions are easily described at a high-level, a naive implementation"},"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":"1701.06659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-23T22:33:35Z","cross_cats_sorted":[],"title_canon_sha256":"5d485d8ad5fc8febb3290940d49a5bd5e4b0ead20482b2fc5e86f1264e24bbcc","abstract_canon_sha256":"15dc38d0c4e11a244ad78682ae3dd69039c41e494c8bc15d403e367750527556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:12.431348Z","signature_b64":"ddg4fOoHOOyuZNKW7jIfbkk2H2oJjdO5O3yfEPAOad4BcMGDlrskZosCxIm+OJZkfsazu+E+mLJFS088AA/SBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21071b08d2c5531252da3f1678001bdb1e81604d06f3eab3210020c62a308445","last_reissued_at":"2026-05-18T00:52:12.430971Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:12.430971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSSD : Deconvolutional Single Shot Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander C. Berg, Ambrish Tyagi, Ananth Ranga, Cheng-Yang Fu, Wei Liu","submitted_at":"2017-01-23T22:33:35Z","abstract_excerpt":"The main contribution of this paper is an approach for introducing additional context into state-of-the-art general object detection. To achieve this we first combine a state-of-the-art classifier (Residual-101[14]) with a fast detection framework (SSD[18]). We then augment SSD+Residual-101 with deconvolution layers to introduce additional large-scale context in object detection and improve accuracy, especially for small objects, calling our resulting system DSSD for deconvolutional single shot detector. While these two contributions are easily described at a high-level, a naive implementation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.06659","kind":"arxiv","version":1},"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":"1701.06659","created_at":"2026-05-18T00:52:12.431022+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.06659v1","created_at":"2026-05-18T00:52:12.431022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.06659","created_at":"2026-05-18T00:52:12.431022+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEDRWCGSYVJR","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEDRWCGSYVJREUW2","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEDRWCGS","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1907.03465","citing_title":"A unified neural network for object detection, multiple object tracking and vehicle re-identification","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06067","citing_title":"ALFA: Agglomerative Late Fusion Algorithm for Object Detection","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06881","citing_title":"Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10310","citing_title":"Towards Adversarially Robust Object Detection","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11830","citing_title":"Reprojection R-CNN: A Fast and Accurate Object Detector for 360{\\deg} Images","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21186","citing_title":"SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1804.02767","citing_title":"YOLOv3: An Incremental Improvement","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M","json":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M.json","graph_json":"https://pith.science/api/pith-number/EEDRWCGSYVJREUW2H4LHQAA33M/graph.json","events_json":"https://pith.science/api/pith-number/EEDRWCGSYVJREUW2H4LHQAA33M/events.json","paper":"https://pith.science/paper/EEDRWCGS"},"agent_actions":{"view_html":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M","download_json":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M.json","view_paper":"https://pith.science/paper/EEDRWCGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.06659&json=true","fetch_graph":"https://pith.science/api/pith-number/EEDRWCGSYVJREUW2H4LHQAA33M/graph.json","fetch_events":"https://pith.science/api/pith-number/EEDRWCGSYVJREUW2H4LHQAA33M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M/action/storage_attestation","attest_author":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M/action/author_attestation","sign_citation":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M/action/citation_signature","submit_replication":"https://pith.science/pith/EEDRWCGSYVJREUW2H4LHQAA33M/action/replication_record"}},"created_at":"2026-05-18T00:52:12.431022+00:00","updated_at":"2026-05-18T00:52:12.431022+00:00"}