{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:263EB5LERUCCESI3SDLEDSAB6V","short_pith_number":"pith:263EB5LE","schema_version":"1.0","canonical_sha256":"d7b640f5648d0422491b90d641c801f547139e4b4f73e3bd03aedc06265687e3","source":{"kind":"arxiv","id":"1709.03655","version":2},"attestation_state":"computed","paper":{"title":"Learning Gating ConvNet for Two-Stream based Methods in Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiagang Zhu, Wei Zou, Zheng Zhu","submitted_at":"2017-09-12T02:09:04Z","abstract_excerpt":"For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs trial and error on the validation set. In order to enhance the adaptability of two-stream ConvNets and improve its performance, an end-to-end trainable gated fusion method, namely gating ConvNet, for the two-stream ConvNets is proposed in this paper based on the MoE (Mixture of Experts) theory. The gating ConvNet takes the combination of feature maps from the "},"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":"1709.03655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-12T02:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"ec29ab152c33d96bf72096c1f4f853334160a68631d7b62d2fbecac17cfee31d","abstract_canon_sha256":"cb3b31429499a3fd7befabe4651fb38254cf38fa2336607bcafd3eed03a80688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:15.812256Z","signature_b64":"8GUuUnV4zntSsfWx8CxSgupBZ81B53CqubL7m6LPwJzM3K4j2WwwGOS70xYtdtxdlcC/Usml1md0lU0N93MrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7b640f5648d0422491b90d641c801f547139e4b4f73e3bd03aedc06265687e3","last_reissued_at":"2026-05-18T00:35:15.811722Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:15.811722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Gating ConvNet for Two-Stream based Methods in Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiagang Zhu, Wei Zou, Zheng Zhu","submitted_at":"2017-09-12T02:09:04Z","abstract_excerpt":"For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs trial and error on the validation set. In order to enhance the adaptability of two-stream ConvNets and improve its performance, an end-to-end trainable gated fusion method, namely gating ConvNet, for the two-stream ConvNets is proposed in this paper based on the MoE (Mixture of Experts) theory. The gating ConvNet takes the combination of feature maps from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03655","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":"1709.03655","created_at":"2026-05-18T00:35:15.811794+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03655v2","created_at":"2026-05-18T00:35:15.811794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03655","created_at":"2026-05-18T00:35:15.811794+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/263EB5LERUCCESI3SDLEDSAB6V","json":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V.json","graph_json":"https://pith.science/api/pith-number/263EB5LERUCCESI3SDLEDSAB6V/graph.json","events_json":"https://pith.science/api/pith-number/263EB5LERUCCESI3SDLEDSAB6V/events.json","paper":"https://pith.science/paper/263EB5LE"},"agent_actions":{"view_html":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V","download_json":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V.json","view_paper":"https://pith.science/paper/263EB5LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03655&json=true","fetch_graph":"https://pith.science/api/pith-number/263EB5LERUCCESI3SDLEDSAB6V/graph.json","fetch_events":"https://pith.science/api/pith-number/263EB5LERUCCESI3SDLEDSAB6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V/action/storage_attestation","attest_author":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V/action/author_attestation","sign_citation":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V/action/citation_signature","submit_replication":"https://pith.science/pith/263EB5LERUCCESI3SDLEDSAB6V/action/replication_record"}},"created_at":"2026-05-18T00:35:15.811794+00:00","updated_at":"2026-05-18T00:35:15.811794+00:00"}