{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4BGVGXDI2IOYBG5WAEWHQTYMN","short_pith_number":"pith:B4BGVGXD","schema_version":"1.0","canonical_sha256":"0f026a9ae34690ec04ddb00963c278634c8958ff0a6c4d7b7f8d989921ed24e7","source":{"kind":"arxiv","id":"2410.03290","version":2},"attestation_state":"computed","paper":{"title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haibo Wang, Lifu Huang, Qifan Wang, Shizhe Diao, Weifeng Ge, Yixin Cao, Yu Cheng, Yufan Zhou, Zhiyang Xu","submitted_at":"2024-10-04T10:04:37Z","abstract_excerpt":"Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding. In this paper, we introduce Grounded-VideoLLM, a novel Video-LLM adept at perceiving and reasoning over specific video moments in a fine-grained manner. We identify that current Video-LLMs have limitations for fine-grained video understanding since they lack effective temporal modeling and timestamp representation. In light of this, we sharpen our model by incorporating (1) an additional temporal stream to encode "},"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":"2410.03290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T10:04:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3cc392b86ac2332e8bc7687790c027d01a7536c39ba5d78e1565f72f09abae00","abstract_canon_sha256":"3126163f8e8a3ca103e17e998b24f026034116ae436445b6495cfb289a1e120c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:50.018280Z","signature_b64":"UumQ0MWbEFwIIDFw1nYW/rAVDxrM6B6xWD8pdcZY+2RQmdpsRn/vujNR3rRVBvBSHqv48igfiuqXL2KQhGbYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f026a9ae34690ec04ddb00963c278634c8958ff0a6c4d7b7f8d989921ed24e7","last_reissued_at":"2026-07-05T11:56:50.017799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:50.017799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haibo Wang, Lifu Huang, Qifan Wang, Shizhe Diao, Weifeng Ge, Yixin Cao, Yu Cheng, Yufan Zhou, Zhiyang Xu","submitted_at":"2024-10-04T10:04:37Z","abstract_excerpt":"Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding. In this paper, we introduce Grounded-VideoLLM, a novel Video-LLM adept at perceiving and reasoning over specific video moments in a fine-grained manner. We identify that current Video-LLMs have limitations for fine-grained video understanding since they lack effective temporal modeling and timestamp representation. In light of this, we sharpen our model by incorporating (1) an additional temporal stream to encode "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03290","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.03290/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2410.03290","created_at":"2026-07-05T11:56:50.017858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03290v2","created_at":"2026-07-05T11:56:50.017858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03290","created_at":"2026-07-05T11:56:50.017858+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4BGVGXDI2IO","created_at":"2026-07-05T11:56:50.017858+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4BGVGXDI2IOYBG5","created_at":"2026-07-05T11:56:50.017858+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4BGVGXD","created_at":"2026-07-05T11:56:50.017858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19706","citing_title":"NEST: Narrative Event Structures in Time for Long Video Understanding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17279","citing_title":"Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09181","citing_title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14733","citing_title":"Video-Zero: Self-Evolution Video Understanding","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25979","citing_title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28229","citing_title":"VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21954","citing_title":"MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12386","citing_title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06673","citing_title":"Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02994","citing_title":"Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13803","citing_title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03631","citing_title":"Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08966","citing_title":"How Should Video LLMs Output Time? An Analysis of Efficient Temporal Grounding Paradigms","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN","json":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN.json","graph_json":"https://pith.science/api/pith-number/B4BGVGXDI2IOYBG5WAEWHQTYMN/graph.json","events_json":"https://pith.science/api/pith-number/B4BGVGXDI2IOYBG5WAEWHQTYMN/events.json","paper":"https://pith.science/paper/B4BGVGXD"},"agent_actions":{"view_html":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN","download_json":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN.json","view_paper":"https://pith.science/paper/B4BGVGXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03290&json=true","fetch_graph":"https://pith.science/api/pith-number/B4BGVGXDI2IOYBG5WAEWHQTYMN/graph.json","fetch_events":"https://pith.science/api/pith-number/B4BGVGXDI2IOYBG5WAEWHQTYMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN/action/storage_attestation","attest_author":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN/action/author_attestation","sign_citation":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN/action/citation_signature","submit_replication":"https://pith.science/pith/B4BGVGXDI2IOYBG5WAEWHQTYMN/action/replication_record"}},"created_at":"2026-07-05T11:56:50.017858+00:00","updated_at":"2026-07-05T11:56:50.017858+00:00"}