{
  "abstract": "With rising performance demands for autonomous driving perception systems, bird’s-eye-view (BEV) perception that combines heterogeneous sensor data and temporal information has become a key research focus. Recent studies have advanced either multimodal temporal detection through BEV-level feature aggregation or sparse object-centric temporal modeling. However, integrating these two directions while preserving modality-specific temporal states remains less explored for LiDAR-camera detection. In this work, we present TempoCross, a 3D detection method based on instance-aware sparse representations for multimodal temporal fusion. TempoCross encodes features from different timestamps and sensor modalities in a unified instance space, enabling adaptive extraction of critical target information from modality- and time-specific states. Initially, both branches perform a preliminary cross-modal fusion to generate queries for the current frame. In the motion compensation module, a hybrid motion modeling strategy reduces alignment discrepancies between historical and current instances caused by complex object motion. This strategy combines explicit rigid-body transformations with implicit learnable deformation residuals, improving both accuracy and robustness in cross-frame instance association. Next, temporal-aware enhancement integrates the initial queries and current-frame features with motion-compensated historical instances. Finally, a lightweight cross-attention fuses current and historical instances from both branches. This formulation reduces the reliance on repeatedly propagating full-scene fused BEV features and concentrates temporal interaction on target-related instance states. On the nuScenes test set, TempoCross achieves 74.1% mAP and 75.7% NDS, outperforming mainstream baseline detectors. The results support the effectiveness of combining LiDAR-camera fusion with instance-aware sparse temporal modeling.",
  "abstract_shown": true,
  "affiliations": [
    "School of Geomatics, Liaoning Technical University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Changqiang Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuanqi Liang"
    },
    {
      "affs": [
        0
      ],
      "name": "Bolin Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Xin Sui"
    },
    {
      "affs": [
        0
      ],
      "name": "Jiaxin Gao"
    },
    {
      "affs": [
        0
      ],
      "name": "Song Gao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1smr6kw93h58n.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-62822-7",
  "fulltext_url": "https://doi.org/10.1038/s41598-026-62822-7",
  "id": "1smr6kw93h58n",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://doi.org/10.1038/s41598-026-62822-7",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "Q"
    ],
    [
      "lcc",
      "R"
    ],
    [
      "openalex",
      "2203|Autonomous Vehicle Technology and Safety"
    ]
  ],
  "openalex": "W7169659711",
  "pdf_url": "https://www.nature.com/articles/s41598-026-62822-7_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/1smr6kw93h58n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:45:54Z",
      "native_id": "eeb8040d57164667a47e9a51336c2c45",
      "source": "doaj",
      "url": "https://doi.org/10.1038/s41598-026-62822-7"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R",
      "subfield": "general"
    }
  ],
  "title": "TempoCross: instance-aware sparse representation for multimodal temporal fusion in 3D detection",
  "title_text": "TempoCross: instance-aware sparse representation for multimodal temporal fusion in 3D detection",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:45:54Z",
  "url": "https://research.draconitic.com/paper/1smr6kw93h58n",
  "venue": "Scientific Reports",
  "versions": []
}