Pith. sign in

REVIEW 4 major objections 4 minor 33 references

V2X collaboration lifts 3D detection and tracking by up to 20 percent

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-03 13:59 UTC pith:X22SQRBK

load-bearing objection No external baselines means the central claim is on faith; the architecture is a sensible combination but needs proper comparison before it can be taken seriously. the 4 major comments →

arxiv 2512.21831 v2 pith:X22SQRBK submitted 2025-12-26 cs.CV

End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration

Zhenwei Yang , Yibo Ai , Weidong Zhang This is my paper
classification cs.CV
keywords multimodal fusionV2X cooperative perceptionend-to-end trackingbird's-eye-view (BEV) representationdeformable cross-attention3D object detectionmulti-object trackingcommunication delay robustness
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper tries to prove that cooperative perception for autonomous driving can be unified into a single end-to-end network that does 3D detection and multi-object tracking at once, using both cameras and LiDAR from the ego vehicle and from other vehicles or roadside units. It claims that a shared bird's-eye-view representation, refined by two cascaded cross-attention layers, folds multi-view and multimodal features together so that they complement each other rather than redundantly add noise. The reported result is consistent improvement over single-view and single-modality baselines on real and simulated V2X benchmarks, with relative gains up to 15-20% and with the advantage surviving one or two frames of communication delay. If true, this matters because it suggests cooperative perception does not need modular tracking-by-detection pipelines, and that latency alone is not a reason to abandon fine-grained feature fusion.

Core claim

On the paper's own terms, XET-V2X establishes that multi-view multimodal cooperative perception can be performed end-to-end: a single network ingests image and point-cloud features from ego and remote agents, aligns them in a shared bird's-eye-view space, and directly outputs detected objects with persistent track identities. The claimed mechanism is a dual-layer spatial cross-attention built on multi-scale deformable attention, where image features from all viewpoints are fused first to form semantically updated queries, and point-cloud features are then fused under the guidance of those queries. This ordering is reported as consistently slightly better than the reverse. The paper reports t

What carries the argument

The load-bearing piece is the dual-layer V2X spatial cross-attention module built from multi-scale deformable attention (MSDeformAttn). Each bird's-eye-view query samples a small set of deformable points from multi-scale feature maps instead of attending densely, which keeps cost low while allowing the network to compensate for spatial misalignment between viewpoints. The first attention layer aggregates image features from ego and remote agents to produce an image-enhanced set of BEV queries; the second layer uses those queries to aggregate point-cloud features. A validity mask excludes reference points that fall outside a remote agent's sensing range, preventing empty features from being m

Load-bearing premise

The whole approach assumes that every agent's camera and LiDAR are internally synchronized, that calibration parameters are accurate, and that the V2X channel only delays complete features by whole frames—never dropping or corrupting them. If any of those assumptions fails in a real deployment, the cross-attention will mix features from inconsistent spatiotemporal positions and the reported robustness may vanish.

What would settle it

A concrete test: take the same model and feed it the real-world V2X benchmark at zero delay but randomly drop 10% and 20% of the cooperative feature maps, or add ±0.5 frame of timestamp jitter to the remote agent's features. If mAP/AMOTA fall by more than, say, 5 points while the baseline models fall less, then the delay robustness is specific to clean whole-frame latency rather than to realistic lossy channels.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Cooperative multi-view features and multimodal fusion are additive: each contributes measurable mAP/AMOTA gains, and their combination does not saturate.
  • Delay robustness is structural: the deformable cross-attention alignment keeps working when cooperative features arrive one or two frames late.
  • Fusion order matters slightly: refining image features before point-cloud features yields the most stable gains across all benchmarks.
  • End-to-end tracking removes the separate association step, so identity consistency is learned jointly with detection; the paper reports lower tracking localization error alongside higher tracking accuracy.
  • The approach generalizes across a real vehicle-infrastructure dataset and two simulated V2V/V2I benchmarks, so the benefit is not an artifact of one data distribution.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Editorial inference: because the delay experiments only shift whole frames, the model's robustness to latency is shown only for loss-free, integer-frame delays; the behavior under packet loss, jitter, or partial feature corruption is untested and likely worse.
  • Editorial inference: the design implies that calibration accuracy and internal sensor synchronization are assumed; if those break, deformable sampling might absorb small misalignment but not large systematic drift. A test with deliberately perturbed extrinsics would map that boundary.
  • Editorial inference: the same dual-layer attention could be applied to other sensor modalities (e.g., radar or sonar) without changing the fusion logic, since the modality only enters through its feature map.
  • Editorial inference: the validity mask suggests the architecture scales to more agents relatively cheaply, but each additional agent adds sampling points, so fleet-size scaling curves are not established.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

4 major / 4 minor

Summary. The paper proposes XET-V2X, an end-to-end 3D detection and multi-object tracking framework for V2X cooperative perception. Each agent extracts point-cloud features with PointPillars/SECOND and image features with ResNet-101/FPN; remote agents transmit intermediate features to the ego vehicle, which applies two cascaded multi-scale deformable cross-attention layers (image-first, then LiDAR) to construct a shared BEV representation, followed by a MOTR-style query-based detection/tracking head. Experiments are reported on V2X-Seq-SPD and two V2X-Sim-derived subsets (V2X-Sim-V2V and V2X-Sim-V2I) under 0/1/2-frame communication delays. The main claimed results are consistent gains over six self-ablation baselines and, in the abstract, 'outperforming representative tracking-by-detection cooperative perception methods.'

Significance. If the empirical claims were fully supported, the framework would be a useful contribution: it integrates multiview, multimodal, and temporal modeling in one end-to-end architecture, uses feature-level transmission, and evaluates on both real and simulated V2X benchmarks. The paper also provides a clean ablation structure and reports detection and tracking metrics together. However, the current evidence does not support the headline claims: the quantitative comparison contains only variants of the proposed model, model selection is performed on the test benchmarks, no uncertainty/error bars are provided, and the delay-robustness analysis covers only integer frame delays rather than lossy channels. The architectural idea is plausible, but the experimental validation as presented is insufficient to establish state-of-the-art performance or the stated advantage over existing cooperative-perception methods.

major comments (4)
  1. [§4.2.1, Table 3; Abstract; §2] The abstract and contribution list claim that XET-V2X 'outperforms representative tracking-by-detection cooperative perception methods' and achieves 'state-of-the-art performance.' Table 3, however, contains only self-ablation baselines (CET-V, LET-V, XET-V, CET-V2X, LET-V2X, XET-V2X). No external method—not V2VNet, Where2Comm, F-Cooper, AttFuse, or any other cooperative-perception pipeline cited in §2—is compared quantitatively. The central value proposition is therefore unsupported by the evidence; this is a load-bearing gap, not a presentation issue.
  2. [§4.2.4, Table 4] The default fusion order (Image→Point) is selected by comparing mAP/AMOTA/AMOTP on the same test splits that are later used for the headline results in Table 3. The text states that the image-first order is 'adopted in the final model' based on its superior test performance. This is test-set model selection and makes the reported numbers optimistic. Model selection should be performed on a validation set, with the test set used only once, or an equivalent nested/hold-out protocol should be reported.
  3. [§3.1, §4.2.2, Table 3] The robustness claim is tested only for integer frame delays (0, 1, 2). Section 3.1 assumes that V2X transmission loses no features and merely delays them by whole frames; real channels also exhibit packet loss, jitter, and calibration drift. Since robustness under communication delays is a central contribution, the experiment should include lossy/asynchronous conditions (e.g., random frame drops, packet-loss rates) or the claim should be accordingly limited.
  4. [§4.1.3, Tables 3–4] All experiments appear to be single runs with no error bars, seed variation, or statistical significance testing. Some test sets are small (e.g., V2X-Sim-V2V has 1,200 test frames), and some reported differences between configurations are large. Without repeated runs or confidence intervals, it is not possible to assess whether the observed gains are stable or within noise. At minimum, the main comparisons and the fusion-order selection should be reported as mean±std over multiple seeds.
minor comments (4)
  1. [Abstract, §3.4, §5] The model name is inconsistently written as 'XET-V2X', 'XET-VIC', and 'XET-V2V' in several places (e.g., §3.4 'XET-VIC framework', §5 'XET-V2X/XET-V2V' and 'XET-VIC'). Please unify the terminology.
  2. [Abstract vs. Table 3] The abstract states 'up to 15-20% relative gains' over single-view or single-modal baselines, but Table 3 shows much larger relative gains, e.g., XET-V2X vs. XET-V on V2X-Sim-V2I mAP is a 108% relative improvement and on V2X-Seq-SPD roughly 62%. Clarify which comparison the abstract is reporting or correct the numbers.
  3. [Table 2] The checkmarks in Table 2 are difficult to read and seem misaligned with the column headers (e.g., CET-V appears to have checkmarks in the wrong columns). Please format the table so each model's properties are unambiguous.
  4. [§4.2.1] The sentence 'XET-VIC exceeds XET' is a typo; it should presumably read 'XET-V2X exceeds XET-V.' Similar typos appear in the section text and conclusion.

Circularity Check

0 steps flagged

No significant circularity: the reported gains are measured on external datasets against explicit baselines; the unsupported external-comparison claim is a support gap, not a circular reduction.

full rationale

XET-V2X is an empirical systems paper rather than a derivation chain. Equations (4)-(6) define the V2X cross-attention and fusion order, but no predicted quantity is derived from those equations by construction; the paper's quantitative claims are measurements in Tables 3-4. The single-view/single-modal baselines (CET-V, LET-V, XET-V, CET-V2X, LET-V2X) are explicitly defined in Sec. 4.1.4, and the evaluation uses external datasets (V2X-Seq-SPD, V2X-Sim). The fusion-order ablation in Sec. 4.2.4 is standard model selection: the paper states that 'image-first, point-cloud-second fusion order consistently achieves slightly better performance' and then adopts it; this is post-hoc selection based on the reported metric, not an a priori prediction fitted to data, so it does not constitute a circular reduction. The self-citations ([5] V2X-Seq, [10] LET-VIC) involve overlapping authors, but [5] is an external open dataset with independent annotations and [10] is cited only as related work; neither is used as the load-bearing proof that the method works. The abstract's claim of 'outperforming representative tracking-by-detection cooperative perception methods' and the contribution 'state-of-the-art performance' are not supported by Table 3, which contains only self-ablation rows and no external cooperative-perception baseline; this is a validation/reporting gap (a correctness concern), not a circular equation or a self-citation chain. Accordingly, no circular step can be exhibited under the required standard, and the circularity score is 0.

Axiom & Free-Parameter Ledger

1 free parameters · 3 axioms · 0 invented entities

The method rests on standard deep-learning components (PointPillars, ResNet, deformable attention, MOTR) and dataset-specific assumptions. No new physical entities are introduced. The only parameter explicitly fit to the benchmarks is the fusion order.

free parameters (1)
  • Fusion order (Image→Point vs Point→Image) = Image→Point
    Selected as final configuration based on best mAP/AMOTA on the three test benchmarks (Table 4). A discrete hyperparameter fitted to the target metrics; no separate validation set is mentioned.
axioms (3)
  • domain assumption Each agent's camera and LiDAR are internally synchronized so that multimodal data at the same index k share a timestamp.
    Stated in §3.1 'Temporal Modeling and Notation'. If false, the cross-modal attention in Eq. (4-6) fuses features from different instants.
  • domain assumption Accurate calibration parameters M^pc, M^img are provided for all agents, and V2X transmission is lossless, with only integer-frame delay.
    Stated in §3.1 Input Representation and §3.5. The model does not handle calibration error or packet loss; the delay-robustness experiment varies only delay.
  • domain assumption The union of all agents' ground-truth annotations restricted to the ego ROI (Eq. 2) is a complete and consistent supervision target.
    Assumed in §3.1. Annotation inconsistencies across agents and modalities would corrupt the loss.

pith-pipeline@v1.3.0-alltime-deepseek · 15546 in / 15611 out tokens · 141084 ms · 2026-08-03T13:59:40.569243+00:00 · methodology

0 comments
read the original abstract

Multiview cooperative perception and multimodal fusion are essential for reliable 3-D spatiotemporal understanding in autonomous driving, especially in cases with occlusions, limited viewpoints, and communication delays in vehicle-to-everything (V2X) scenarios. In this paper, Cross-modal End-to-End Tracking for V2X (XET-V2X), a multimodal fused end-to-end tracking framework for V2X collaboration that unifies multiview multimodal sensing within a shared spatiotemporal representation, is proposed. To efficiently align heterogeneous viewpoints and modalities, XET-V2X introduces a dual-layer spatial cross-attention module based on multiscale deformable attention. Multiview image features are aggregated to enhance semantic consistency, followed by point cloud fusion guided by the updated spatial queries, enabling effective cross-modal interaction while reducing computational overhead. Experiments based on the real-world V2X Sequential Perception Dataset (V2X-Seq-SPD) dataset and two simulated V2X-Sim-derived subsets, namely the vehicle-to-vehicle (V2X-Sim-V2V) and vehicle-to-infrastructure (V2X-Sim-V2I) subsets, demonstrate consistent improvements in detection and tracking performance under varying communication delays, with XET-V2X achieving up to 15-20% relative gains in mean average precision (mAP) and average multi-object tracking accuracy (AMOTA) over single-view or single-modal baselines, while also outperforming representative tracking-by-detection cooperative perception methods.

Figures

Figures reproduced from arXiv: 2512.21831 by Weidong Zhang, Yibo Ai, Zhenwei Yang.

Figure 1
Figure 1. Figure 1: V2X Cooperative Perception Diagram. The red vehicle denotes the ego vehicle, while the blue vehicles represent cooperative CAVs. Both the ego vehicle and cooperative CAVs are equipped with forward-facing fan-shaped cameras and LiDAR sensors with front-view coverage. The RSU is equipped with fan-shaped cameras covering the four approaches of the intersection and a 360◦ LiDAR sensor, providing comprehensive … view at source ↗
Figure 2
Figure 2. Figure 2: Architecture of XET-V2X (i.e., RSUs or CAVs), XET-V2X employs PointPillars [28] to extract point cloud features and ResNet [29] to extract image features, yielding high-dimensional feature representations. Subsequently, two stacked multi-view cooperative cross-attention modules are applied to fuse features across viewpoints and modalities. Finally, object detection and tracking are performed based on the M… view at source ↗
Figure 3
Figure 3. Figure 3: Backbone. (a) Point Cloud Backbone; (b) Image Backbone. • Ego-vehicle ROI in the V2X-Seq-SPD dataset [5]: x ∈ [−51.2, 51.2] m, y ∈ [−51.2, 51.2] m, z ∈ [−5.0, 3.0] m; • Roadside ROI in the V2X-Seq-SPD dataset [5]: x ∈ [0, 102.4] m, y ∈ [−51.2, 51.2] m, z ∈ [−5.0, 3.0] m; • Ego-vehicle ROI in the V2X-Sim dataset [6]: x ∈ [−51.2, 51.2] m, y ∈ [−51.2, 51.2] m, z ∈ [−3.0, 5.0] m; • Other-agent ROI in the V2X-S… view at source ↗
Figure 4
Figure 4. Figure 4: Performance comparison under different communication latency conditions across three datasets. Subfigures [PITH_FULL_IMAGE:figures/full_fig_p013_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative visualization and comparison of perception results on the V2X-Seq-SPD dataset [ [PITH_FULL_IMAGE:figures/full_fig_p015_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative visualization and comparison of perception results on the V2X-Sim datasets [6]. [PITH_FULL_IMAGE:figures/full_fig_p017_6.png] view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

33 extracted references · 2 linked inside Pith

  1. [1]

    Cooper: Cooperative perception for connected autonomous vehicles based on 3d point clouds

    Qi Chen, Sihai Tang, Qing Yang, and Song Fu. Cooper: Cooperative perception for connected autonomous vehicles based on 3d point clouds. In2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), pages 514–524. IEEE, 2019

    2019

  2. [2]

    F-cooper: Feature based cooperative perception for autonomous vehicle edge computing system using 3d point clouds

    Qi Chen, Xu Ma, Sihai Tang, Jingda Guo, Qing Yang, and Song Fu. F-cooper: Feature based cooperative perception for autonomous vehicle edge computing system using 3d point clouds. InProceedings of the 4th ACM/IEEE Symposium on Edge Computing, pages 88–100, 2019

    2019

  3. [3]

    V2vnet: Vehicle-to-vehicle communication for joint perception and prediction

    Tsun-Hsuan Wang, Sivabalan Manivasagam, Ming Liang, Bin Yang, Wenyuan Zeng, and Raquel Urtasun. V2vnet: Vehicle-to-vehicle communication for joint perception and prediction. InComputer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 605–621. Springer, 2020

    2020

  4. [4]

    Where2comm: Communication-efficient collaborative perception via spatial confidence maps.Advances in neural information processing systems, 35:4874– 4886, 2022

    Yue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong, and Siheng Chen. Where2comm: Communication-efficient collaborative perception via spatial confidence maps.Advances in neural information processing systems, 35:4874– 4886, 2022

    2022

  5. [5]

    V2x-seq: A large-scale sequential dataset for vehicle-infrastructure cooperative perception and forecasting

    Haibao Yu, Wenxian Yang, Hongzhi Ruan, Zhenwei Yang, Yingjuan Tang, Xu Gao, Xin Hao, Yifeng Shi, Yifeng Pan, Ning Sun, et al. V2x-seq: A large-scale sequential dataset for vehicle-infrastructure cooperative perception and forecasting. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5486–5495, 2023

    2023

  6. [6]

    V2x-sim: Multi-agent collaborative perception dataset and benchmark for autonomous driving.IEEE Robotics and Automation Letters, 7(4):10914–10921, 2022

    Yiming Li, Dekun Ma, Ziyan An, Zixun Wang, Yiqi Zhong, Siheng Chen, and Chen Feng. V2x-sim: Multi-agent collaborative perception dataset and benchmark for autonomous driving.IEEE Robotics and Automation Letters, 7(4):10914–10921, 2022

    2022

  7. [7]

    V2v4real: A real-world large-scale dataset for vehicle-to-vehicle cooperative perception

    Runsheng Xu, Xin Xia, Jinlong Li, Hanzhao Li, Shuo Zhang, Zhengzhong Tu, Zonglin Meng, Hao Xiang, Xiaoyu Dong, Rui Song, et al. V2v4real: A real-world large-scale dataset for vehicle-to-vehicle cooperative perception. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13712–13722, 2023

    2023

  8. [8]

    Advisory warnings based on cooperative perception

    Florian Seeliger, Galia Weidl, Dominik Petrich, Frederik Naujoks, Gabi Breuel, Alexandra Neukum, and Klaus Dietmayer. Advisory warnings based on cooperative perception. In2014 IEEE Intelligent Vehicles Symposium Proceedings, pages 246–252. IEEE, 2014

    2014

  9. [9]

    Shared perception for connected and automated vehicles

    Yeojun Kim, Luca Onesto, Samuel Tay, Lujie Yang, Jacopo Guanetti, Sergio Savaresi, and Francesco Borrelli. Shared perception for connected and automated vehicles. In2020 IEEE Intelligent Vehicles Symposium (IV), pages 21–26. IEEE, 2020

    2020

  10. [10]

    Lidar-based end-to-end temporal perception for vehicle-infrastructure cooperation.IEEE INTERNET OF THINGS JOURNAL, 12(13):22862–22874, JUL 1 2025

    Zhenwei Yang, Jilei Mao, Wenxian Yang, Yibo Ai, Yu Kong, Haibao Yu, and Weidong Zhang. Lidar-based end-to-end temporal perception for vehicle-infrastructure cooperation.IEEE INTERNET OF THINGS JOURNAL, 12(13):22862–22874, JUL 1 2025

    2025

  11. [11]

    Dair-v2x: A large-scale dataset for vehicle-infrastructure cooperative 3d object detection

    Haibao Yu, Yizhen Luo, Mao Shu, Yiyi Huo, Zebang Yang, Yifeng Shi, Zhenglong Guo, Hanyu Li, Xing Hu, Jirui Yuan, et al. Dair-v2x: A large-scale dataset for vehicle-infrastructure cooperative 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 21361–21370, 2022

    2022

  12. [12]

    Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication

    Runsheng Xu, Hao Xiang, Xin Xia, Xu Han, Jinlong Li, and Jiaqi Ma. Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. In2022 International Conference on Robotics and Automation (ICRA), pages 2583–2589. IEEE, 2022

    2022

  13. [13]

    Pointpainting: Sequential fusion for 3d object detection

    Sourabh V ora, Alex H Lang, Bassam Helou, and Oscar Beijbom. Pointpainting: Sequential fusion for 3d object detection. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4604–4612, 2020

    2020

  14. [14]

    Centerfusion: Center-based radar and camera fusion for 3d object detection

    Ramin Nabati and Hairong Qi. Centerfusion: Center-based radar and camera fusion for 3d object detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1527–1536, 2021

    2021

  15. [15]

    Deformable feature aggregation for dynamic multi-modal 3d object detection

    Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, and Feng Zhao. Deformable feature aggregation for dynamic multi-modal 3d object detection. InEuropean conference on computer vision, pages 628–644. Springer, 2022

    2022

  16. [16]

    Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection

    Yingwei Li, Adams Wei Yu, Tianjian Meng, Ben Caine, Jiquan Ngiam, Daiyi Peng, Junyang Shen, Yifeng Lu, Denny Zhou, Quoc V Le, et al. Deepfusion: Lidar-camera deep fusion for multi-modal 3d object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 17182–17191, 2022. 18 APREPRINT- DECEMBER29, 2025

    2022

  17. [17]

    Transfusion: Robust lidar-camera fusion for 3d object detection with transformers

    Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu, and Chiew-Lan Tai. Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1090–1099, 2022

    2022

  18. [18]

    Futr3d: A unified sensor fusion framework for 3d detection

    Xuanyao Chen, Tianyuan Zhang, Yue Wang, Yilun Wang, and Hang Zhao. Futr3d: A unified sensor fusion framework for 3d detection. Inproceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 172–181, 2023

    2023

  19. [19]

    Deepinteraction: 3d object detection via modality interaction.Advances in Neural Information Processing Systems, 35:1992–2005, 2022

    Zeyu Yang, Jiaqi Chen, Zhenwei Miao, Wei Li, Xiatian Zhu, and Li Zhang. Deepinteraction: 3d object detection via modality interaction.Advances in Neural Information Processing Systems, 35:1992–2005, 2022

    1992

  20. [20]

    4d-net for learned multi-modal alignment

    AJ Piergiovanni, Vincent Casser, Michael S Ryoo, and Anelia Angelova. 4d-net for learned multi-modal alignment. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 15435–15445, 2021

    2021

  21. [21]

    Recurrentbev: A long-term temporal fusion framework for multi-view 3d detection

    Ming Chang, Xishan Zhang, Rui Zhang, Zhipeng Zhao, Guanhua He, and Shaoli Liu. Recurrentbev: A long-term temporal fusion framework for multi-view 3d detection. InEuropean Conference on Computer Vision, pages 131–147. Springer, 2024

    2024

  22. [22]

    V2xpnp: Vehicle-to-everything spatio-temporal fusion for multi-agent perception and prediction.arXiv preprint arXiv:2412.01812, 2024

    Zewei Zhou, Hao Xiang, Zhaoliang Zheng, Seth Z Zhao, Mingyue Lei, Yun Zhang, Tianhui Cai, Xinyi Liu, Johnson Liu, Maheswari Bajji, et al. V2xpnp: Vehicle-to-everything spatio-temporal fusion for multi-agent perception and prediction.arXiv preprint arXiv:2412.01812, 2024

    Pith/arXiv arXiv 2024

  23. [23]

    Center-based 3d object detection and tracking

    Tianwei Yin, Xingyi Zhou, and Philipp Krahenbuhl. Center-based 3d object detection and tracking. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11784–11793, 2021

    2021

  24. [24]

    Trackformer: Multi-object tracking with transformers

    Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixe, and Christoph Feichtenhofer. Trackformer: Multi-object tracking with transformers. InProceedings of the IEEE/CVF conference on computer vision and pattern recogni- tion, pages 8844–8854, 2022

    2022

  25. [25]

    Motr: End-to-end multiple-object tracking with transformer

    Fangao Zeng, Bin Dong, Yuang Zhang, Tiancai Wang, Xiangyu Zhang, and Yichen Wei. Motr: End-to-end multiple-object tracking with transformer. InEuropean Conference on Computer Vision, pages 659–675. Springer, 2022

    2022

  26. [26]

    Learnable online graph representations for 3d multi-object tracking.IEEE Robotics and Automation Letters, 7(2):5103–5110, 2022

    Jan-Nico Zaech, Alexander Liniger, Dengxin Dai, Martin Danelljan, and Luc Van Gool. Learnable online graph representations for 3d multi-object tracking.IEEE Robotics and Automation Letters, 7(2):5103–5110, 2022

    2022

  27. [27]

    Motiontrack: end-to-end transformer- based multi-object tracking with lidar-camera fusion

    Ce Zhang, Chengjie Zhang, Yiluan Guo, Lingji Chen, and Michael Happold. Motiontrack: end-to-end transformer- based multi-object tracking with lidar-camera fusion. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 151–160, 2023

    2023

  28. [28]

    Pointpillars: Fast encoders for object detection from point clouds

    Alex H Lang, Sourabh V ora, Holger Caesar, Lubing Zhou, Jiong Yang, and Oscar Beijbom. Pointpillars: Fast encoders for object detection from point clouds. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12697–12705, 2019

    2019

  29. [29]

    Deep residual learning for image recognition

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016

    2016

  30. [30]

    Quest: Query stream for vehicle-infrastructure cooperative perception.arXiv preprint arXiv:2308.01804, 2023

    Siqi Fan, Haibao Yu, Wenxian Yang, Jirui Yuan, and Zaiqing Nie. Quest: Query stream for vehicle-infrastructure cooperative perception.arXiv preprint arXiv:2308.01804, 2023

    Pith/arXiv arXiv 2023

  31. [31]

    Transiff: An instance-level feature fusion framework for vehicle- infrastructure cooperative 3d detection with transformers

    Ziming Chen, Yifeng Shi, and Jinrang Jia. Transiff: An instance-level feature fusion framework for vehicle- infrastructure cooperative 3d detection with transformers. InProceedings of the IEEE/CVF International Confer- ence on Computer Vision, pages 18205–18214, 2023

    2023

  32. [32]

    Dense reinforcement learning for safety validation of autonomous vehicles.Nature, 615(7953):620–627, 2023

    Shuo Feng, Haowei Sun, Xintao Yan, Haojie Zhu, Zhengxia Zou, Shengyin Shen, and Henry X Liu. Dense reinforcement learning for safety validation of autonomous vehicles.Nature, 615(7953):620–627, 2023

    2023

  33. [33]

    Attention is all you need.Advances in neural information processing systems, 30, 2017

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need.Advances in neural information processing systems, 30, 2017. 19

    2017