Paper Citation Record · LEDGER

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding

As of 22 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 4 inbound Pith citation observations for arXiv:2504.12643.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.12643 v3

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:31:13.039058Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:47:22.541050Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T09:07:47.605932Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy11
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fb46d675-e91e-4eb3-8425-724be831a97e · outbound

This paper cites nuscenes: A multimodal dataset for autonomous driving.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding nuscenes: A multimodal dataset for autonomous driving

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.923890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94618c66-406d-48be-9e9f-b80079e435ea · outbound

This paper cites End-to-end object detection with transformers.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding End-to-end object detection with transformers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.928528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf8c4e2-904e-44ed-b695-0a14abf048c3 · outbound

This paper cites Depth- net: A recurrent neural network architecture for monocular depth pre- diction.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Depth- net: A recurrent neural network architecture for monocular depth pre- diction

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.353642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d387582d-2282-4530-994d-29c340be15b3 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.935996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1269e6c6-b826-4999-85b7-0b80a1ced1f0 · outbound

This paper cites Mask r-cnn.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Mask r-cnn

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.344022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 46522b9b-9e03-4758-a20b-1586aee442da · outbound

This paper cites Deep residual learning for image recognition.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Deep residual learning for image recognition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.943785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 390f478b-4e6a-478c-958e-6c34bc5f527f · outbound

This paper cites BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.947420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbb71f6-931f-4756-9602-5163d1428bab · outbound

This paper cites BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.951291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d868bfcd-8eaa-4d63-a08e-404394841377 · outbound

This paper cites Centermask: Real-time anchor-free instance segmentation.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Centermask: Real-time anchor-free instance segmentation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.328844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30cf1ba1-34a8-4243-80c3-1f4532ca93f4 · outbound

This paper cites Dn-detr: Accelerate detr training by introducing query denoising.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Dn-detr: Accelerate detr training by introducing query denoising

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.958838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c60288ff-cc17-44fb-a910-25ff7d279868 · outbound

This paper cites Bevstereo: Enhancing depth estimation in multi-view 3d object detection with temporal stereo.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Bevstereo: Enhancing depth estimation in multi-view 3d object detection with temporal stereo

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.962243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e029934-c678-4306-8dcc-df96470957bd · outbound

This paper cites Bevdepth: Acquisition of reliable depth for multi-view 3d object detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Bevdepth: Acquisition of reliable depth for multi-view 3d object detection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.965448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 407501c6-4017-4a1c-a9f1-acbd026d3a3b · outbound

This paper cites Bevformer: learning bird’s-eye-view representation from lidar-camera via spatiotemporal transformers.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Bevformer: learning bird’s-eye-view representation from lidar-camera via spatiotemporal transformers.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.968653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b5c746b-e9d3-416b-90c0-6444f2720dd5 · outbound

This paper cites Fb-bev: Bev representation from forward-backward view transformations.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Fb-bev: Bev representation from forward-backward view transformations

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.297400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5df66585-8fb0-4d19-a709-e5b485013974 · outbound

This paper cites Sparse4D v3: Advancing End-to-End 3D Detection and Tracking.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Sparse4D v3: Advancing End-to-End 3D Detection and Tracking

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.975240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f0829d4-77ff-4efc-9c91-4c8cb81474a3 · outbound

This paper cites Ray denoising: Depth-aware hard negative sampling for multi-view 3d object detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Ray denoising: Depth-aware hard negative sampling for multi-view 3d object detection

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.286531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 87715754-8943-4aae-88c8-01a1c5ce74ed · outbound

This paper cites Petr: Position embedding transformation for multi-view 3d object detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Petr: Position embedding transformation for multi-view 3d object detection

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.274340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a76c5e66-7113-4a57-8910-33be968292d7 · outbound

This paper cites Petrv2: A unified framework for 3d perception from multi-camera images.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Petrv2: A unified framework for 3d perception from multi-camera images

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.985353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479f4040-112c-4d32-8a47-7b1e4ac34396 · outbound

This paper cites Is pseudo-lidar needed for monocular 3d object detection? InProceed- ings of the IEEE/CVF International Conference on Computer Vision, pages 3142–3152, 2021.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Is pseudo-lidar needed for monocular 3d object detection? InProceed- ings of the IEEE/CVF International Conference on Computer Vision, pages 3142–3152, 2021

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.256846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 72c76f90-3020-457f-b63a-8cba2af2e600 · outbound

This paper cites Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.991943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff3b5ec-ffb0-4ac9-a1a9-02398ea3bb4d · outbound

This paper cites Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:12.995985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64520385-94a6-4531-b72a-90eaf33e1688 · outbound

This paper cites Hop: History-and-order aware pre-training for vision-and- language navigation.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Hop: History-and-order aware pre-training for vision-and- language navigation

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.239710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 096686c3-83e6-4724-b16d-1bec388896de · outbound

This paper cites 3dppe: 3d point positional encoding for transformer-based multi-camera 3d object detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding 3dppe: 3d point positional encoding for transformer-based multi-camera 3d object detection

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.003266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ac30dd9-fa0c-491d-9a47-3fedd8e08557 · outbound

This paper cites Sparse r-cnn: End-to-end object detection with learnable proposals.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Sparse r-cnn: End-to-end object detection with learnable proposals

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.006723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf36e4a8-a98d-465c-9f1b-1a5ebd7ece3b · outbound

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

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.010141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb9d6c59-df5f-4164-9b00-46b490f67b65 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.013670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e6f7eb-4256-4d91-be54-5e1617e9e38a · outbound

This paper cites Exploring object-centric temporal modeling for efficient multi-view 3d object detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Exploring object-centric temporal modeling for efficient multi-view 3d object detection

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.017367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f569149-3038-4d92-a5c3-26e21f6242de · outbound

This paper cites Detr3d: 3d object detection from multi- view images via 3d-to-2d queries.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Detr3d: 3d object detection from multi- view images via 3d-to-2d queries

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.201882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2040c045-dc32-4e66-89bb-724a055d1808 · outbound

This paper cites Object as query: Lifting any 2d object detector to 3d detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Object as query: Lifting any 2d object detector to 3d detection

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.189385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a4777d53-db04-4c46-9b5b-d02c4e96d1ff · outbound

This paper cites Cape: Camera view position embedding for multi-view 3d object detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Cape: Camera view position embedding for multi-view 3d object detection

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:31:13.174620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d3eaa36a-d12c-4b38-bbb2-b313807620e6 · outbound

This paper cites DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.031248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1285a2ac-a99b-4565-9bb6-da9b1bd61062 · outbound

This paper cites Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.035327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aecf5d2a-f789-4ec2-971c-c21aaf1d3641 · outbound

This paper cites Deformable DETR: Deformable Transformers for End-to-End Object Detection.

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding Deformable DETR: Deformable Transformers for End-to-End Object Detection

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T12:31:13.039058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8e6a1fb8-13d2-4046-b779-4e9983f90928 · inbound

All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles cites this paper.

All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding

Reference 171

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:00:48.115163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3e694238-4615-413f-8ce7-c29aabe9e826 · inbound

FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception cites this paper.

FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:40:59.288451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aa928c84-18cb-4912-9763-f00664ae0883 · inbound

nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding cites this paper.

nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T09:07:47.607418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6feaab0d-b9aa-40d5-869a-666f6e2fb0f1 · inbound

Geometry-Grounded Unified 3D Perception for Autonomous Driving cites this paper.

Geometry-Grounded Unified 3D Perception for Autonomous Driving RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T15:47:22.541050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.