Paper Citation Record · LEDGER

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding

As of 8 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2507.17533.

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

pith.paper-citation-record.v1
2507.17533 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:51:52.797897Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

16 of 16 outbound references displayed

verified exact2
verified fuzzy7
unresolved6
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8b70df00-f2d6-4d7a-a5b1-27cc903c92bd · outbound

This paper cites Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:52.710758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67051f14-6b6e-4ebe-be36-f6f4d01e6680 · outbound

This paper cites PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:52.729516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bdd77f3-e474-4a78-81fb-ea1a2e023047 · outbound

This paper cites Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:52.748673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6b3963e-3f5b-4aa8-9e3c-aa8340bd5439 · outbound

This paper cites P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:51:52.956071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4c1e08a2-074f-4bad-b2e8-7d13eaa19204 · outbound

This paper cites Masked autoencoders for point cloud self-supervised learning.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Masked autoencoders for point cloud self-supervised learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.200822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 07ea80dc-6f0f-4195-9a1d-6f614c67bc75 · outbound

This paper cites PVT: Point-Voxel Transformer for Point Cloud Learning.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding PVT: Point-Voxel Transformer for Point Cloud Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:52.767519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e3ba5a-34a4-4db1-8462-77c379c8b992 · outbound

This paper cites Asfm-net: Asymmetrical siamese feature matching network for point completion.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Asfm-net: Asymmetrical siamese feature matching network for point completion

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.180306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3818ead-c011-49cf-b98f-d93cc81192c8 · outbound

This paper cites We fine-tune our model on the point cloud completion benchmarks for 200 epochs.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding We fine-tune our model on the point cloud completion benchmarks for 200 epochs

Reference 16

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T14:51:52.912620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b82c22fa-2e12-41d7-9532-d9c32ab8077a · outbound

This paper cites We follow previous works and use 1024 points with coordinate information as the input [Yu et al., 2022, Lu et al., 2022, Gao et al., 2022].

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding We follow previous works and use 1024 points with coordinate information as the input [Yu et al., 2022, Lu et al., 2022, Gao et al., 2022]

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.125740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1e904047-8528-4efc-8994-8fbb1742c7e1 · outbound

This paper cites Similar to PointNet [Qi et al., 2017a], we sample 2,048 points from each model.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Similar to PointNet [Qi et al., 2017a], we sample 2,048 points from each model

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.110264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed713b84-6091-4566-8c11-811ff9471d0c · outbound

This paper cites 3d shapenets: A deep representation for volumetric shapes.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding 3d shapenets: A deep representation for volumetric shapes

Reference 2008

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.142204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 810b6d53-d3bf-4dfa-ba12-aed8b2d1d18a · outbound

This paper cites Grnet: Gridding residual network for dense point cloud completion.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Grnet: Gridding residual network for dense point cloud completion

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.160183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a316b901-a17e-4247-b5d3-c4fbe17c1a1e · outbound

This paper cites Pointcontrast: Unsupervised pre-training for 3d point cloud understanding.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Pointcontrast: Unsupervised pre-training for 3d point cloud understanding

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:51:53.219492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3a7b2b1e-e2d5-4038-b13f-262b6d6b8621 · outbound

This paper cites Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting

Reference 2020

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:51:53.046813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d0d9424f-6cf3-4b85-8d1b-bf5e39bf080f · outbound

This paper cites Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:52.741538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88684cbf-eae9-48e3-9446-9eedd51f4530 · outbound

This paper cites Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training.

Multi-modal Multi-task Pre-training for Improved Point Cloud Understanding Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T14:51:52.717350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.