Paper Citation Record · LEDGER

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

As of 17 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2602.02401.

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

pith.paper-citation-record.v1
2602.02401 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:29:32.217743Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1f6b9a6f-bef7-430a-82d0-730b80ae7ed4 · outbound

This paper cites Posetrack: a benchmark for human pose estimation and tracking.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Posetrack: a benchmark for human pose estimation and tracking

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:27.310622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece96d30-de9f-4d1d-9c49-c12928df1fff · outbound

This paper cites Qwen2.5-VL Technical Report.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:27.414903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ba9e52-b40a-4ff2-960c-36f1259b1f80 · outbound

This paper cites Keep it smpl: automatic estimation of 3d human pose and shape from a single image.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Keep it smpl: automatic estimation of 3d human pose and shape from a single image

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:27.565941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a45041-6704-43b5-98d6-654eeb4c829f · outbound

This paper cites MotionLLM: Understanding Human Behaviors from Human Motions and Videos.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation MotionLLM: Understanding Human Behaviors from Human Motions and Videos

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:27.699878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78b118cd-d133-43fb-8f4c-b4b7648ea270 · outbound

This paper cites Cascaded pyramid net- work for multi-person pose estimation.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Cascaded pyramid net- work for multi-person pose estimation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:27.846420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6914ba-3544-45a1-9403-6e1b18e7ac96 · outbound

This paper cites Towards accurate 3d hu- man motion prediction from incomplete observations.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Towards accurate 3d hu- man motion prediction from incomplete observations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:27.981867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee50f37-e92e-442b-93f2-47224f8551d1 · outbound

This paper cites Instructblip: Towards general-purpose vision- language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267, 2023.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Instructblip: Towards general-purpose vision- language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.133471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f7110b5-5e6a-4d23-a7b2-2aa59f869551 · outbound

This paper cites Explore in-context learning for 3d point cloud understanding.NeurIPS, 2023.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Explore in-context learning for 3d point cloud understanding.NeurIPS, 2023

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.205559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46faa35-e5a7-4571-9253-ab38f5a9d211 · outbound

This paper cites Posellava: Pose centric multimodal llm for fine-grained 3d pose manipulation.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Posellava: Pose centric multimodal llm for fine-grained 3d pose manipulation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.288751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14f5ea1c-c1f5-4ca1-bbb2-54dab34fb079 · outbound

This paper cites Chatpose: Chatting about 3d human pose.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Chatpose: Chatting about 3d human pose

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.408920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c104e165-f5ea-4025-8e6b-05a1ddd546a1 · outbound

This paper cites Robust motion in-betweening.ACM TOG,.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Robust motion in-betweening.ACM TOG,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.521056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 394e920b-b424-4231-a713-48db12f44dc1 · outbound

This paper cites Human motion prediction via spatio-temporal in- painting.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Human motion prediction via spatio-temporal in- painting

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.629196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b374e9-bbcb-47a9-8cba-8d600788c693 · outbound

This paper cites an unresolved cited work.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.685114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 621d6b57-5efe-485b-9576-ad63e9fa0b66 · outbound

This paper cites Motiongpt: Human motion as a foreign lan- guage.Advances in Neural Information Processing Systems, 36:20067–20079, 2023.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Motiongpt: Human motion as a foreign lan- guage.Advances in Neural Information Processing Systems, 36:20067–20079, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.745560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91507628-b474-419b-b09e-0f8fcbfbae1c · outbound

This paper cites Convolutional autoen- coders for human motion infilling.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Convolutional autoen- coders for human motion infilling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.821414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b24c566d-0ef5-4e5a-b279-476b49759be1 · outbound

This paper cites Unipose: A unified multimodal framework for human pose comprehension, generation and editing.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Unipose: A unified multimodal framework for human pose comprehension, generation and editing

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:28.934565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dabebcfc-c098-475b-8410-a9de3a14c00f · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.062206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a426fce7-66e5-4437-9141-b415cad56e9e · outbound

This paper cites Recognizing human ac- tions as the evolution of pose estimation maps.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Recognizing human ac- tions as the evolution of pose estimation maps

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.105083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ffbc221-2af1-4fc3-9a49-a61b4280d17a · outbound

This paper cites Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.172448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db5b80fd-0152-439e-9d02-dca3daf239c3 · outbound

This paper cites Lit- tle.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Lit- tle

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.239573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c48a91e-79dc-421e-8f60-7427f1d66cfb · outbound

This paper cites an unresolved cited work.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.357160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afdaa9fc-5697-4a5b-8d59-59fcb4829dae · outbound

This paper cites Ski models: Skeleton induced vision- language embeddings for understanding activities of daily living.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Ski models: Skeleton induced vision- language embeddings for understanding activities of daily living

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.477839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed9959e5-9f80-4733-9f89-d8a0716074ea · outbound

This paper cites Deep high-resolution representation learning for human pose es- timation.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Deep high-resolution representation learning for human pose es- timation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.578889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f532764b-df60-45bd-96d3-3d57a587e26e · outbound

This paper cites In- tegral human pose regression.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation In- tegral human pose regression

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.742039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b2b29eb-9619-4a9c-a1ea-c667ae6adcfd · outbound

This paper cites Deeppose: Human pose estimation via deep neural networks.2014 IEEE Con- ference on Computer Vision and Pattern Recognition, pages 1653–1660, 2013.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Deeppose: Human pose estimation via deep neural networks.2014 IEEE Con- ference on Computer Vision and Pattern Recognition, pages 1653–1660, 2013

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:29.876407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df06097c-9d87-4dd4-a404-c7a3eebb1ad0 · outbound

This paper cites Neural discrete representation learning.Advances in neural information pro- cessing systems, 30, 2017.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Neural discrete representation learning.Advances in neural information pro- cessing systems, 30, 2017

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.019846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8fa943b-e15e-4b7e-b52c-9b7dbc168b8c · outbound

This paper cites Recovering ac- curate 3d human pose in the wild using imus and a moving camera.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Recovering ac- curate 3d human pose in the wild using imus and a moving camera

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.155479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9591d841-a598-4e4f-8a51-1a22562581b1 · outbound

This paper cites Locllm: Exploiting generalizable human keypoint localization via large language model.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Locllm: Exploiting generalizable human keypoint localization via large language model

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.279452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e71a125-a750-4b63-b246-2103fa2890ef · outbound

This paper cites Gcnext: towards the unity of graph convolutions for human motion prediction.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Gcnext: towards the unity of graph convolutions for human motion prediction

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.415704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c74d62e-153b-4503-be0c-999ca277b7eb · outbound

This paper cites Skeleton-in-context: unified skeleton sequence modeling with in-context learning.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Skeleton-in-context: unified skeleton sequence modeling with in-context learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.593198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 536b7f00-8d20-4e00-adfa-fa4c3817f563 · outbound

This paper cites Dynamic dense graph convolutional network for skeleton-based human motion prediction.IEEE T-IP,.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Dynamic dense graph convolutional network for skeleton-based human motion prediction.IEEE T-IP,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.743744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6521beb8-f74b-476a-a313-c4b183aaa3e8 · outbound

This paper cites mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.854898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f85c847c-4c48-400e-9517-18f61fc12f00 · outbound

This paper cites LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:30.970986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 164398b9-3f4c-4ea6-9bcd-4cb014261a64 · outbound

This paper cites Distribution-aware coordinate representation for human pose estimation.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Distribution-aware coordinate representation for human pose estimation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:31.081631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39ade4f0-06d7-4b8d-8eff-d1eb477b928e · outbound

This paper cites Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:31.217592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66464e1f-e7bd-42a5-a5c1-0ef8189e9a86 · outbound

This paper cites 3d human pose estima- tion with spatial and temporal transformers.2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages 11636–11645, 2021.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation 3d human pose estima- tion with spatial and temporal transformers.2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages 11636–11645, 2021

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:31.362629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1381a7cb-7c75-4a26-861d-7eeac39b202d · outbound

This paper cites Generative Tweening: Long-term Inbetweening of 3D Human Motions.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Generative Tweening: Long-term Inbetweening of 3D Human Motions

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:31.523985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26de938a-3df0-4115-9bd6-02be1941d6ad · outbound

This paper cites Mo- tiongpt3: Human motion as a second modality.arXiv preprint arXiv:2506.24086, 2025.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Mo- tiongpt3: Human motion as a second modality.arXiv preprint arXiv:2506.24086, 2025

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:31.682961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec370381-c88b-41b9-9eb4-b651ffcd90cc · outbound

This paper cites Motionbert: a unified perspective on learning human motion representations.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Motionbert: a unified perspective on learning human motion representations

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:31.838924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8a82218-8e00-4bcf-a121-ff233d6999a8 · outbound

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

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Deformable DETR: Deformable Transformers for End-to-End Object Detection

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:32.009011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b9ecdb-15f4-451d-8e40-77aee9ff1ad9 · outbound

This paper cites Semantic Spheres.

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation Semantic Spheres

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T05:29:32.217743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.