SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance | Paper Citation Record

Observation 8d1d1d6e-93c2-4c81-9783-401fd5aedf2f · outbound

This paper cites GPT-4 Technical Report.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-10T13:45:28.713183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f68afbbe-6aa2-4d86-b2f0-48961a960021 · outbound

This paper cites Qwen2.5-VL Technical Report.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Qwen2.5-VL Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-10T13:45:28.717111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 027a544d-dd9f-4b14-8a71-e10c1117650f · outbound

This paper cites Multi-hmr: Multi-person whole-body hu- man mesh recovery in a single shot.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Multi-hmr: Multi-person whole-body hu- man mesh recovery in a single shot

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.312533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 99c7a567-b929-4a2c-81d0-9b799a322d4b · outbound

This paper cites Keep it smpl: Automatic estimation of 3d human pose and shape from a sin- gle image.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Keep it smpl: Automatic estimation of 3d human pose and shape from a sin- gle image

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.298657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8af1b78a-b3ad-421b-a240-59448d9704b2 · outbound

This paper cites Executing your commands via motion diffusion in latent space.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Executing your commands via motion diffusion in latent space

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.337394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9399b534-5bf0-4049-8df8-b83d59b46d69 · outbound

This paper cites an unresolved cited work.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-18T22:52:53.334564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation be0fbf85-80de-42db-94b7-cb5e6a3e6b51 · outbound

This paper cites ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.721750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6b2cc349-84b5-4565-ae7d-5e000cc18717 · outbound

This paper cites Interaction transformer for human reaction generation.IEEE Transactions on Multimedia, 25: 8842–8854.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Interaction transformer for human reaction generation.IEEE Transactions on Multimedia, 25: 8842–8854

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.252337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fcc9f00-0a99-46df-a0d1-46659e5fecb1 · outbound

This paper cites Huang, Siyu Tang, Dimitris Tzionas, and Michael J.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Huang, Siyu Tang, Dimitris Tzionas, and Michael J

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.248963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5bdf9610-c1c6-4bb9-9964-112f9ecd6d01 · outbound

This paper cites Improving diffusion models for inverse problems using manifold constraints.Advances in Neural Information Pro- cessing Systems, 35:25683–25696.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Improving diffusion models for inverse problems using manifold constraints.Advances in Neural Information Pro- cessing Systems, 35:25683–25696

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.265210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f52c2d8f-de2c-4a81-9fdb-e515b4723e23 · outbound

This paper cites Capturing closely interacted two-person motions with reaction priors.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Capturing closely interacted two-person motions with reaction priors

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.399045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4a0e78ce-6470-4d1d-9720-8e9dcfa387d2 · outbound

This paper cites Diffpose: Spatiotemporal diffusion model for video-based human pose estimation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Diffpose: Spatiotemporal diffusion model for video-based human pose estimation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.242545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ed59af49-6d42-4d85-88b2-d6d7a4433753 · outbound

This paper cites Three- dimensional reconstruction of human interactions.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Three- dimensional reconstruction of human interactions

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.252748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 085f1491-1cdb-4709-bcec-e5447295ce69 · outbound

This paper cites Remips: Physically consistent 3d reconstruction of multiple interacting people under weak supervision.Advances in Neural Information Processing Systems, 34:19385–19397.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Remips: Physically consistent 3d reconstruction of multiple interacting people under weak supervision.Advances in Neural Information Processing Systems, 34:19385–19397

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.245773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 195a239f-1555-4235-a877-8b9fb5470a89 · outbound

This paper cites The potential of human pose estimation for motion capture in sports: a validation study.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance The potential of human pose estimation for motion capture in sports: a validation study

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.274385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b11c6fa1-46c9-4f57-98f4-bdbc24fad827 · outbound

This paper cites YOLOX: Exceeding YOLO Series in 2021.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance YOLOX: Exceeding YOLO Series in 2021

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T10:31:31.716715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 231ad2ff-c78f-4b64-aa1a-52800ffbe519 · outbound

This paper cites Remos: 3d motion- conditioned reaction synthesis for two-person interactions.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Remos: 3d motion- conditioned reaction synthesis for two-person interactions

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.256187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 38bd7a86-da8c-4ee0-9cdb-24b21279af68 · outbound

This paper cites Humans in 4d: Recon- structing and tracking humans with transformers.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Humans in 4d: Recon- structing and tracking humans with transformers

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.275257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ef78a10-c21b-4a2c-8fa1-53c940ef19e4 · outbound

This paper cites Reconstructing groups of people with hypergraph relational reasoning.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 14827–14837.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Reconstructing groups of people with hypergraph relational reasoning.2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 14827–14837

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.302307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ad06032d-f147-4ecd-bf6f-4f33a1ae9da0 · outbound

This paper cites Closely interactive human reconstruction with proxemics and physics-guided adaption.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Closely interactive human reconstruction with proxemics and physics-guided adaption

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.201592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1cc66f67-1d1d-4a84-91ea-836ae669d962 · outbound

This paper cites Motiongpt: Human motion as a foreign language.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Motiongpt: Human motion as a foreign language

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.305833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 53bbd18a-63a5-4ef6-a1ec-df1f83f6f189 · outbound

This paper cites Coherent reconstruction of multiple humans from a single image.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Coherent reconstruction of multiple humans from a single image

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.278429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 066b7571-312b-4570-89a4-a5b042201a16 · outbound

This paper cites Ultralytics yolov8.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Ultralytics yolov8

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.262395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9542a235-ce89-420d-a0ea-5810ffb7a09e · outbound

This paper cites End-to-end recovery of human shape and pose.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance End-to-end recovery of human shape and pose

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.198411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b12592ca-acd1-47b4-9133-6583a036e339 · outbound

This paper cites Maximizing parallelism in the construction of bvhs, octrees, and k-d trees.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Maximizing parallelism in the construction of bvhs, octrees, and k-d trees

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.218802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d373bf78-d032-4f09-a33f-6e18637413b6 · outbound

This paper cites Harmony4d: A video dataset for in-the-wild close human interactions.Advances in Neural Information Processing Systems, 37:107270–107285.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Harmony4d: A video dataset for in-the-wild close human interactions.Advances in Neural Information Processing Systems, 37:107270–107285

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.262199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1be506f4-b1e7-48af-b1a3-875b4e58eceb · outbound

This paper cites Vibe: Video inference for human body pose and shape es- timation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Vibe: Video inference for human body pose and shape es- timation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.327774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 397ebd9f-6868-4ce0-8471-43b3f5c6f621 · outbound

This paper cites Pare: Part attention regressor for 3d human body estimation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Pare: Part attention regressor for 3d human body estimation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.408926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5d222bc6-8106-4185-be12-148b47ad5986 · outbound

This paper cites Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.388334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 919d9be6-2563-45cc-ad83-7859a9afb4b7 · outbound

This paper cites Cliff: Carrying location information in full frames into human pose and shape estimation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Cliff: Carrying location information in full frames into human pose and shape estimation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.374975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1c450a65-936d-49dd-9f9d-f3c5ad1a672c · outbound

This paper cites Intergen: Diffusion-based multi-human motion gener- ation under complex interactions.International Journal of Computer Vision, 132(9):3463–3483.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Intergen: Diffusion-based multi-human motion gener- ation under complex interactions.International Journal of Computer Vision, 132(9):3463–3483

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.384967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d878b0cd-3039-43b3-995c-6b56990b421b · outbound

This paper cites Motions as queries: One-stage multi- person holistic human motion capture.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Motions as queries: One-stage multi- person holistic human motion capture

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.378604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation de078a7b-efad-4bd0-8f8b-0247e94272dd · outbound

This paper cites Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with Social Affordance Canonicalization and Forecasting

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.743951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3d731841-a0d4-48a7-b325-e4c4b430a2d2 · outbound

This paper cites DPoser: Diffusion Model as Robust 3D Human Pose Prior.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance DPoser: Diffusion Model as Robust 3D Human Pose Prior

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.731725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 59d7e6dc-177a-46a4-95dd-fc530fabb610 · outbound

This paper cites Autotrackanything.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Autotrackanything

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.394391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 24a0c873-b6d2-4446-bce2-e6493e7ff415 · outbound

This paper cites Generative proxemics: A prior for 3d social interaction from images.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Generative proxemics: A prior for 3d social interaction from images

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.366798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 15595afc-2073-4a69-a174-bdae940fb6a4 · outbound

This paper cites Richter, and Vladlen Koltun.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Richter, and Vladlen Koltun

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.381815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b3a0bc52-f2a9-40b4-9a4a-8567ff6ba741 · outbound

This paper cites Improved denoising diffusion probabilistic models.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Improved denoising diffusion probabilistic models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.321340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7f1fe315-32d5-485e-8684-ac318ebd56f2 · outbound

This paper cites Expressive body capture: 3d hands, face, and body from a single image.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Expressive body capture: 3d hands, face, and body from a single image

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.315815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 15ff25fb-9d3d-4edc-860c-80c7707d1d88 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Learning transferable visual models from natural language supervi- sion

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.330900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cc44dc07-9303-422d-b909-22505dfb46ff · outbound

This paper cites Humor: 3d human motion model for robust pose estimation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Humor: 3d human motion model for robust pose estimation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.344979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e74f3ca2-216f-4f75-a0ae-20c0083f41ed · outbound

This paper cites Diffhpe: Robust, coherent 3d human pose lifting with diffu- sion.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Diffhpe: Robust, coherent 3d human pose lifting with diffu- sion

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.341979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0ca26665-9ee5-43ff-a839-56739bd0bf57 · outbound

This paper cites Phasemp: Robust 3d pose estimation via phase-conditioned human motion prior.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Phasemp: Robust 3d pose estimation via phase-conditioned human motion prior

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.283581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6788fb61-8a43-4dcf-8c68-7938be0ab16d · outbound

This paper cites Sat-hmr: Real-time multi-person 3d mesh estimation via scale-adaptive tokens.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Sat-hmr: Real-time multi-person 3d mesh estimation via scale-adaptive tokens

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.291371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 53c8238d-916f-4de6-8aa2-643dc52eefab · outbound

This paper cites Pose Priors from Language Models.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Pose Priors from Language Models

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.758533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2e474906-302e-436e-8cec-d74050c0d340 · outbound

This paper cites Monocular, one-stage, regression of multiple 3d people.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Monocular, one-stage, regression of multiple 3d people

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.301934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c85e3fff-52b2-4734-8b94-c46edfbc78ce · outbound

This paper cites Putting people in their place: Monocular regression of 3d people in depth.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Putting people in their place: Monocular regression of 3d people in depth

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.280900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d9f39284-2b2f-42ec-b981-631d1017fbb7 · outbound

This paper cites Role-aware interac- tion generation from textual description.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Role-aware interac- tion generation from textual description

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.363506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3da8615b-d35e-46c3-8fa6-8c8e04e0a868 · outbound

This paper cites Human motion diffusion model.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Human motion diffusion model

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.351674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1948523b-56c3-4059-98e7-27095c7b15ed · outbound

This paper cites Multiphys: multi- person physics-aware 3d motion estimation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Multiphys: multi- person physics-aware 3d motion estimation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.357131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5ac2ede6-9eca-4ac3-805c-338a62e230f7 · outbound

This paper cites Ai-based pose estimation of human operators in manu- facturing environments.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Ai-based pose estimation of human operators in manu- facturing environments

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.360206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation daa37d63-7b30-4b6b-a579-4221a8955e46 · outbound

This paper cites Recovering accurate 3d 10 human pose in the wild using imus and a moving camera.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Recovering accurate 3d 10 human pose in the wild using imus and a moving camera

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.268195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7c454b44-dede-4217-9bfa-d99857998936 · outbound

This paper cites Tlcontrol: Trajectory and language control for human motion synthesis.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Tlcontrol: Trajectory and language control for human motion synthesis

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.271393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 83785512-473b-42ec-a49d-3317b11fc39c · outbound

This paper cites Black, and Muhammed Kocabas.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Black, and Muhammed Kocabas

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.348079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d58bee86-da79-4845-9633-4d850f28837e · outbound

This paper cites Inter- control: Generate human motion interactions by controlling every joint.CoRR.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Inter- control: Generate human motion interactions by controlling every joint.CoRR

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.294935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a2122ad1-a533-429e-bc30-fd7dad5287b2 · outbound

This paper cites Crowd3d: Towards hundreds of peo- ple reconstruction from a single image.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Crowd3d: Towards hundreds of peo- ple reconstruction from a single image

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.309275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4bf87ddf-fdb0-4fbd-8b55-57afe73e0dde · outbound

This paper cites an unresolved cited work.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-18T22:52:53.324587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c80ef291-b9cb-4055-9d53-76f31efc21dc · outbound

This paper cites Occluded human pose estimation based on part-aware discrete diffusion priors.Knowledge-Based Systems, 315:113272.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Occluded human pose estimation based on part-aware discrete diffusion priors.Knowledge-Based Systems, 315:113272

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.391374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b0503eef-c9a8-4f88-bc9d-cb25b56b346d · outbound

This paper cites OmniControl: Control Any Joint at Any Time for Human Motion Generation.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance OmniControl: Control Any Joint at Any Time for Human Motion Generation

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.763411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 97dfb901-8290-4d87-8418-aaf0e46ee057 · outbound

This paper cites Adapting Human Mesh Recovery with Vision-Language Feedback.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Adapting Human Mesh Recovery with Vision-Language Feedback

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.735611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 68f2d89f-c9df-47de-ac8d-f69ec13edd37 · outbound

This paper cites Ghum & ghuml: Generative 3d human shape and articulated pose models.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Ghum & ghuml: Generative 3d human shape and articulated pose models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.242822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af619c5b-c207-43a1-8904-7b4de1431c29 · outbound

This paper cites Regennet: Towards human action-reaction synthesis.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Regennet: Towards human action-reaction synthesis

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.259373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ac71c589-1814-4daa-9c07-c41c8dff2a7e · outbound

This paper cites Spatial tempo- ral graph convolutional networks for skeleton-based action recognition.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Spatial tempo- ral graph convolutional networks for skeleton-based action recognition

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.236533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bed42e8e-b8f9-4fe9-8f80-56d5307c1916 · outbound

This paper cites Hi4d: 4d instance segmentation of close human interaction.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Hi4d: 4d instance segmentation of close human interaction

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.255947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 92596ee1-058e-47ba-a46f-9ac21993e8a3 · outbound

This paper cites Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.739912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f95df2aa-29cf-4937-aedf-98934fae142c · outbound

This paper cites Glamr: Global occlusion-aware human mesh recovery with dynamic cameras.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Glamr: Global occlusion-aware human mesh recovery with dynamic cameras

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.239582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8772aa84-e8fd-4b30-97ac-93575caa6030 · outbound

This paper cites Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.208595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 50a9228d-539b-499b-b1a4-8341c8e775cb · outbound

This paper cites Smoothnet: A plug-and-play network for refining human poses in videos.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Smoothnet: A plug-and-play network for refining human poses in videos

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.204869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd7e8873-2c56-40b7-a0f1-7ab7e1a60286 · outbound

This paper cites Faster Segment Anything: Towards Lightweight SAM for Mobile Applications.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:41:43.533652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6ccb73f4-e8d8-42a1-bb1a-3f4a7b840d47 · outbound

This paper cites Adding conditional control to text-to-image diffusion models.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Adding conditional control to text-to-image diffusion models

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.259131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f7b2b1a4-d85b-4057-b3bc-cfc4ff65e429 · outbound

This paper cites DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.749075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3deb9596-ea89-435a-bf82-7f9022e11db5 · outbound

This paper cites 3d human pose estimation with spatial and temporal transformers.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance 3d human pose estimation with spatial and temporal transformers

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.281424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3f8ba371-e660-4747-bce0-85ee3d7de9b0 · outbound

This paper cites Dpmesh: Exploiting diffusion prior for occluded human mesh recovery.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Dpmesh: Exploiting diffusion prior for occluded human mesh recovery

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.229380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 18763daa-a75c-412e-8755-11449c5f9000 · outbound

This paper cites Implementation details Our model was implemented using PyTorch and trained on an NVIDIA RTX 3090 GPU.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Implementation details Our model was implemented using PyTorch and trained on an NVIDIA RTX 3090 GPU

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.403191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1a085c2d-95df-43a2-a496-8342a6e73c3a · outbound

This paper cites Ablation on Geometry Optimizer Geometry Optimizer focuses on processing 3D joint posi- tions to provide geometric guidance information.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Ablation on Geometry Optimizer Geometry Optimizer focuses on processing 3D joint posi- tions to provide geometric guidance information

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.191100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 765d0f5b-1a08-4ff7-86d6-a42b384589c0 · outbound

This paper cites Reconstruction under VLM Limitations Based on our user study, the text descriptions generated by the VLM are, on average, superior to those produced by human annotators.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance Reconstruction under VLM Limitations Based on our user study, the text descriptions generated by the VLM are, on average, superior to those produced by human annotators

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:45:28.709131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 70a13032-811f-4141-8f61-f1a3f6008a45 · outbound

This paper cites LLMs are used only for light text polishing and grammar fixes.

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance LLMs are used only for light text polishing and grammar fixes

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T22:52:53.194682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers