Paper Citation Record · LEDGER

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

As of 15 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2412.20148.

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

pith.paper-citation-record.v1
2412.20148 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T23:34:38.175518Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

37 of 37 outbound references displayed

verified exact1
verified fuzzy25
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a511b0a2-41e2-4d37-a0b9-25a203b3c103 · outbound

This paper cites Real-time talking head driven by voice and its application to communication and entertainment,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Real-time talking head driven by voice and its application to communication and entertainment,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.614742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b75c368f-5bb0-4314-b9ce-b150275dda9b · outbound

This paper cites The acceptability of virtual characters as social skills trainers: usability study,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis The acceptability of virtual characters as social skills trainers: usability study,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.601610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f24d32fe-fbee-452d-bcaa-440db297e7ed · outbound

This paper cites Seeing is believing but is hearing? comparing audio and video communication for young children,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Seeing is believing but is hearing? comparing audio and video communication for young children,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.589807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 596dd746-5ea6-481b-b428-271aa710d75f · outbound

This paper cites Learning person-specific cognition from facial reactions for automatic personality recognition,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Learning person-specific cognition from facial reactions for automatic personality recognition,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.577718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 84ce33ad-75ac-415e-8e97-9867f5f5968d · outbound

This paper cites React2023: The first multiple appropriate facial reaction generation challenge,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis React2023: The first multiple appropriate facial reaction generation challenge,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.565227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d5bc93f2-b595-467c-92b8-532c2f1453b3 · outbound

This paper cites 3d facial expressions through analysis-by-neural-synthesis,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis 3d facial expressions through analysis-by-neural-synthesis,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.553083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cc395ed8-b064-41c3-a4c4-2d4e21ca32eb · outbound

This paper cites Gen- erative adversarial nets,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Gen- erative adversarial nets,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.064198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abc3e796-fae0-4ca0-95f2-d3319502fef8 · outbound

This paper cites Image- to-image translation with conditional adversarial networks,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Image- to-image translation with conditional adversarial networks,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.533526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6618bd1c-5cbd-418c-9834-01e0c63a1a8a · outbound

This paper cites High-resolution image synthesis with latent diffu- sion models,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis High-resolution image synthesis with latent diffu- sion models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.071678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f08b573-2fed-457e-a78c-0c34e8edbe29 · outbound

This paper cites A lip sync expert is all you need for speech to lip generation in the wild,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis A lip sync expert is all you need for speech to lip generation in the wild,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.513890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7aa0c587-58f8-4f61-ab09-4f8a455e5be6 · outbound

This paper cites Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Sadtalker: Learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.501360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c575e914-8f9a-4b0f-8f98-7b2f9748735c · outbound

This paper cites Identity-preserving talking face generation with landmark and appearance priors,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Identity-preserving talking face generation with landmark and appearance priors,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.488555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2023f2c1-b6e4-4cc6-b051-ff4217ada107 · outbound

This paper cites Makelttalk: speaker-aware talking-head animation,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Makelttalk: speaker-aware talking-head animation,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.476826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 55a86728-9140-4715-858f-0e7de15f1f9b · outbound

This paper cites Difftalk: Crafting diffusion models for generalized audio-driven portraits animation,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Difftalk: Crafting diffusion models for generalized audio-driven portraits animation,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.465349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4e2f5ac3-3ac3-4894-a878-a1a5e543aca7 · outbound

This paper cites Diffclip: Leveraging stable diffusion for language grounded 3d classi- fication,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Diffclip: Leveraging stable diffusion for language grounded 3d classi- fication,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.453965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 998d7390-d363-41d9-80cc-93bf85cd8bfe · outbound

This paper cites Hallo: Hierarchical audio- driven visual synthesis for portrait image animation,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Hallo: Hierarchical audio- driven visual synthesis for portrait image animation,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.442423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cb08c2db-9185-40d8-8a55-65f7e3198d9f · outbound

This paper cites Nerf: Representing scenes as neural radiance fields for view synthesis,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Nerf: Representing scenes as neural radiance fields for view synthesis,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.100813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0707b315-6161-42ed-b5ef-1e10ae7d561f · outbound

This paper cites Ad-nerf: Audio driven neural radiance fields for talking head synthesis,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Ad-nerf: Audio driven neural radiance fields for talking head synthesis,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.422257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7f901c67-5c65-423e-a59d-1172277b7f3b · outbound

This paper cites Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.107656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4be9759-ab60-4fa2-aaa8-2f5a2a845b00 · outbound

This paper cites Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.408753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8a0e6a54-7072-4b4c-9d20-2240949b3b43 · outbound

This paper cites SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-10T23:34:38.255084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1e25acc8-5bb8-4b06-8fc8-a7950664aa57 · outbound

This paper cites Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.396409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4046d7a7-ab4e-4a4a-b026-865b773b2614 · outbound

This paper cites GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.122794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c72c8043-001e-4f60-9408-833135136e1f · outbound

This paper cites 3d gaussian splatting for real-time radiance field rendering,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis 3d gaussian splatting for real-time radiance field rendering,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.126840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 170c7cca-7688-4829-a25d-fd9aadc72653 · outbound

This paper cites TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.131215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9467c623-ff47-4f04-ab9c-4b5f8ea913ea · outbound

This paper cites Gaussiantalker: Real-time high- fidelity talking head synthesis with audio-driven 3d gaussian splatting,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Gaussiantalker: Real-time high- fidelity talking head synthesis with audio-driven 3d gaussian splatting,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.377180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f44067fb-38b9-49fe-93f4-d7d6a137097c · outbound

This paper cites Gaussiantalker: Speaker-specific talking head synthesis via 3d gaussian splatting,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Gaussiantalker: Speaker-specific talking head synthesis via 3d gaussian splatting,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.366109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cb1eec3c-6bb3-427e-a62b-ca65fe931004 · outbound

This paper cites Gstalker: Real-time audio-driven talking face generation via deformable gaussian splatting,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Gstalker: Real-time audio-driven talking face generation via deformable gaussian splatting,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.353455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3b874741-d370-4796-a220-1121e9d24818 · outbound

This paper cites Semantic-aware implicit neural audio-driven video portrait generation,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Semantic-aware implicit neural audio-driven video portrait generation,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.340643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 23424211-9a31-431c-8065-29b937c208cd · outbound

This paper cites Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Efficient region-aware neural radiance fields for high-fidelity talking portrait synthesis,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.328246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4a2d8b96-3bad-4314-8ade-eeaf21875d7c · outbound

This paper cites DSSIM: a structural similarity index for floating-point data.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis DSSIM: a structural similarity index for floating-point data

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.152906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 161f97ae-cf8a-4723-8377-a2bb3b774372 · outbound

This paper cites Audio-driven talking head generation,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Audio-driven talking head generation,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.316134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bc2aff7e-4aab-4f20-adb3-e5e979c3d9ae · outbound

This paper cites Adam: A Method for Stochastic Optimization.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Adam: A Method for Stochastic Optimization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.160514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d6f1647-15c1-438f-9a48-f8c55eff45ef · outbound

This paper cites Decoupled weight decay regulariza- tion,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Decoupled weight decay regulariza- tion,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.304382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7ef89ba2-d45a-48b4-9276-a633e9b644f5 · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis The unreasonable effectiveness of deep features as a perceptual metric,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.168149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4075f01-f477-45c2-a07a-2210fbb13024 · outbound

This paper cites Lip movements generation at a glance,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Lip movements generation at a glance,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T23:34:38.285018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1a8e0a5b-5da0-44ae-a05b-1e448b6f2f34 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity,.

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis Image quality assessment: from error visibility to structural similarity,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T23:34:38.175518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.