Paper Citation Record · LEDGER

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings

As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2502.06012.

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

pith.paper-citation-record.v1
2502.06012 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T17:09:18.680337Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

28 of 28 outbound references displayed

verified exact1
verified fuzzy12
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c9307a56-36dc-43b4-add9-feb4284afeb0 · outbound

This paper cites Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:19.091720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 47ddadcb-d087-4eb1-86d6-06434784b766 · outbound

This paper cites Combining Residual Networks with LSTMs for Lipreading,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Combining Residual Networks with LSTMs for Lipreading,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:19.074488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4b4a39e7-a127-4a86-8281-b656e5e37680 · outbound

This paper cites Active Speakers in Context,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Active Speakers in Context,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:19.056810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c1136810-d3a3-402f-819d-de2d8f289c8e · outbound

This paper cites ASD-Transformer: Efficient Active Speaker Detection Using Self And Multimodal Transformers,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings ASD-Transformer: Efficient Active Speaker Detection Using Self And Multimodal Transformers,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.557553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a840b7-088d-4d2b-8965-d29d9c87d898 · outbound

This paper cites Hello! My name is... Buffy.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Hello! My name is... Buffy

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.564019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09db0d23-3d42-46be-82b3-4652a159bc36 · outbound

This paper cites MAAS: Multi-modal Assignation for Active Speaker Detection,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings MAAS: Multi-modal Assignation for Active Speaker Detection,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.569695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d87e82d8-2b51-441b-bd18-8c5834c0465f · outbound

This paper cites Target Active Speaker Detection with Audio-visual Cues,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Target Active Speaker Detection with Audio-visual Cues,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.576552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f99e09c-4b40-4109-b829-75bf046371a9 · outbound

This paper cites Ava Active Speaker: An Audio-Visual Dataset for Active Speaker De- tection,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Ava Active Speaker: An Audio-Visual Dataset for Active Speaker De- tection,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.581381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac4f4dfd-872a-45dc-891f-bf0e2010181a · outbound

This paper cites Improving Audiovisual Active Speaker Detection in Egocentric Recordings with the Data-Efficient Image Transformer,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Improving Audiovisual Active Speaker Detection in Egocentric Recordings with the Data-Efficient Image Transformer,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.988225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 21ef0601-6f5b-49da-a5f2-e9ad0d680dfc · outbound

This paper cites Ego4D: Around the World in 3,000 Hours of Egocentric Video,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Ego4D: Around the World in 3,000 Hours of Egocentric Video,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.590424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36daf742-d0ff-45dd-9b53-f0257df901ad · outbound

This paper cites End-to-End Active Speaker Detection, author=Juan Leon Alcazar and Moritz Cordes and Chen Zhao and Bernard Ghanem,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings End-to-End Active Speaker Detection, author=Juan Leon Alcazar and Moritz Cordes and Chen Zhao and Bernard Ghanem,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.962200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 04974023-5009-4843-8fbd-f24c2d8d0f4f · outbound

This paper cites How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.600233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb15f594-52b5-4eb8-a1a7-cfaff91a8646 · outbound

This paper cites A Light Weight Model for Active Speaker Detection,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings A Light Weight Model for Active Speaker Detection,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.605275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 672bc6f7-3ec5-4460-969d-ccaff54edcc4 · outbound

This paper cites LoCoNet: Long-Short Context Network for Active Speaker Detection,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings LoCoNet: Long-Short Context Network for Active Speaker Detection,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.609862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ba33c77-cfdf-4790-afb3-92d924c42c6a · outbound

This paper cites Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.615111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7985d78f-7386-4bc4-bfe9-64a21de0d797 · outbound

This paper cites ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.619710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9c9d624-29e9-44ae-9f97-53500061f0d5 · outbound

This paper cites Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-08T17:09:18.766401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7eda9495-fd1b-4522-bbbf-c9191089d911 · outbound

This paper cites Efficient Personal V oice Activity Detection with Wake Word Reference Speech,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Efficient Personal V oice Activity Detection with Wake Word Reference Speech,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.904791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9fe9b316-a7de-4906-a1bf-4b9883193f88 · outbound

This paper cites V oxCeleb: A Large-Scale Speaker Identification Dataset,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings V oxCeleb: A Large-Scale Speaker Identification Dataset,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.636126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8792db4-8364-4ab7-9d03-35e7e6946e63 · outbound

This paper cites Ring Loss: Convex Feature Normalization for Face Recognition,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Ring Loss: Convex Feature Normalization for Face Recognition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.887481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c34fe6a-207f-4beb-a411-a14f2c7ce986 · outbound

This paper cites ArcFace: Additive Angular Margin Loss for Deep Face Recognition,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings ArcFace: Additive Angular Margin Loss for Deep Face Recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.870149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 786bcc82-f5bf-4bc3-acaa-a9ff2a5cfed2 · outbound

This paper cites SphereFace: Deep Hypersphere Embedding for Face Recognition,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings SphereFace: Deep Hypersphere Embedding for Face Recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.853270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e72199d4-0acd-4d42-85b9-72cdffc84cec · outbound

This paper cites CosFace: Large Margin Cosine Loss for Deep Face Recognition,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings CosFace: Large Margin Cosine Loss for Deep Face Recognition,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.835514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 599cbf32-1274-4f73-a393-10805583039d · outbound

This paper cites Partial FC: Training 10 Million Identities on a Single Ma- chine,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Partial FC: Training 10 Million Identities on a Single Ma- chine,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.819850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 72c51122-fd47-4229-8770-65d107bced6b · outbound

This paper cites Attention is All you Need,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Attention is All you Need,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T17:09:18.803865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 497d1872-2ede-461d-b85a-85a0398a7510 · outbound

This paper cites Robust Object Recogni- tion Through Symbiotic Deep Learning In Mobile Robots,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Robust Object Recogni- tion Through Symbiotic Deep Learning In Mobile Robots,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.670905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a683ce62-4341-4bca-9986-5edeae446089 · outbound

This paper cites The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results,.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.675378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23a06e36-1d2c-49dd-80aa-aab1d90798dc · outbound

This paper cites Technical Report for Ego4D Long Term Action Anticipation Challenge 2023.

Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings Technical Report for Ego4D Long Term Action Anticipation Challenge 2023

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T17:09:18.680337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.