Paper Citation Record · LEDGER

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects

As of 22 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2510.14904.

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

pith.paper-citation-record.v1
2510.14904 v4

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T09:31:56.230128Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T22:00:28.350003Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T17:27:15.695591Z

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b9d496f5-0135-4d66-9a52-e266713f2900 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:54.671015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5cb5944-ad01-445f-9ada-49d3245f2506 · outbound

This paper cites Qwen Technical Report.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Qwen Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:54.979216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1f49450-7e1b-424f-b3e3-caf108aba6aa · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.130506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c61aa5-734c-4aec-b0a5-643ae63bd371 · outbound

This paper cites Mask2Former for Video Instance Segmentation.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Mask2Former for Video Instance Segmentation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.211242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0f2e32d-d78b-47c8-962d-16790570e484 · outbound

This paper cites MOT16: A Benchmark for Multi-Object Tracking.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects MOT16: A Benchmark for Multi-Object Tracking

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.405737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f2d587-583a-4d8d-ab65-175b7edd4ba3 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.677230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c086e104-ba0c-4d83-871c-b98f3eecf8f9 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects OPT: Open Pre-trained Transformer Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.764860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b28ff36-1485-409a-977a-e2fd82a4212d · outbound

This paper cites Objects as Points.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Objects as Points

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.854600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df0af9d0-9f62-4bb3-a8cb-6124ff427a92 · outbound

This paper cites We attribute this difference to the numerous objects that disappear for a significant number of frames in the long videos of VidSTG.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects We attribute this difference to the numerous objects that disappear for a significant number of frames in the long videos of VidSTG

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.968091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f73a68d5-7146-42a6-9c2a-747a8c1d5d89 · outbound

This paper cites pair of tongs.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects pair of tongs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:56.055146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e257921a-b5e1-4351-805f-d89416021cfc · outbound

This paper cites bottle":.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects bottle":

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:56.125904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c70f8275-a183-47bf-ae31-e5005b7c144c · outbound

This paper cites For VidSTG/VLN/BenSMOT experiments we use video-level tuning for captioning with temporal aggregation, with Tagg = 32/8/8 respectively.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects For VidSTG/VLN/BenSMOT experiments we use video-level tuning for captioning with temporal aggregation, with Tagg = 32/8/8 respectively

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:56.230128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b19bb7-47ed-45df-af26-832d62963239 · outbound

This paper cites Dreamix: Video Diffusion Models are General Video Editors.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Dreamix: Video Diffusion Models are General Video Editors

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.488204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c31615e6-fe7c-4042-9204-7fcb77738f34 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Gemini: A Family of Highly Capable Multimodal Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.556728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 484453aa-2b37-403e-91e9-67c6d07ab0b1 · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.057137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46532c84-7337-422b-933d-91342ba3ec0f · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:54.874954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc5e43c7-6ca4-42bb-9704-686e15bb2390 · outbound

This paper cites GPT-4 Technical Report.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects GPT-4 Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:54.797674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f1efc0-2eac-420c-bf07-6137a9194470 · outbound

This paper cites The Llama 3 Herd of Models.

CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects The Llama 3 Herd of Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T09:31:55.311502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f69ea9cf-2ddc-4df9-b101-ba497e1521bf · inbound

Watch, Remember, Reason: Human-View Video Understanding with MLLMs cites this paper.

Watch, Remember, Reason: Human-View Video Understanding with MLLMs CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects

Reference 119

Resolution: verified exact; local_arxiv, observed 2026-07-02T17:27:15.697142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.