Paper Citation Record · LEDGER

PercepCap: Video Captioner with Structured Spatio-Temporal Perception

As of 22 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2607.20389.

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

pith.paper-citation-record.v1
2607.20389 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:02:03.322619Z

measured 43 of 43 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 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

43 of 43 outbound references displayed

verified exact0
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c8393da9-816f-444a-a576-4e81edcb2b57 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.126290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd3d746c-0d31-4308-b2fd-fd6163347d76 · outbound

This paper cites Qwen2.5-VL Technical Report.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.131618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ac68c0-9b2a-436d-a235-09b1308c211f · outbound

This paper cites Activitynet: A large- scale video benchmark for human activity understanding.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Activitynet: A large- scale video benchmark for human activity understanding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.136729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a2ab20c-32cd-4207-afa5-4298ace80d12 · outbound

This paper cites AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.141536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7ca5978-b6db-44e8-a69b-e6aeb2321a94 · outbound

This paper cites VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.146589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e0cd9cf-368b-4956-b544-b5bbd374e380 · outbound

This paper cites Vidbridge-r1: Bridging QA and captioning for RL-based video understanding models with intermediate proxy tasks.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Vidbridge-r1: Bridging QA and captioning for RL-based video understanding models with intermediate proxy tasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.151348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddef46af-9b02-46dd-962e-ae0c6a8e9869 · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.156349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2793345b-030b-4ce0-b2ca-e126fe1c59c6 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.161003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e773c642-522a-4375-8026-1b9b52077a05 · outbound

This paper cites ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.165633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60e1131a-e19f-4b5c-8192-c0af7254f2dd · outbound

This paper cites Gemini 3 Flash: frontier intelligence built for speed.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Gemini 3 Flash: frontier intelligence built for speed

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.170486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94bdbe3d-c78a-48d8-9813-755d914c131b · outbound

This paper cites MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.174754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d82e4985-eb75-4f10-b1a4-a9ed2fb4d011 · outbound

This paper cites VIDEOP2R: Video Understanding from Perception to Reasoning.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception VIDEOP2R: Video Understanding from Perception to Reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.179245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da513b2d-6f92-4f17-b154-02f62604a93d · outbound

This paper cites Kimi-VL Technical Report.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Kimi-VL Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.183827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b71761-28b1-4e0c-94a8-e8ab46ebfcca · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.188685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0afa628-5378-4971-a9fa-dec576fd2943 · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.193696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 138fd2ab-267f-4afa-8eab-76f6fbbcd211 · outbound

This paper cites Video-llava: Learning united visual representation by alignment before projection.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Video-llava: Learning united visual representation by alignment before projection

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.198541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03a3248e-05ee-4294-9b22-3a62ec7e38fd · outbound

This paper cites MiMo-VL technical report, 2025.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception MiMo-VL technical report, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.203392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32461e25-5782-49b6-a010-1cc41b265953 · outbound

This paper cites VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.207694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53729e25-2423-4d2d-9905-c59511a9fde8 · outbound

This paper cites an unresolved cited work.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.212359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a389b9d5-8ab3-4146-9ff9-23a00909d5e7 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, 2026.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Qwen3.5: Towards native multimodal agents, 2026

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.216944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe942059-c849-4b64-9137-101848421199 · outbound

This paper cites Timechat: A time-sensitive multimodal large language model for long video understanding.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Timechat: A time-sensitive multimodal large language model for long video understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.221848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a40ff84-6af1-4376-960f-a9988d8681c8 · outbound

This paper cites Qwen3 technical report, 2025.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Qwen3 technical report, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.226653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0f1f7c-4481-4f16-9324-f6b1129e406d · outbound

This paper cites Gemini 3.1 pro: A smarter model for your most complex tasks, 2026.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Gemini 3.1 pro: A smarter model for your most complex tasks, 2026

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.230903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bef3798-b3c7-487e-941a-c8e92139deae · outbound

This paper cites Reft: Reasoning with reinforced fine-tuning.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Reft: Reasoning with reinforced fine-tuning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.235083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 922b3bc3-e978-43ae-b0ff-2453d87e706f · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.239135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4661c7-a4c4-4aeb-8791-76af60bd4357 · outbound

This paper cites Tarsier: Recipes for Training and Evaluating Large Video Description Models.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Tarsier: Recipes for Training and Evaluating Large Video Description Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.243631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5cf8e40-d2b5-4a4b-acff-aa37c7d95ec2 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.248142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6a1186f-f177-43b6-91e8-07412c4b0314 · outbound

This paper cites YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.252658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403360a5-3898-4e15-b88c-8971218457de · outbound

This paper cites CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.257559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a9f074-7e9a-4d3e-b4f4-83053fe8869b · outbound

This paper cites Videochat-r1.5: Visual test-time scaling to reinforce multimodal reasoning by iterative perception.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Videochat-r1.5: Visual test-time scaling to reinforce multimodal reasoning by iterative perception

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.262030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7deff422-86ba-4f42-a199-15919089ae58 · outbound

This paper cites TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.266407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de40401e-a909-464c-817d-d64cb75620bf · outbound

This paper cites Timelens: Rethinking video temporal grounding with multimodal llms.CoRR, abs/2512.14698, 2025.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Timelens: Rethinking video temporal grounding with multimodal llms.CoRR, abs/2512.14698, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.271785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aa51a07-7303-412e-9152-bd644c668234 · outbound

This paper cites perception.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception perception

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.276162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f72a2dfa-011d-49dc-a372-c0d2efa55601 · outbound

This paper cites an unresolved cited work.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.280832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516049fe-0bb4-49ef-a319-813a14a8e89d · outbound

This paper cites These extracted textual contents define which entities and events must appear in the perception trace.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception These extracted textual contents define which entities and events must appear in the perception trace

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.285330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46c5d169-24b9-4bae-85e2-2b1f2ae60a82 · outbound

This paper cites 14 Figure 5: Constructed training example from Caption-Anchored Perception Data Construction.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception 14 Figure 5: Constructed training example from Caption-Anchored Perception Data Construction

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.290370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d487d8-a1ea-47bf-9f0b-2becda677cf1 · outbound

This paper cites objects". - The value of.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception objects". - The value of

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.294926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a5bb5e-573c-4fb4-95cb-3cb8e7635d20 · outbound

This paper cites - The same real-world instance MUST keep the same id across frames.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception - The same real-world instance MUST keep the same id across frames

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.299431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec7877d2-57b9-4db1-8847-142a7023c16f · outbound

This paper cites an unresolved cited work.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.304452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e5937c-4035-4979-9a5f-42c853934163 · outbound

This paper cites - bbox_2d: [xmin, ymin, xmax, ymax] in relative pixel coordinates, range [0, 1000].

PercepCap: Video Captioner with Structured Spatio-Temporal Perception - bbox_2d: [xmin, ymin, xmax, ymax] in relative pixel coordinates, range [0, 1000]

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.309760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eefe8180-7335-4187-a559-1eab0c4047e6 · outbound

This paper cites an unresolved cited work.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.313844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06653c42-c7b0-4e5d-8f5c-a112c2d4dcfd · outbound

This paper cites an unresolved cited work.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.318125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8b9f358-5f34-4e56-be07-028c06531626 · outbound

This paper cites objects":[{.

PercepCap: Video Captioner with Structured Spatio-Temporal Perception objects":[{

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T10:02:03.322619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.