Question-Aware Evidence Ledgers for Video Relational Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916075349737472 |
|---|---|
| author | Ou, Yilin Qi, Mengshi Ma, Huadong |
| author_facet | Ou, Yilin Qi, Mengshi Ma, Huadong |
| contents | The VRR-QA challenge evaluates visual relational reasoning in videos, where answers often depend on implicit spatial relations, event boundaries, target identity, and dialogue context rather than a single salient frame. We present a test-time reasoning pipeline built around a strong GPT-5.5 video QA solver and a set of question-aware evidence ledgers. The initial solver answers each question from a uniform video representation, while routed ledgers are prompted to make the required targets, count units, reference frames, and temporal or spatial scope explicit for counting, spatial, endpoint, viewpoint, and dialogue reasoning. External tools such as open-vocabulary detection, depth cues, pair crops, ASR, and scene-graph ledgers are used only as evidence sources. A conservative gate keeps the current answer unless independent evidence uniquely supports a different option. The final evidence-gated pipeline achieves 92.95% overall accuracy and 93.79% macro accuracy on the challenge test split. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_02506 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Question-Aware Evidence Ledgers for Video Relational Reasoning Ou, Yilin Qi, Mengshi Ma, Huadong Computer Vision and Pattern Recognition The VRR-QA challenge evaluates visual relational reasoning in videos, where answers often depend on implicit spatial relations, event boundaries, target identity, and dialogue context rather than a single salient frame. We present a test-time reasoning pipeline built around a strong GPT-5.5 video QA solver and a set of question-aware evidence ledgers. The initial solver answers each question from a uniform video representation, while routed ledgers are prompted to make the required targets, count units, reference frames, and temporal or spatial scope explicit for counting, spatial, endpoint, viewpoint, and dialogue reasoning. External tools such as open-vocabulary detection, depth cues, pair crops, ASR, and scene-graph ledgers are used only as evidence sources. A conservative gate keeps the current answer unless independent evidence uniquely supports a different option. The final evidence-gated pipeline achieves 92.95% overall accuracy and 93.79% macro accuracy on the challenge test split. |
| title | Question-Aware Evidence Ledgers for Video Relational Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2606.02506 |