pith. sign in

arxiv: 2606.01104 · v1 · pith:FNNEJJH7new · submitted 2026-05-31 · 💻 cs.CV

Adaptive Dense Evidence Refinement for Video Relational Reasoning for VRR-QA Challenge

classification 💻 cs.CV
keywords systemadaptivedenseaccuracyanswersaverageevidencefinal
0
0 comments X
read the original abstract

VRR-QA evaluates whether video-language systems can infer spatial, temporal, viewpoint, depth, and visibility relations that are not always resolved by a single frame. We present an inference-only system built around adaptive test-time computation. The system first answers each question with a direct video-language model pass, then uses multiple lightweight views to find unstable questions. Only these difficult questions are routed to a high-budget dense evidence module that constructs timestamped frame observations, relation-specific probes, candidate verification, and conservative temporal aggregation. This design separates two problems that are often confused in video question answering: finding plausible alternative answers and deciding when a current answer should actually be changed. On the test split, the final system obtains 90.07 average accuracy and 87.81 macro average accuracy. The report focuses on the final test system and the implementation settings required to reproduce the adaptive dense verifier.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.