paper-with-me

Papers

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

2026-05-31 · Yuyang Sun, Yongliang Wu, Xingyu Zhu, Yuxia Chen, Zhenxiang Jiang, Yangguang Ji, Wenbo Zhu, Yanxi Shi, Jay Wu, Shuo Wang, Xu Yang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.01104

Code (0)

등록된 구현이 없습니다.

Tasks

Video Question AnsweringRelational Reasoning

Similar Papers 제목 키워드 기반

AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding

2026-05-13 · Xiao Yang, Yingzhe Ma, Haoxuan Yu, Zixin Li 외 arxiv

Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets t…

Computational Efficiency

DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition

2025-08-07 · Haijing Liu, Tao Pu, Hefeng Wu, Keze Wang 외 arxiv

Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify multiple seen and unseen object categories within an image, requiring both precise intra-class localization to pinpoint objects and effective inter-class …

A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning

2026-01-29 · Jiate Liu, Zebin Chen, Shaobo Qiao, Mingchen Ju 외 arxiv

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two…

Question AnsweringKnowledge Graphs

Question-Aware Evidence Ledgers for Video Relational Reasoning

2026-06-01 · Yilin Ou, Mengshi Qi, Huadong Ma arxiv

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. …

Relational Reasoning

Exploring Relational Context for Multi-Task Dense Prediction

2021-04-28 · ICCV 2021 10 · David Bruggemann, Menelaos Kanakis, Anton Obukhov, Stamatios Georgoulis 외

The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream t…

Neural Architecture SearchPredictionSemantic Segmentation