SVFSearch is the first open benchmark for short-video frame search in the Chinese gaming domain, providing a frozen retrieval environment and showing performance gaps of 13-29 points between direct QA models, practical agents, and oracle knowledge.
arXiv preprint arXiv:2410.08182 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
R3G improves vision-centric visual question answering by generating reasoning plans to guide two-stage image retrieval and reranking, achieving state-of-the-art results on MRAG-Bench across six MLLM backbones.
VisRet improves text-to-image retrieval by generating images from text queries and then retrieving within the image modality, reporting average nDCG@30 gains of 0.125 with CLIP and 0.121 with E5-V across four benchmarks.
CoGR-MoE improves VQA by using concept-guided expert routing with option feature reweighting and contrastive learning to achieve consistent yet flexible reasoning across answer options.
citing papers explorer
-
SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain
SVFSearch is the first open benchmark for short-video frame search in the Chinese gaming domain, providing a frozen retrieval environment and showing performance gaps of 13-29 points between direct QA models, practical agents, and oracle knowledge.
-
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
-
R3G: A Reasoning--Retrieval--Reranking Framework for Vision-Centric Answer Generation
R3G improves vision-centric visual question answering by generating reasoning plans to guide two-stage image retrieval and reranking, achieving state-of-the-art results on MRAG-Bench across six MLLM backbones.
-
VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
VisRet improves text-to-image retrieval by generating images from text queries and then retrieving within the image modality, reporting average nDCG@30 gains of 0.125 with CLIP and 0.121 with E5-V across four benchmarks.
-
CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering
CoGR-MoE improves VQA by using concept-guided expert routing with option feature reweighting and contrastive learning to achieve consistent yet flexible reasoning across answer options.