20 results for “Video Retrieval”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Yang Liu, Qianqian Xu, Peisong Wen, Siran Dai +1 more
The paper proposes a training-free framework, Visual Representation-Guided Video-LLM Reasoning, to perform composed video retrieval by using visual examples and text instructions, achieving strong per…
Reno Kriz, David Etter, Alexander Martin, Cameron Carpenter +10 more
The authors release a large-scale dataset of raw videos, MultiVENT-Raw, to facilitate progress in information retrieval and machine understanding of raw video content.
The paper proposes a zero-shot reason-then-retrieve pipeline using Qwen3.5-27B to solve the challenging task of composed video retrieval (CoVR-R), achieving high performance on both validation and bli…
Qixin Hu, Shuai Yang, Wei Huang, Song Han +1 more
LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…
David Yuchen Wang, Haoying Li, Hailun Xu, Wei Chee Yew +5 more
This paper proposes a novel video deduplication framework that efficiently reduces online repetition rates while maintaining high precision.
Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee +1 more
The paper proposes COVRAG, a depth-based memory retrieval framework that maximizes the coverage of target-view regions to significantly improve long-term geometric consistency in autoregressive long v…
Alexander Martin, Dengjia Zhang, Joel Brogan, Francis Ferraro +6 more
The paper presents the results of the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR).
Shihang Zhang, Mingjin Kuai, Ye Wei, Zhen Zhang +1 more
GIRL-DETR introduces Gradient-Isolated Reinforcement Learning to enhance temporal localization in lightweight Video Moment Retrieval models, achieving high accuracy by decoupling feature representatio…
Yinsong Xu, Wei Jing, Liuxin Zhang, Wanjun Lv +1 more
The paper proposes a unified framework that decouples long-video reasoning into semantic and visual evidence, significantly improving performance on the HD-EPIC VQA Challenge.
Weijian Jian, Siyang Chen, Yuguang Yang, Yajun Zhang +3 more
This paper introduces GARRET, a region-retrieval framework for multimodal retrieval-augmented generation over visually rich documents.
The paper proposes Dynamic Adapter Routing (DAR), a novel method that significantly improves continual multimodal retrieval by adaptively selecting and merging specialized adapters.
Lixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng +2 more
The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…
This paper proposes a scheme to optimize model sparsity in neural sparse retrieval using adaptive strategies.
Ziyu Song, Jiaming Fang, Kuangyu Li, Tuo Xia +1 more
This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.
Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang +2 more
The paper proposes Conditional Retrieval Alignment (CoRA), a gradient-free framework for task-conditioned retrieval using a frozen encoder and paired inputs and outputs.
The paper proposes a framework called LARE to improve image retrieval in crowded scenes by modeling low-attention regions.
Yilin Wen, Rong Yang, Xiaojia Chang, Hong Sun +10 more
The paper presents CoRe, a query rewriter system that uses the deployed multimodal relevance model as its source for reward and closes the simulation-production gap, allowing for weekly redeployment.
Yue Feng, Jingjing Li, Qijia Lu, Wei Ji +8 more
This paper addresses the challenge of detecting and explaining AI-manipulated segments within long, untrimmed videos by proposing a new benchmark and a coarse-to-fine forensic detection framework.
This paper proposes an end-to-end pipeline for luggage re-identification from multiple video streams in real-world environments.