English
Related papers

Related papers: Adapting MLLMs for Nuanced Video Retrieval

200 papers

Online video web content is richly multimodal: a single video blends vision, speech, ambient audio, and on-screen text. Retrieval systems typically treat these modalities as independent retrieval sources, which can lead to noisy and subpar…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 David Wan , Han Wang , Elias Stengel-Eskin , Jaemin Cho , Mohit Bansal

The rapid growth of video content demands efficient and precise retrieval systems. While vision-language models (VLMs) excel in representation learning, they often struggle with adaptive, time-sensitive video retrieval. This paper…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yicheng Duan , Xi Huang , Duo Chen

Multimodal retrieval systems typically employ Vision Language Models (VLMs) that encode images and text independently into vectors within a shared embedding space. Despite incorporating text encoders, VLMs consistently underperform…

Information Retrieval · Computer Science 2026-01-22 Xinyuan Zhang , Lina Zhang , Lisung Chen , Guangyao Liu , Shuai Nie , Jiaming Xu , Runyu Shi , Ying Huang , Guoquan Zhang

We address the problem of text-based activity retrieval in video. Given a sentence describing an activity, our task is to retrieve matching clips from an untrimmed video. To capture the inherent structures present in both text and video, we…

Computer Vision and Pattern Recognition · Computer Science 2018-12-27 Huijuan Xu , Kun He , Bryan A. Plummer , Leonid Sigal , Stan Sclaroff , Kate Saenko

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…

Computation and Language · Computer Science 2025-10-20 Qiyu Wu , Shuyang Cui , Satoshi Hayakawa , Wei-Yao Wang , Hiromi Wakaki , Yuki Mitsufuji

We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We…

Machine Learning · Computer Science 2019-06-18 Gil Sadeh , Lior Fritz , Gabi Shalev , Eduard Oks

Audio-text retrieval enables semantic alignment between audio content and natural language queries, supporting applications in multimedia search, accessibility, and surveillance. However, current state-of-the-art approaches struggle with…

Computation and Language · Computer Science 2026-04-28 Meizhu Liu , Matthew Rowe , Amit Agarwal , Michael Avendi , Yassi Abbasi , Hitesh Laxmichand Patel , Paul Li , Kyu J. Han , Tao Sheng , Sujith Ravi , Dan Roth

Visual-semantic embedding aims to learn a joint embedding space where related video and sentence instances are located close to each other. Most existing methods put instances in a single embedding space. However, they struggle to embed…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Huy Manh Nguyen , Tomo Miyazaki , Yoshihiro Sugaya , Shinichiro Omachi

This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Thong Thanh Nguyen

Despite the remarkable success of multimodal large language models (MLLMs) in generative tasks, we observe that they exhibit a counterintuitive deficiency in the zero-shot multimodal retrieval task. In this work, we investigate the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Hengyi Feng , Zeang Sheng , Meiyi Qiang , Yang Li , Wentao Zhang

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Hu Xu , Gargi Ghosh , Po-Yao Huang , Prahal Arora , Masoumeh Aminzadeh , Christoph Feichtenhofer , Florian Metze , Luke Zettlemoyer

The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually…

Computer Vision and Pattern Recognition · Computer Science 2020-07-07 Xun Yang , Jianfeng Dong , Yixin Cao , Xun Wang , Meng Wang , Tat-Seng Chua

Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since…

Computer Vision and Pattern Recognition · Computer Science 2023-12-20 Zhihang Liu , Jun Li , Hongtao Xie , Pandeng Li , Jiannan Ge , Sun-Ao Liu , Guoqing Jin

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models (LLMs) to access multimodal knowledge bases containing both text and visual information such as charts, diagrams, and tables in financial…

Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding tasks. However, they continue to struggle with long-form videos because of an inefficient perception of temporal intervals. Unlike humans, who can…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Chenglin Li , Qianglong Chen , fengtao , Yin Zhang

Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Zhenzhi Wang , Limin Wang , Tao Wu , Tianhao Li , Gangshan Wu

Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches leverage contrastive learning to construct a unified embedding…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Shiyao Yu , Zi-An Wang , Kangning Yin , Zheng Tian , Mingyuan Zhang , Weixin Si , Shihao Zou

Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other…

Computation and Language · Computer Science 2024-06-17 Jari Kolehmainen , Aditya Gourav , Prashanth Gurunath Shivakumar , Yile Gu , Ankur Gandhe , Ariya Rastrow , Grant Strimel , Ivan Bulyko

This paper presents a case study on deploying Large Language Models (LLMs) as an advanced "annotation" mechanism to achieve nuanced content understanding (e.g., discerning content "vibe") at scale within a large-scale industrial short-form…

Partially Relevant Video Retrieval (PRVR) seeks videos where only part of the content matches a text query. Existing methods treat every annotated text-video pair as a positive and all others as negatives, ignoring the rich semantic…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 WonJun Moon , MinSeok Jung , Gilhan Park , Tae-Young Kim , Cheol-Ho Cho , Woojin Jun , Jae-Pil Heo