中文
相关论文

相关论文: Towards Universal Video Retrieval: Generalizing Vi…

200 篇论文

Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model, where queries and candidates can consist of pure text, images, or a combination of both. Previous work has attempted to adopt…

计算与语言 · 计算机科学 2025-04-02 Xin Zhang , Yanzhao Zhang , Wen Xie , Mingxin Li , Ziqi Dai , Dingkun Long , Pengjun Xie , Meishan Zhang , Wenjie Li , Min Zhang

Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. However, existing multimodal embeddings like VLM2Vec, E5-V, GME…

计算机视觉与模式识别 · 计算机科学 2025-07-08 Rui Meng , Ziyan Jiang , Ye Liu , Mingyi Su , Xinyi Yang , Yuepeng Fu , Can Qin , Zeyuan Chen , Ran Xu , Caiming Xiong , Yingbo Zhou , Wenhu Chen , Semih Yavuz

Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Jianhui Wei , Xiaotian Zhang , Yichen Li , Yuan Wang , Yan Zhang , Ziyi Chen , Zhihang Tang , Wei Xu , Zuozhu Liu

Modern video retrieval systems are expected to handle diverse tasks ranging from corpus-level retrieval, fine-grained moment localization to flexible multimodal querying. Specialized architectures achieve strong retrieval performance by…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Shaunak Halbe , Bhagyashree Puranik , Jayakrishnan Unnikrishnan , Kushan Thakkar , Vimal Bhat , Toufiq Parag

Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely limited by the lack of robust evaluation benchmarks and high-quality preference data. To…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Yuancheng Wei , Linli Yao , Lei Li , Haojie Zhang , Hao Zhou , Fandong Meng , Xu Sun

Universal multimodal retrieval (UMR), which aims to address complex retrieval tasks where both queries and candidates span diverse modalities, has been significantly advanced by the emergence of MLLMs. While state-of-the-art MLLM-based…

信息检索 · 计算机科学 2026-02-17 Xiaojie Li , Chu Li , Shi-Zhe Chen , Xi Chen

The real world is dynamic, yet most image fusion methods process static frames independently, ignoring temporal correlations in videos and leading to flickering and temporal inconsistency. To address this, we propose Unified Video Fusion…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Zixiang Zhao , Haowen Bai , Bingxin Ke , Yukun Cui , Lilun Deng , Yulun Zhang , Kai Zhang , Konrad Schindler

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias…

计算机视觉与模式识别 · 计算机科学 2022-05-18 Xun Wang , Bingqing Ke , Xuanping Li , Fangyu Liu , Mingyu Zhang , Xiao Liang , Qiushi Xiao , Cheng Luo , Yue Yu

Recent works in video quality assessment (VQA) typically employ monolithic models that typically predict a single quality score for each test video. These approaches cannot provide diagnostic, interpretable feedback, offering little insight…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Chen Feng , Tianhao Peng , Fan Zhang , David Bull

We propose the Multi-modal Untrimmed Video Retrieval task, along with a new benchmark (MUVR) to advance video retrieval for long-video platforms. MUVR aims to retrieve untrimmed videos containing relevant segments using multi-modal queries.…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Yue Feng , Jinwei Hu , Qijia Lu , Jiawei Niu , Li Tan , Shuo Yuan , Ziyi Yan , Yizhen Jia , Qingzhi He , Shiping Ge , Ethan Q. Chen , Wentong Li , Limin Wang , Jie Qin

Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can be broadly divided into two categories: early-fusion…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Juan Li , Chuanghao Ding , Xujie Zhang , Cam-Tu Nguyen

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Jiehui Huang , Yuechen Zhang , Xu He , Yuan Gao , Zhi Cen , Bin Xia , Yan Zhou , Xin Tao , Pengfei Wan , Jiaya Jia

Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing…

计算机视觉与模式识别 · 计算机科学 2026-01-22 Yufan Deng , Zilin Pan , Hongyu Zhang , Xiaojie Li , Ruoqing Hu , Yufei Ding , Yiming Zou , Yan Zeng , Daquan Zhou

With the growth of high-quality data and advancement in visual pre-training paradigms, Video Foundation Models (VFMs) have made significant progress recently, demonstrating their remarkable performance on traditional video understanding…

计算机视觉与模式识别 · 计算机科学 2024-07-10 Xinhao Li , Zhenpeng Huang , Jing Wang , Kunchang Li , Limin Wang

Learning-based underwater image enhancement (UIE) methods have made great progress. However, the lack of large-scale and high-quality paired training samples has become the main bottleneck hindering the development of UIE. The inter-frame…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Yaofeng Xie , Lingwei Kong , Kai Chen , Ziqiang Zheng , Xiao Yu , Zhibin Yu , Bing Zheng

Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…

We propose a realistic scenario for the unsupervised video learning where neither task boundaries nor labels are provided when learning a succession of tasks. We also provide a non-parametric learning solution for the under-explored problem…

计算机视觉与模式识别 · 计算机科学 2025-09-01 Nattapong Kurpukdee , Adrian G. Bors

Fine-grained and instance-level recognition methods are commonly trained and evaluated on specific domains, in a model per domain scenario. Such an approach, however, is impractical in real large-scale applications. In this work, we address…

Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow-based generation due to text-visual token imbalance and the…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Jiabin Luo , Junhui Lin , Zeyu Zhang , Biao Wu , Meng Fang , Ling Chen , Hao Tang

Multi-modal retrieval has seen tremendous progress with the development of vision-language models. However, further improving these models require additional labelled data which is a huge manual effort. In this paper, we propose a framework…

计算机视觉与模式识别 · 计算机科学 2023-09-26 Avinash Madasu , Estelle Aflalo , Gabriela Ben Melech Stan , Shachar Rosenman , Shao-Yen Tseng , Gedas Bertasius , Vasudev Lal
‹ 上一页 1 2 3 10 下一页 ›