English
Related papers

Related papers: A CLIP-Hitchhiker's Guide to Long Video Retrieval

200 papers

Mixed modality search -- retrieving information across a heterogeneous corpus composed of images, texts, and multimodal documents -- is an important yet underexplored real-world application. In this work, we investigate how contrastive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Binxu Li , Yuhui Zhang , Xiaohan Wang , Weixin Liang , Ludwig Schmidt , Serena Yeung-Levy

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Tiancheng Gu , Kaicheng Yang , Xiang An , Ziyong Feng , Dongnan Liu , Weidong Cai , Jiankang Deng

While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task. We design a new…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Shen Yan , Xuehan Xiong , Arsha Nagrani , Anurag Arnab , Zhonghao Wang , Weina Ge , David Ross , Cordelia Schmid

Video summarization aims to extract keyframes/shots from a long video. Previous methods mainly take diversity and representativeness of generated summaries as prior knowledge in algorithm design. In this paper, we formulate video…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Yudong Jiang , Kaixu Cui , Bo Peng , Changliang Xu

We introduce EditCLIP, a novel representation-learning approach for image editing. Our method learns a unified representation of edits by jointly encoding an input image and its edited counterpart, effectively capturing their…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Qian Wang , Aleksandar Cvejic , Abdelrahman Eldesokey , Peter Wonka

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Haocheng Dai , Sarang Joshi

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Mengmeng Wang , Jiazheng Xing , Boyuan Jiang , Jun Chen , Jianbiao Mei , Xingxing Zuo , Guang Dai , Jingdong Wang , Yong Liu

We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to the…

Computer Vision and Pattern Recognition · Computer Science 2016-05-17 Basura Fernando , Efstratios Gavves , Jose Oramas , Amir Ghodrati , Tinne Tuytelaars

Developing video captioning models is computationally expensive. The dynamic nature of video also complicates the design of multimodal models that can effectively caption these sequences. However, we find that by using minimal computational…

Computer Vision and Pattern Recognition · Computer Science 2025-02-20 Chunhui Zhang , Yiren Jian , Zhongyu Ouyang , Soroush Vosoughi

Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning…

Computer Vision and Pattern Recognition · Computer Science 2023-01-27 Ruyang Liu , Jingjia Huang , Ge Li , Jiashi Feng , Xinglong Wu , Thomas H. Li

Video segmentation is a popular task, but applying image segmentation models frame-by-frame to videos does not preserve temporal consistency. In this paper, we propose a method to extend a query-based image segmentation model to video using…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Tsubasa Mizuno , Toru Tamaki

Recent advancements in video large language models (Video LLMs) have significantly advanced the field of video question answering (VideoQA). While existing methods perform well on short videos, they often struggle with long-range reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Mustafa Chasmai , Gauri Jagatap , Gouthaman KV , Grant Van Horn , Subhransu Maji , Andrea Fanelli

Large-scale datasets have been pivotal to the advancements of deep learning models in recent years, but training on such large datasets invariably incurs substantial storage and computational overhead. Meanwhile, real-world datasets often…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Suorong Yang , Peng Ye , Wanli Ouyang , Dongzhan Zhou , Furao Shen

Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-18 Rabah Ouldnoughi , Chia-Wen Kuo , Zsolt Kira

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

Machine Learning · Computer Science 2024-09-02 Lakshmi Nair

The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Guanqi Zhan , Yuanpei Liu , Kai Han , Weidi Xie , Andrew Zisserman

Contrastive Language-Image Pretraining (CLIP) is widely used to train models to align images and texts in a common embedding space by mapping them to fixed-sized vectors. These models are key to multimodal information retrieval and related…

Until recently, the general corpus of CLIP-type fundamental models has widely explored either the retrieval of short descriptions or the classification of objects in the scene as SINGLE-object image classification task. The same holds for…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Advik Sinha , Saurabh Atreya , Aashutosh A , Sk Aziz Ali , Abhijit Das

We investigate the success conditions for compositional generalization of CLIP models on real-world data through performance prediction. Prior work shows that CLIP requires exponentially more pretraining data for linear performance gains on…

Machine Learning · Computer Science 2025-02-26 Thaddäus Wiedemer , Yash Sharma , Ameya Prabhu , Matthias Bethge , Wieland Brendel

Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Jue Wang , Anoop Cherian , Fatih Porikli , Stephen Gould
‹ Prev 1 3 4 5 6 7 10 Next ›