English
Related papers

Related papers: Online pre-training with long-form videos

200 papers

We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units which are deep both spatially and temporally. Our model…

Machine Learning · Computer Science 2016-02-16 Shikhar Sharma , Ryan Kiros , Ruslan Salakhutdinov

In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance. However, online methods have their inherent…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Junfeng Wu , Qihao Liu , Yi Jiang , Song Bai , Alan Yuille , Xiang Bai

Our work tackles the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs). Despite the effectiveness of contrastive learning, the substantial computational resources…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Jinhong Lin , Cheng-En Wu , Yibing Wei , Pedro Morgado

Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion information is represented as optical flows in most of the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Chuanbo Tang , Xihua Sheng , Zhuoyuan Li , Haotian Zhang , Li Li , Dong Liu

Understanding human behavior is an important problem in the pursuit of visual intelligence. A challenge in this endeavor is the extensive and costly effort required to accurately label action segments. To address this issue, we consider…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Seth Z. Zhao , Reza Ghoddoosian , Isht Dwivedi , Nakul Agarwal , Behzad Dariush

Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Yuncong Yang , Jiawei Ma , Shiyuan Huang , Long Chen , Xudong Lin , Guangxing Han , Shih-Fu Chang

The objective of this paper is visual-only self-supervised video representation learning. We make the following contributions: (i) we investigate the benefit of adding semantic-class positives to instance-based Info Noise Contrastive…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Tengda Han , Weidi Xie , Andrew Zisserman

In recent years, interest in synthetic data has grown, particularly in the context of pre-training the image modality to support a range of computer vision tasks, including object classification, medical imaging etc. Previous work has…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Davyd Svyezhentsev , George Retsinas , Petros Maragos

Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos. This enables the video…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Ziyi Lin , Shijie Geng , Renrui Zhang , Peng Gao , Gerard de Melo , Xiaogang Wang , Jifeng Dai , Yu Qiao , Hongsheng Li

Concepts involved in long-form videos such as people, objects, and their interactions, can be viewed as following an implicit prior. They are notably complex and continue to pose challenges to be comprehensively learned. In recent years,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Jinheng Xie , Jiajun Feng , Zhaoxu Tian , Kevin Qinghong Lin , Yawen Huang , Xi Xia , Nanxu Gong , Xu Zuo , Jiaqi Yang , Yefeng Zheng , Mike Zheng Shou

Contrastive Language-Image Pretraining (CLIP) has demonstrated strong zero-shot performance across diverse downstream text-image tasks. Existing CLIP methods typically optimize a contrastive objective using negative samples drawn from each…

Machine Learning · Computer Science 2025-10-23 Haotian Sun , Yitong Li , Yuchen Zhuang , Niao He , Hanjun Dai , Bo Dai

The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc. However, existing methods commonly process the frames…

Computer Vision and Pattern Recognition · Computer Science 2020-10-01 Jie Shao , Xin Wen , Bingchen Zhao , Xiangyang Xue

Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval. However, these models have not been adapted to video,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Santiago Castro , Fabian Caba Heilbron

We present a self-supervised learning approach to learn audio-visual representations from video and audio. Our method uses contrastive learning for cross-modal discrimination of video from audio and vice-versa. We show that optimizing for…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Pedro Morgado , Nuno Vasconcelos , Ishan Misra

Human action recognition in videos is a critical task with significant implications for numerous applications, including surveillance, sports analytics, and healthcare. The challenge lies in creating models that are both precise in their…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Yufei Xie

Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Chao-Yuan Wu , Manzil Zaheer , Hexiang Hu , R. Manmatha , Alexander J. Smola , Philipp Krähenbühl

Unsupervised learning of latent motion from Internet videos is crucial for robot learning. Existing discrete methods generally mitigate the shortcut learning caused by extracting excessive static backgrounds through vector quantization with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Jiange Yang , Yansong Shi , Haoyi Zhu , Mingyu Liu , Kaijing Ma , Yating Wang , Gangshan Wu , Tong He , Limin Wang

Contrastive language-image pre-training (CLIP) serves as a de-facto standard to align images and texts. Nonetheless, the loose correlation between images and texts of web-crawled data renders the contrastive objective data inefficient and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Jinghao Zhou , Li Dong , Zhe Gan , Lijuan Wang , Furu Wei

We introduce OmniSource, a novel framework for leveraging web data to train video recognition models. OmniSource overcomes the barriers between data formats, such as images, short videos, and long untrimmed videos for webly-supervised…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Haodong Duan , Yue Zhao , Yuanjun Xiong , Wentao Liu , Dahua Lin

Contrastive learning has delivered impressive results for various tasks in the self-supervised regime. However, existing approaches optimize for learning representations specific to downstream scenarios, i.e., \textit{global}…

Machine Learning · Computer Science 2021-10-29 Shuang Ma , Zhaoyang Zeng , Daniel McDuff , Yale Song