English
Related papers

Related papers: MILES: Visual BERT Pre-training with Injected Lang…

200 papers

Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Anurag Das , Xinting Hu , Li Jiang , Bernt Schiele

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…

Computation and Language · Computer Science 2021-09-13 Haoran Xu , Benjamin Van Durme , Kenton Murray

Person Re-identification is a research area with significant real world applications. Despite recent progress, existing methods face challenges in robust re-identification in the wild, e.g., by focusing only on a particular modality and on…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Siyuan Huang , Ram Prabhakar , Yuxiang Guo , Rama Chellappa , Cheng Peng

Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Kexue Fu , Peng Gao , ShaoLei Liu , Renrui Zhang , Yu Qiao , Manning Wang

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

To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on…

Computation and Language · Computer Science 2023-05-05 Shitao Xiao , Zheng Liu , Yingxia Shao , Zhao Cao

Standard approaches for video recognition usually operate on the full input videos, which is inefficient due to the widely present spatio-temporal redundancy in videos. Recent progress in masked video modelling, i.e., VideoMAE, has shown…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Zhiwu Qing , Shiwei Zhang , Ziyuan Huang , Xiang Wang , Yuehuan Wang , Yiliang Lv , Changxin Gao , Nong Sang

Encoded representations from a pretrained deep learning model (e.g., BERT text embeddings, penultimate CNN layer activations of an image) convey a rich set of features beneficial for information retrieval. Embeddings for a particular…

Machine Learning · Computer Science 2023-04-24 Hyunjin Choi , Hyunjae Lee , Seongho Joe , Youngjune L. Gwon

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint…

Computer Vision and Pattern Recognition · Computer Science 2019-09-13 Chen Sun , Austin Myers , Carl Vondrick , Kevin Murphy , Cordelia Schmid

Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge such as object motion, 3D geometry, and physical cues. In…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Chenting Wang , Yuhan Zhu , Yicheng Xu , Jiange Yang , Lang Lin , Ziang Yan , Yali Wang , Yi Wang , Limin Wang

Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Wenhao Wu , Zhun Sun , Wanli Ouyang

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Yi Zhu , Yanpeng Zhou , Chunwei Wang , Yang Cao , Jianhua Han , Lu Hou , Hang Xu

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

Computer Vision and Pattern Recognition · Computer Science 2023-07-19 Chong Liu , Yuqi Zhang , Hongsong Wang , Weihua Chen , Fan Wang , Yan Huang , Yi-Dong Shen , Liang Wang

Large-scale pretraining and task-specific fine-tuning is now the standard methodology for many tasks in computer vision and natural language processing. Recently, a multitude of methods have been proposed for pretraining vision and language…

Computation and Language · Computer Science 2021-06-01 Emanuele Bugliarello , Ryan Cotterell , Naoaki Okazaki , Desmond Elliott

Contrastive Language-Image Pretraining (CLIP) efficiently learns visual concepts by pre-training with natural language supervision. CLIP and its visual encoder have been explored on various vision and language tasks and achieve strong…

Computation and Language · Computer Science 2022-10-13 An Yan , Jiacheng Li , Wanrong Zhu , Yujie Lu , William Yang Wang , Julian McAuley

Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, such as CLIP, to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-12 Saurabhchand Bhati , Jesús Villalba , Laureano Moro-Velazquez , Thomas Thebaud , Najim Dehak

We describe a protocol to study text-to-video retrieval training with unlabeled videos, where we assume (i) no access to labels for any videos, i.e., no access to the set of ground-truth captions, but (ii) access to labeled images in the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-29 Lucas Ventura , Cordelia Schmid , Gül Varol

Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for vision tasks, typically through fine-tuning to produce universal representations. However, their performance on video remains…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Issar Tzachor , Dvir Samuel , Rami Ben-Ari

Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…

Computation and Language · Computer Science 2021-09-14 Xiongyi Zhang , Jan-Willem van de Meent , Byron C. Wallace

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Yuxiang Wei , Yabo Zhang , Zhilong Ji , Jinfeng Bai , Lei Zhang , Wangmeng Zuo