paper-with-me

홈 › Papers

FILS: Self-Supervised Video Feature Prediction In Semantic Language Space

2024-06-05 · Mona Ahmadian, Frank Guerin, Andrew Gilbert

This paper demonstrates a self-supervised approach for learning semantic video representations. Recent vision studies show that a masking strategy for vision and natural language supervision has contributed to developing transferable visual pretraining. Our goal is to achieve a more semantic video representation by leveraging the text related to the video content during the pretraining in a fully self-supervised manner. To this end, we present FILS, a novel self-supervised video Feature prediction In semantic Language Space (FILS). The vision model can capture valuable structured information by correctly predicting masked feature semantics in language space. It is learned using a patch-wise video-text contrastive strategy, in which the text representations act as prototypes for transforming vision features into a language space, which are then used as targets for semantically meaningful feature prediction using our masked encoder-decoder structure. FILS demonstrates remarkable transferability on downstream action recognition tasks, achieving state-of-the-art on challenging egocentric datasets, like Epic-Kitchens, Something-SomethingV2, Charades-Ego, and EGTEA, using ViT-Base. Our efficient method requires less computation and smaller batches compared to previous works.

📄 PDF Abstract BibTeX arXiv:2406.03447

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionDecoder

Similar Papers 제목 키워드 기반

Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction

2018-11-28 · Longlong Jing, Xiaodong Yang, Jingen Liu, YingLi Tian

The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper,…

Action RecognitionPredictionSelf-Supervised Action RecognitionTemporal Action Localization+1

Hierarchical Self-supervised Representation Learning for Movie Understanding

2022-04-06 · CVPR 2022 1 · Fanyi Xiao, Kaustav Kundu, Joseph Tighe, Davide Modolo

Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical se…

Action RecognitionContrastive LearningRepresentation Learning

Representation Learning with Video Deep InfoMax

2020-07-27 · R. Devon Hjelm, Philip Bachman

Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse …

Action RecognitionData AugmentationRepresentation LearningSelf-Supervised Learning

Collaboratively Self-supervised Video Representation Learning for Action Recognition

2024-01-15 · Jie Zhang, Zhifan Wan, Lanqing Hu, Stephen Lin 외

Considering the close connection between action recognition and human pose estimation, we design a Collaboratively Self-supervised Video Representation (CSVR) learning framework specific to action recognition by jointly …

Action RecognitionPose EstimationPose PredictionRepresentation Learning

Pixel-level Correspondence for Self-Supervised Learning from Video

2022-07-08 · Yash Sharma, Yi Zhu, Chris Russell, Thomas Brox

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Corres…

Contrastive Learningimage-classificationImage ClassificationOptical Flow Estimation+3