paper-with-me

홈 › Papers

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

2021-09-28 · EMNLP 2021 11 · Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, Christoph Feichtenhofer

We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.

📄 PDF Abstract BibTeX arXiv:2109.14084

Code (2)

pytorch/fairseq 공식 구현 pytorch
facebookresearch/fairseq pytorch

Tasks

Action LocalizationAction SegmentationLong Video Retrieval (Background Removed)RetrievalTemporal Action LocalizationTemporal Relation ExtractionVideo RetrievalZero-Shot Video Retrieval

Similar Papers 제목 키워드 기반

VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models

2024-10-01 · Jiapeng Wang, Chengyu Wang, Kunzhe Huang, Jun Huang 외

Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descript…

Hallucinationtext similarityVideo DescriptionVideo Retrieval

Test of Time: Instilling Video-Language Models with a Sense of Time

2023-01-05 · CVPR 2023 1 · Piyush Bagad, Makarand Tapaswi, Cees G. M. Snoek

Modelling and understanding time remains a challenge in contemporary video understanding models. With language emerging as a key driver towards powerful generalization, it is imperative for foundational video-language mo…

Video-Text RetrievalVideo Understanding

VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners

2022-12-09 · Shen Yan, Tao Zhu, ZiRui Wang, Yuan Cao 외

We explore an efficient approach to establish a foundational video-text model. We present VideoCoCa that maximally reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with m…

Question AnsweringRetrievalText to Video RetrievalVideo Captioning+7

Contrastive Video-Language Learning with Fine-grained Frame Sampling

2022-10-10 · Zixu Wang, Yujie Zhong, Yishu Miao, Lin Ma 외

Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level …

Question AnsweringRepresentation LearningRetrievalVideo Question Answering+1

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

2023-02-01 · Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu 외

Contrastive Language-Image Pretraining (CLIP) has demonstrated impressive zero-shot learning abilities for image understanding, yet limited effort has been made to investigate CLIP for zero-shot video recognition. We int…

Action RecognitionContinual LearningVideo RecognitionZero-Shot Learning