paper-with-me

홈 › Papers

Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding

2023-11-25 · Ruyang Liu, Jingjia Huang, Wei Gao, Thomas H. Li, Ge Li

Large-scale image-language pretrained models, e.g., CLIP, have demonstrated remarkable proficiency in acquiring general multi-modal knowledge through web-scale image-text data. Despite the impressive performance of image-language models on various image tasks, how to effectively expand them on general video understanding remains an area of ongoing exploration. In this paper, we investigate the image-to-video transferring from the perspective of the model and the data, unveiling two key obstacles impeding the adaptation of image-language models: non-generalizable temporal modeling and partially misaligned video-text data. To address these challenges, we propose Spatial-Temporal Auxiliary Network with Mutual-guided alignment module (Mug-STAN), a simple yet effective framework extending image-text model to diverse video tasks and video-text data.Specifically, STAN adopts a branch structure with decomposed spatial-temporal modules to enable generalizable temporal modeling, while Mug suppresses misalignment by introducing token-wise feature aggregation of either modality from the other. Extensive experimental results verify Mug-STAN significantly improves adaptation of language-image pretrained models such as CLIP and CoCa at both video-text post-pretraining and finetuning stages. With our solution, state-of-the-art zero-shot and finetuning results on various downstream datasets, including MSR-VTT, DiDeMo, LSMDC, Kinetics-400, Something-Something-2, HMDB-51, UCF- 101, and AVA, are achieved. Moreover, by integrating pretrained Mug-STAN with the emerging multimodal dialogue model, we can realize zero-shot video chatting. Codes are available at https://github.com/farewellthree/STAN

📄 PDF Abstract BibTeX arXiv:2311.15075

Code (1)

farewellthree/stan 공식 구현 pytorch

Tasks

Video Understanding

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding

2022-04-15 · ACL 2022 5 · Chan-Jan Hsu, Hung-Yi Lee, Yu Tsao

Transformer-based models are widely used in natural language understanding (NLU) tasks, and multimodal transformers have been effective in visual-language tasks. This study explores distilling visual information from pre…

Natural Language Understanding

Adapting Pretrained Transformer to Lattices for Spoken Language Understanding

2020-11-02 · Chao-Wei Huang, Yun-Nung Chen

Lattices are compact representations that encode multiple hypotheses, such as speech recognition results or different word segmentations. It is shown that encoding lattices as opposed to 1-best results generated by autom…

Natural Language Understandingspeech-recognitionSpeech RecognitionSpoken Language Understanding

Keeping Representation Similarity in Finetuning for Medical Image Analysis

2025-03-10 · Wenqiang Zu, Shenghao Xie, Hao Chen, Yiming Liang 외

Foundation models pretrained on large-scale natural images have been widely used to adapt to medical image analysis through finetuning. This is largely attributed to pretrained representations capturing universal, robust…

image-classificationImage ClassificationMedical Image AnalysisMedical Image Classification

Multimodal Conditionality for Natural Language Generation

2021-09-02 · Michael Sollami, Aashish Jain

Large scale pretrained language models have demonstrated state-of-the-art performance in language understanding tasks. Their application has recently expanded into multimodality learning, leading to improved representati…

DescriptiveLanguage ModelingLanguage ModellingText Generation

Efficiently Adapting Pretrained Language Models To New Languages

2023-11-09 · Zoltan Csaki, Pian Pawakapan, Urmish Thakker, Qiantong Xu

Recent large language models (LLM) exhibit sub-optimal performance on low-resource languages, as the training data of these models is usually dominated by English and other high-resource languages. Furthermore, it is cha…

Cross-Lingual Transfer