English
Related papers

Related papers: Multimodal Knowledge Alignment with Reinforcement …

200 papers

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Qiying Yu , Quan Sun , Xiaosong Zhang , Yufeng Cui , Fan Zhang , Yue Cao , Xinlong Wang , Jingjing Liu

While speech emotion recognition (SER) research has made significant progress, achieving generalization across various corpora continues to pose a problem. We propose a novel domain adaptation technique that embodies a multitask framework…

Computation and Language · Computer Science 2023-10-10 Chung-Soo Ahn , Jagath C. Rajapakse , Rajib Rana

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Machine Learning · Computer Science 2025-04-04 Artyom Gadetsky , Andrei Atanov , Yulun Jiang , Zhitong Gao , Ghazal Hosseini Mighan , Amir Zamir , Maria Brbic

Utilizing a shared embedding space, emerging multimodal models exhibit unprecedented zero-shot capabilities. However, the shared embedding space could lead to new vulnerabilities if different modalities can be misaligned. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Shaeke Salman , Md Montasir Bin Shams , Xiuwen Liu

Zero-shot learning is the problem of predicting instances over classes not seen during training. One approach to zero-shot learning is providing auxiliary class information to the model. Prior work along this vein have largely used…

Machine Learning · Computer Science 2023-02-01 Austin W. Hanjie , Ameet Deshpande , Karthik Narasimhan

The growing number of action classes has posed a new challenge for video understanding, making Zero-Shot Action Recognition (ZSAR) a thriving direction. The ZSAR task aims to recognize target (unseen) actions without training examples by…

Computer Vision and Pattern Recognition · Computer Science 2021-08-20 Shizhe Chen , Dong Huang

Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Vladislav Lialin , Stephen Rawls , David Chan , Shalini Ghosh , Anna Rumshisky , Wael Hamza

Vision models trained on multimodal datasets can benefit from the wide availability of large image-caption datasets. A recent model (CLIP) was found to generalize well in zero-shot and transfer learning settings. This could imply that…

Artificial Intelligence · Computer Science 2021-09-16 Benjamin Devillers , Bhavin Choksi , Romain Bielawski , Rufin VanRullen

In this paper, we propose a new approach to learn multimodal multilingual embeddings for matching images and their relevant captions in two languages. We combine two existing objective functions to make images and captions close in a joint…

Computation and Language · Computer Science 2020-11-02 Alireza Mohammadshahi , Remi Lebret , Karl Aberer

Multimodal self-supervised learning is getting more and more attention as it allows not only to train large networks without human supervision but also to search and retrieve data across various modalities. In this context, this paper…

Recognizing characters and predicting speakers of dialogue are critical for comic processing tasks, such as voice generation or translation. However, because characters vary by comic title, supervised learning approaches like training…

Multimedia · Computer Science 2024-09-06 Yingxuan Li , Ryota Hinami , Kiyoharu Aizawa , Yusuke Matsui

Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…

Sound · Computer Science 2022-06-13 Duygu Dogan , Huang Xie , Toni Heittola , Tuomas Virtanen

Despite Multimodal Large Language Models (MLLMs) showing promising results on general zero-shot image classification tasks, fine-grained image classification remains challenging. It demands precise attention to subtle visual details to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Yunqi Hong , Sohyun An , Andrew Bai , Neil Y. C. Lin , Cho-Jui Hsieh

In recent literature, few-shot classification has predominantly been defined by the N-way k-shot meta-learning problem. Models designed for this purpose are usually trained to excel on standard benchmarks following a restricted setup,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Constance Ferragu , Philomene Chagniot , Vincent Coyette

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…

Computation and Language · Computer Science 2022-10-19 Kunbo Ding , Weijie Liu , Yuejian Fang , Weiquan Mao , Zhe Zhao , Tao Zhu , Haoyan Liu , Rong Tian , Yiren Chen

Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results. However, cross-lingual embedding space mapping is usually studied in static word-level…

Computation and Language · Computer Science 2021-09-08 Haoran Xu , Philipp Koehn

Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…

Computer Vision and Pattern Recognition · Computer Science 2021-03-01 Marimuthu Kalimuthu , Aditya Mogadala , Marius Mosbach , Dietrich Klakow

Large multilingual language models such as mBERT or XLM-R enable zero-shot cross-lingual transfer in various IR and NLP tasks. Cao et al. (2020) proposed a data- and compute-efficient method for cross-lingual adjustment of mBERT that uses a…

Computation and Language · Computer Science 2023-11-01 Pavel Efimov , Leonid Boytsov , Elena Arslanova , Pavel Braslavski

The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Noam Rotstein , David Bensaid , Shaked Brody , Roy Ganz , Ron Kimmel

The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Donggeun Kim , Yujin Jo , Myungjoo Lee , Taesup Kim