中文
相关论文

相关论文: The Devil is in the Distributions: Explicit Modeli…

200 篇论文

Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is…

计算机视觉与模式识别 · 计算机科学 2023-08-28 Bang Yang , Fenglin Liu , Xian Wu , Yaowei Wang , Xu Sun , Yuexian Zou

Image caption generation is one of the most challenging problems at the intersection of vision and language domains. In this work, we propose a realistic captioning task where the input scenes may incorporate visual objects with no…

计算机视觉与模式识别 · 计算机科学 2022-07-04 Berkan Demirel , Ramazan Gokberk Cinbis

We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has…

计算机视觉与模式识别 · 计算机科学 2022-07-29 Yoad Tewel , Yoav Shalev , Roy Nadler , Idan Schwartz , Lior Wolf

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language…

计算机视觉与模式识别 · 计算机科学 2024-01-05 Longtian Qiu , Shan Ning , Xuming He

Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation…

计算机视觉与模式识别 · 计算机科学 2023-07-13 Yongrae Jo , Seongyun Lee , Aiden SJ Lee , Hyunji Lee , Hanseok Oh , Minjoon Seo

Zero-shot video captioning aims to generate sentences for describing videos without training the model on video-text pairs, which remains underexplored. Existing zero-shot image captioning methods typically adopt a text-only training…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Zeyu Pan , Ping Li , Wenxiao Wang

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…

计算机视觉与模式识别 · 计算机科学 2024-04-29 Lucas Ventura , Cordelia Schmid , Gül Varol

Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image…

计算机视觉与模式识别 · 计算机科学 2024-09-12 Dan Song , Xinwei Fu , Ning Liu , Weizhi Nie , Wenhui Li , Lanjun Wang , You Yang , Anan Liu

Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within…

计算机视觉与模式识别 · 计算机科学 2019-08-02 Berkan Demirel , Ramazan Gokberk Cinbis , Nazli Ikizler-Cinbis

Large-scale pre-trained multi-modal models (e.g., CLIP) demonstrate strong zero-shot transfer capability in many discriminative tasks. Their adaptation to zero-shot image-conditioned text generation tasks has drawn increasing interest.…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Wei Li , Linchao Zhu , Longyin Wen , Yi Yang

Given the features of a video, recurrent neural networks can be used to automatically generate a caption for the video. Existing methods for video captioning have at least three limitations. First, semantic information has been widely…

计算机视觉与模式识别 · 计算机科学 2021-02-15 Haoran Chen , Ke Lin , Alexander Maye , Jianming Li , Xiaolin Hu

Zero-shot audio captioning aims at automatically generating descriptive textual captions for audio content without prior training for this task. Different from speech recognition which translates audio content that contains spoken language…

音频与语音处理 · 电气工程与系统科学 2023-11-15 Leonard Salewski , Stefan Fauth , A. Sophia Koepke , Zeynep Akata

Zero-shot action recognition relies on transferring knowledge from vision-language models to unseen actions using semantic descriptions. While recent methods focus on temporal modeling or architectural adaptations to handle video data, we…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Salman Iqbal , Waheed Rehman

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks…

计算机视觉与模式识别 · 计算机科学 2022-11-15 Junyang Wang , Yi Zhang , Ming Yan , Ji Zhang , Jitao Sang

This paper presents a novel approach to Zero-Shot Action Recognition. Recent works have explored the detection and classification of objects to obtain semantic information from videos with remarkable performance. Inspired by them, we…

计算机视觉与模式识别 · 计算机科学 2023-09-12 Valter Estevam , Rayson Laroca , David Menotti , Helio Pedrini

The task of audio captioning is similar in essence to tasks such as image and video captioning. However, it has received much less attention. We propose three desiderata for captioning audio -- (i) fluency of the generated text, (ii)…

声音 · 计算机科学 2023-09-08 Tal Shaharabany , Ariel Shaulov , Lior Wolf

Video captioning is a challenging task since it requires generating sentences describing various diverse and complex videos. Existing video captioning models lack adequate visual representation due to the neglect of the existence of gaps…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Mingkang Tang , Zhanyu Wang , Zhenhua Liu , Fengyun Rao , Dian Li , Xiu Li

The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…

计算机视觉与模式识别 · 计算机科学 2022-08-09 Roni Paiss , Hila Chefer , Lior Wolf

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two…

声音 · 计算机科学 2024-06-11 Yiming Zhang , Xuenan Xu , Ruoyi Du , Haohe Liu , Yuan Dong , Zheng-Hua Tan , Wenwu Wang , Zhanyu Ma

Zero-shot image captioning (IC) without well-paired image-text data can be divided into two categories, training-free and text-only-training. Generally, these two types of methods realize zero-shot IC by integrating pretrained…

计算机视觉与模式识别 · 计算机科学 2024-03-07 Zequn Zeng , Yan Xie , Hao Zhang , Chiyu Chen , Zhengjue Wang , Bo Chen
‹ 上一页 1 2 3 10 下一页 ›