paper-with-me

Papers

Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation

2023-03-21 · CVPR 2023 1 · Sara Sarto, Manuele Barraco, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. Our source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.

📄 PDF Abstract BibTeX arXiv:2303.12112

Code (1)

aimagelab/pacscore 공식 구현 pytorch

Tasks

Contrastive LearningImage CaptioningVideo Captioning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Contrastive Learning 설명 없음
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

RCA-NOC: Relative Contrastive Alignment for Novel Object Captioning

2023-12-11 · ICCV 2023 1 · Jiashuo Fan, Yaoyuan Liang, Leyao Liu, ShaoLun Huang 외

In this paper, we introduce a novel approach to novel object captioning which employs relative contrastive learning to learn visual and semantic alignment. Our approach maximizes compatibility between regions and object …

Contrastive LearningObjectTAG

Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training

2024-10-09 · Sara Sarto, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi 외

Despite significant advancements in caption generation, existing evaluation metrics often fail to capture the full quality or fine-grained details of captions. This is mainly due to their reliance on non-specific human-w…

Caption GenerationContrastive Learning

Supervised Contrastive Frame Aggregation for Video Representation Learning

2025-12-14 · Shaif Chowdhury, Mushfika Rahman, Greg Hamerly arxiv

We propose a supervised contrastive learning framework for video representation learning that leverages temporally global context. We introduce a video to image aggregation strategy that spatially arranges multiple frame…

Representation LearningContrastive LearningData Augmentation

Style-Aware Contrastive Learning for Multi-Style Image Captioning

2023-01-26 · Yucheng Zhou, Guodong Long

Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style. However, existing methods overlook the relationship between linguist…

Contrastive LearningImage CaptioningRetrievalTriplet

OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning

2024-04-04 · Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing

We propose the new task 'open-world video instance segmentation and captioning'. It requires to detect, segment, track and describe with rich captions never before seen objects. This challenging task can be addressed by …

DescriptiveDiversityInstance SegmentationLanguage Modeling+7