Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

natural-language-processing-2

Visual Entailment

3260 papers • 126 benchmarks • 313 datasets

Visual Entailment (VE) - is a task consisting of image-sentence pairs whereby a premise is defined by an image, rather than a natural language sentence as in traditional Textual Entailment tasks. The goal is to predict whether the image semantically entails the text.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in visual-entailment-4

Trend

Dataset

Best Model

Actions

SNLI-VE val

SNLI-VE val

SNLI-VE test

SNLI-VE test

e-SNLI-VE

e-SNLI-VE

Libraries

i

Use these libraries to find visual-entailment-4 models and implementations

2 papers 2,320

Datasets

SNLI-VE

VSR

e-SNLI-VE

Subtasks

No subtasks available.

Most implemented papers

UNITER: UNiversal Image-TExt Representation Learning

Zhe Gan, Linjie Li, Licheng Yu, Yen-Chun Chen, Jingjing Liu, Yu Cheng, Ahmed El Kholy, Faisal Ahmed•Tue Sep 24 2019

UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets is introduced, which can power heterogeneous downstream V+L tasks with joint multimodal embeddings.

2505

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

CoCa: Contrastive Captioners are Image-Text Foundation Models

Vijay Vasudevan, Yonghui Wu, Jiahui Yu, Mojtaba Seyedhosseini, Legg Yeung•Tue May 03 2022

Contrastive Captioner (CoCa), a minimalist design to pretrain an image-text encoder-decoder foundation model jointly with contrastive loss and captioning loss, thereby subsuming model capabilities from contrastive approaches like CLIP and generative methods like SimVLM.

1623 0

How Much Can CLIP Benefit Vision-and-Language Tasks?

Z. Yao, Sheng Shen, K. Keutzer, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Hao Tan, Liunian Harold Li•Mon Jul 12 2021

It is shown that CLIP significantly outperforms widely-used visual encoders trained with in-domain annotated data, such as BottomUp-TopDown, and achieves competitive or better results on diverse V&L tasks, while establishing new state-of-the-art results on Visual Question Answering, Visual Entailment, and V & L Navigation tasks.

479 0

OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Jianxin Ma, Chang Zhou, Jingren Zhou, Hongxia Yang, Shuai Bai, Junyang Lin, Rui Men, Peng Wang, Zhikang Li•Sun Feb 06 2022

OFA is proposed, a Task-Agnostic and Modality- agnostic framework that supports Task Comprehensiveness and achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni- modal tasks.

1022 0

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Zhe Gan, Linjie Li, Jingjing Liu, Yu Cheng, Yen-Chun Chen, Chen Zhu•Wed Jun 10 2020

To enable large-scale training, VILLA adopts the "free" adversarial training strategy, and combines it with KL-divergence-based regularization to promote higher invariance in the embedding space.

539 0

Distilled Dual-Encoder Model for Vision-Language Understanding

Bing Qin, Ming Liu, Zekun Wang, Furu Wei, Wenhui Wang, Haichao Zhu•Wed Dec 15 2021

DiDE, a framework that distills the knowledge of the fusion-encoder teacher model into the dual-encoding student model, and encourages the student not only to mimic the predictions of teacher, but also to calculate the cross-modal attention distributions and align with the teacher.

35 0

Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning

Jianlong Fu, Zhaoyang Zeng, Yupan Huang, Zhicheng Huang, Bei Liu, Dongmei Fu•Tue Apr 06 2021

This paper proposes SOHO to "Seeing Out of tHe bOx" that takes a whole image as input, and learns vision-language representation in an end-to-end manner, and does not require bounding box annotations which enables inference 10 times faster than region-based approaches.

303 0

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning

Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Y. Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji•Thu Dec 14 2023

A new task of Chart Caption Factual Error Correction is established and CHARTVE, a model for visual entailment that outperforms proprietary and open-source LVLMs in evaluating factual consistency is introduced, and an interpretable two-stage framework that excels at correcting factual errors is proposed.

52 0

Visual Entailment Task for Visually-Grounded Language Learning

Ning Xie, Derek Doran, Farley Lai, Asim Kadav•Sun Nov 25 2018

EVE and several other state-of-the-art visual question answering (VQA) based models are evaluated on the SNLI-VE dataset, facilitating grounded language understanding and providing insights on how modern VQA based models perform.

59 0

Adding a benchmark result helps the community track progress.

Visual Entailment | State-of-the-Art