SOTAVerified

Visual Entailment

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 56 papers

TitleStatusHype
VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks—0
VEglue: Testing Visual Entailment Systems via Object-Aligned Joint ErasingCode0
ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks—0
p-Laplacian Adaptation for Generative Pre-trained Vision-Language ModelsCode0
Lightweight In-Context Tuning for Multimodal Unified Models—0
Stop Pre-Training: Adapt Visual-Language Models to Unseen LanguagesCode0
"Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image Captioning—0
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning—0
Few-shot Multimodal Multitask Multilingual Learning—0
Compound Tokens: Channel Fusion for Vision-Language Representation Learning—0
A survey on knowledge-enhanced multimodal learning—0
AlignVE: Visual Entailment Recognition Based on Alignment Relations—0
Pre-training image-language transformers for open-vocabulary tasks—0
Prompt Tuning for Generative Multimodal Pretrained ModelsCode0
Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language ExplanationsCode0
Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering—0
Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks—0
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment—0
Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment—0
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks—0
Logically at Factify 2022: Multimodal Fact Verification—0
Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation—0
How Much Can CLIP Benefit Vision-and-Language Tasks?—0
Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.