Papers with Code 아카이브
Visual Entailment
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 19
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks
Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation
Understanding Figurative Meaning through Explainable Visual Entailment
MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition
p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models
Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
Good Questions Help Zero-Shot Image Reasoning
Lightweight In-Context Tuning for Multimodal Unified Models
Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages
"Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image Captioning
I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
Few-shot Multimodal Multitask Multilingual Learning
Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift
Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations
Compound Tokens: Channel Fusion for Vision-Language Representation Learning
A survey on knowledge-enhanced multimodal learning
I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision
AlignVE: Visual Entailment Recognition Based on Alignment Relations
MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
Pre-training image-language transformers for open-vocabulary tasks
Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment
Prompt Tuning for Generative Multimodal Pretrained Models
Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations
MixGen: A New Multi-Modal Data Augmentation
CoCa: Contrastive Captioners are Image-Text Foundation Models
Answer-Me: Multi-Task Open-Vocabulary Visual Question Answering
Visual Spatial Reasoning
Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks
Fine-Grained Visual Entailment
CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment
NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.