Papers with Code 아카이브
Visual Commonsense Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 7
- 보존된 평가 기록
- 10
Image source: Visual Commonsense Reasoning
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Generative Visual Commonsense Answering and Explaining with Generative Scene Graph Constructing
How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey
Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor
Improving Visual Commonsense in Language Models via Multiple Image Generation
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?
ALGO: Object-Grounded Visual Commonsense Reasoning for Open-World Egocentric Action Recognition
Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models
Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR
EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning
ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
Improving Vision-and-Language Reasoning via Spatial Relations Modeling
ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models
A Survey on Interpretable Cross-modal Reasoning
GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning
GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions
CAVL: Learning Contrastive and Adaptive Representations of Vision and Language
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
Learning to Agree on Vision Attention for Visual Commonsense Reasoning
Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning
VASR: Visual Analogies of Situation Recognition
A survey on knowledge-enhanced multimodal learning
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
ILLUME: Rationalizing Vision-Language Models through Human Interactions
On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
Super-Prompting: Utilizing Model-Independent Contextual Data to Reduce Data Annotation Required in Visual Commonsense Tasks
Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks
Attention Mechanism based Cognition-level Scene Understanding
VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers
All in One: Exploring Unified Video-Language Pre-training
Joint Answering and Explanation for Visual Commonsense Reasoning
CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks
MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound
SGEITL: Scene Graph Enhanced Image-Text Learning for Visual Commonsense Reasoning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.