https://github.com/vis-nlp/chartqapro
공식 코드ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering
Papers with Code 아카이브
Visual Question Answering (VQA)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 9
- 평가표
- 76
- 보존된 평가 기록
- 725
Visual Question Answering (VQA) is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.
Image Source: visualqa.org
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/vis-nlp/unichart
공식 코드UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
https://github.com/vision-cair/dochaystacks
공식 코드Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
https://github.com/vision-cair/minigpt-4
공식 코드MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
https://github.com/vision-cair/minigpt-med
공식 코드MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis
https://github.com/vision-x-nyu/thinking-in-space
공식 코드Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
https://github.com/visionxlab/lrs-vqa
공식 코드https://github.com/vistec-ai/wangchanlion
공식 코드https://github.com/visual-haystacks/vhs_benchmark
공식 코드Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark
https://github.com/visual-text-QA/VTQA-Demo
공식 코드VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning
https://github.com/visualaikhu/missing-avqa
공식 코드https://github.com/vita-group/o1-planning
공식 코드On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability
https://github.com/vityavitalich/imad
공식 코드https://github.com/vl2g/KaLMA
공식 코드https://github.com/vlgiitr/Are-VLMs-Really-Blind
공식 코드https://github.com/vmichals/FigureQA-baseline
공식 코드https://github.com/vmurahari3/visdial-bert
공식 코드Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline
https://github.com/vqaonline/vqaonlinevisualization
공식 코드Fully Authentic Visual Question Answering Dataset from Online Communities
https://github.com/vqassessment/bvqi
공식 코드Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion
https://github.com/vqassessment/dover
공식 코드https://github.com/vqassessment/maxvqa
공식 코드https://github.com/vt-nlp/socratic-questioning
공식 코드The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models
https://github.com/vuhoangminh/vqa_medical
공식 코드A Question-Centric Model for Visual Question Answering in Medical Imaging
https://github.com/wad3birch/AutoBench-V
공식 코드AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?
https://github.com/walkerworldpeace/mllmerging
공식 코드Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging
https://github.com/waltonfuture/InstructionGPT-4
공식 코드InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4
https://github.com/wangjiarui153/AIGV-Assessor
공식 코드https://github.com/wangzheallen/STL-VQA
공식 코드Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering
https://github.com/wayveai/lingoqa
공식 코드https://github.com/weichenzh/open3dvqa
공식 코드https://github.com/weihuanglin/inf-llava
공식 코드INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model
https://github.com/weiyifan1023/MVGE
공식 코드Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question
https://github.com/wenboown/generative-ai-for-semiconductor-physical-design
공식 코드Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications
https://github.com/wenchuan-zhang/patho-r1
공식 코드Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner
https://github.com/wenhuang2000/vhtest
공식 코드https://github.com/wenjinw/latin-prompt
공식 코드Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.