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/cooelf/AwesomeMRC
공식 코드https://github.com/cooelf/SemBERT
공식 코드https://github.com/cooelf/subMrc
공식 코드https://github.com/cooelf/subword_seg
공식 코드https://github.com/cooldawnant/infochartqa
공식 코드InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
https://github.com/copenlu/spanex
공식 코드https://github.com/cos4007/grape_demonstrations
공식 코드https://github.com/cpystan/wsi-vqa
공식 코드WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering
https://github.com/cratileo/d2r
공식 코드https://github.com/cse-ai-lab/RealCQA
공식 코드RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic
https://github.com/csebuetnlp/illusionvqa
공식 코드IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
https://github.com/csuhan/onellm
공식 코드https://github.com/cvi-szu/facebench
공식 코드https://github.com/cvi-szu/qa-clims
공식 코드Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation
https://github.com/czczup/vit-adapter
공식 코드https://github.com/czzzzzzzzzzzzzzzzz/vgat
공식 코드https://github.com/d-ailin/clip-guided-decoding
공식 코드https://github.com/dair-iitd/TourismQA
공식 코드Joint Spatio-Textual Reasoning for Answering Tourism Questions
https://github.com/dalcalab/voxel
공식 코드VoxelPrompt: A Vision-Language Agent for Grounded Medical Image Analysis
https://github.com/dali-does/clevr-math
공식 코드CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning
https://github.com/damithdr/questionanswering
공식 코드https://github.com/damo-nlp-sg/pmr
공식 코드https://github.com/damo-nlp-sg/vcd
공식 코드Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
https://github.com/damo-nlp-sg/video-llama
공식 코드Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
https://github.com/damo-nlp-sg/videollama2
공식 코드VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
https://github.com/dandelin/vilt
공식 코드ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
https://github.com/danielgordon10/thor-iqa-cvpr-2018
공식 코드https://github.com/danilo-perico/guided_navigation_qsr
공식 코드Guided Navigation from Multiple Viewpoints using Qualitative Spatial Reasoning
https://github.com/dariad/rczoo
공식 코드https://github.com/datascienceuibk/arabicaqa
공식 코드ArabicaQA: A Comprehensive Dataset for Arabic Question Answering
https://github.com/datascienceuibk/chroniclingamericaqa
공식 코드https://github.com/davidmascharka/tbd-nets
공식 코드Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
https://github.com/dayihengliu/CRQDA
공식 코드Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
https://github.com/dayuyang1999/zeqr
공식 코드ZeQR: Zero-shot Query Reformulation for Conversational Search
https://github.com/dcdmllm/hyperllava
공식 코드HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.