https://github.com/opengvlab/internvl-mmdetseg
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
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/p1k0pan/ICD
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
https://github.com/pasrichashivam/Convnets_Grad-CAM_Grad-CAM-PlusPlus_Keras_tensorflow-2
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/patil-suraj/question_generation
https://github.com/peizeli96/MHys
Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering
https://github.com/peizeli96/Object-attribute-matters-in-visual-question-answering
https://github.com/pengfeiliheu/mumc
PathVQA: 30000+ Questions for Medical Visual Question Answering
https://github.com/peteanderson80/Up-Down-Captioner
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
https://github.com/phanav/upsaclay-hygieia
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/phellonchen/DMRM
Dual Attention Networks for Visual Reference Resolution in Visual Dialog
https://github.com/phisad/keras-hicoatt
Hierarchical Question-Image Co-Attention for Visual Question Answering
https://github.com/piaosonglin1985/tf-faster-rcnn
https://github.com/pku-yuangroup/languagebind
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
https://github.com/pku-yuangroup/video-bench
https://github.com/pliang279/multiviz
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
https://github.com/prajjwal1/autodial
https://github.com/pramodkaushik/np_analysis
https://github.com/pramodkaushik/visual_qa_analysis
Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
https://github.com/princeton-nlp/helmet
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
https://github.com/princeton-vl/Princeton365
https://github.com/priyavrat-misra/xrays-and-gradcam
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/pwc-1/Paper-10
Unifying Vision, Text, and Layout for Universal Document Processing
https://github.com/pwc-1/Paper-8/tree/main/blip
https://github.com/pwc-1/Paper-9/tree/main/2/minigpt4
https://github.com/pwc-1/Paper-9/tree/main/5/visual_bert
VisualBERT: A Simple and Performant Baseline for Vision and Language
https://github.com/pwc-1/Paper-9/tree/main/5/xmod
Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model
https://github.com/pwc-1/Paper-9/tree/main/6/CAJ/src/models
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
https://github.com/pwc-1/Paper-9/tree/main/instructblip
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
https://github.com/pwc-1/Paper-9/tree/main/layoutlmv2
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
https://github.com/pwc-1/Paper-9/tree/main/layoutlmv3
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
https://github.com/pwc-1/Paper-9/tree/main/lxmert
https://github.com/pytorch/captum
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/qbetterk/parlai
https://github.com/qiujihao19/artemis
https://github.com/qizekun/ReCon
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/qizekun/SoFar
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.