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/Junjue-Wang/EarthVQA
공식 코드https://github.com/JunweiLiang/FVTA_MemexQA
공식 코드https://github.com/KLUE-benchmark/KLUE
공식 코드https://github.com/KazutoshiShinoda/VQAG
공식 코드https://github.com/Kevinz-code/SeVa
공식 코드https://github.com/LLaVA-VL/LLaVA-Plus-Codebase
공식 코드LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
https://github.com/LZ-CH/DSPNet
공식 코드DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
https://github.com/LaVi-Lab/Video-3D-LLM
공식 코드Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding
https://github.com/LeoLee7/Directional_guidance
공식 코드Right this way: Can VLMs Guide Us to See More to Answer Questions?
https://github.com/Linvyl/DAM-QA
공식 코드Describe Anything Model for Visual Question Answering on Text-rich Images
https://github.com/LiqunChen0606/Graph-Optimal-Transport
공식 코드https://github.com/Luffy03/UniBiomed
공식 코드UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation
https://github.com/LuoweiZhou/VLP
공식 코드Unified Vision-Language Pre-Training for Image Captioning and VQA
https://github.com/MAGIC-AI4Med/ChestX-Reasoner
공식 코드https://github.com/MILVLG/activitynet-qa
공식 코드ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
https://github.com/MILVLG/mcan-vqa
공식 코드Deep Modular Co-Attention Networks for Visual Question Answering
https://github.com/MILVLG/mmnas
공식 코드https://github.com/MM-IR/DualVGR-VideoQA
공식 코드DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
https://github.com/MSR3D/MSR3D
공식 코드https://github.com/MalvinaNikandrou/contvqa
공식 코드Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering
https://github.com/MalvinaNikandrou/crope
공식 코드CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts
https://github.com/MalvinaNikandrou/mafed
공식 코드Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation
https://github.com/MapEval/MapEval-API
공식 코드MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
https://github.com/MapEval/MapEval-Textual
공식 코드MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
https://github.com/MapEval/MapEval-Visual
공식 코드MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
https://github.com/MarcBS/VIBIKNet
공식 코드VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering
https://github.com/McGill-NLP/AURORA
공식 코드Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
https://github.com/Microsoft/SDNet
공식 코드SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
https://github.com/MiliLab/GeoLLaVA-8K
공식 코드GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
https://github.com/Mingxiao-Li/DMMGR
공식 코드https://github.com/MuyeHuang/EvoChart
공식 코드EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding
https://github.com/MuyeHuang/VProChart
공식 코드https://github.com/NKU-IIPLab/BMRC
공식 코드Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction
https://github.com/NNReasoning/What-Can-Neural-Networks-Reason-About
공식 코드https://github.com/NUS-HPC-AI-Lab/SGL
공식 코드A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.