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/2toinf/ivm
공식 코드https://github.com/3DAgentWorld/Toolkit-for-Prompt-Compression
공식 코드An Empirical Study on Prompt Compression for Large Language Models
https://github.com/ACL2020Anonymous/SymBERT
공식 코드Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
https://github.com/AIF4S/MediConfusion
공식 코드https://github.com/AIGeeksGroup/3DCoCa
공식 코드https://github.com/AIM-SKKU/QA-TIGER
공식 코드Question-Aware Gaussian Experts for Audio-Visual Question Answering
https://github.com/AIM3-RUC/YouMakeup_Baseline
공식 코드YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos
https://github.com/ASMIftekhar/VSGNet
공식 코드VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions
https://github.com/ATR-DBI/Map-EQA
공식 코드Map-based Modular Approach for Zero-shot Embodied Question Answering
https://github.com/Abhiram4572/mi_bart
공식 코드Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering
https://github.com/Abhishek0697/Detection-of-Hate-Speech-in-Multimodal-Memes
공식 코드https://github.com/AikyamLab/hallucinogen
공식 코드HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models
https://github.com/Aishwarya-NR/LRTA_Perturbed_Dataset
공식 코드https://github.com/AkariAsai/logic_guided_qa
공식 코드Logic-Guided Data Augmentation and Regularization for Consistent Question Answering
https://github.com/Akutagawa1998/LazyBench
공식 코드Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs
https://github.com/Alab-NII/mrc-heuristics
공식 코드https://github.com/Ale9806/eVLLM
공식 코드μ-Bench: A Vision-Language Benchmark for Microscopy Understanding
https://github.com/AleksandrIvchenko/QoE-assesment
공식 코드Study on the Assessment of the Quality of Experience of Streaming Video
https://github.com/AleksandrIvchenko/QoE-models
공식 코드Study on the Assessment of the Quality of Experience of Streaming Video
https://github.com/AlexJJJChen/Climate-Zoo
공식 코드https://github.com/AlexKuhnle/ShapeWorld
공식 코드ShapeWorld - A new test methodology for multimodal language understanding
https://github.com/Archer-Tatsu/VQA-ODV
공식 코드https://github.com/AwellmanZha/M2ConceptBase
공식 코드M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base
https://github.com/BierOne/VQA-AttReg
공식 코드Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
https://github.com/BinWang28/InstructDS
공식 코드https://github.com/Bravo5542/TJSTG
공식 코드Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios
https://github.com/ByungKwanLee/CoLLaVO
공식 코드https://github.com/ByungKwanLee/MoAI
공식 코드MoAI: Mixture of All Intelligence for Large Language and Vision Models
https://github.com/CLARIN-PL/PUGG
공식 코드Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction
https://github.com/CLUEbenchmark/CLUE
공식 코드https://github.com/CLUEbenchmark/FewCLUE
공식 코드https://github.com/CMFiltenborg/lingually_constrained_tracking
공식 코드https://github.com/CSU-JPG/MVPBench
공식 코드Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT
https://github.com/CYandYue/Dentist
공식 코드A Unified Hallucination Mitigation Framework for Large Vision-Language Models
https://github.com/Cadene/block.bootstrap.pytorch
공식 코드BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.