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/yiqings/rvt
공식 코드https://github.com/yixuan423/compressed-face-videos-quality-assessment
공식 코드Perceptual Quality Assessment of Face Video Compression: A Benchmark and An Effective Method
https://github.com/yiyangzhou/csr
공식 코드https://github.com/yiyangzhou/lure
공식 코드Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
https://github.com/yiyangzhou/povid
공식 코드Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
https://github.com/yjch00/plural
공식 코드https://github.com/ykotseruba/snap
공식 코드SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks
https://github.com/ylsung/ladder-side-tuning
공식 코드LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning
https://github.com/ylsung/vl-merging
공식 코드https://github.com/ymcui/Chinese-BERT-wwm
공식 코드https://github.com/ymcui/Cross-Lingual-MRC
공식 코드https://github.com/ymcui/ExpMRC
공식 코드ExpMRC: Explainability Evaluation for Machine Reading Comprehension
https://github.com/ymcui/cmrc2017
공식 코드Dataset for the First Evaluation on Chinese Machine Reading Comprehension
https://github.com/ymcui/cmrc2018
공식 코드A Span-Extraction Dataset for Chinese Machine Reading Comprehension
https://github.com/ymcui/cmrc2019
공식 코드A Sentence Cloze Dataset for Chinese Machine Reading Comprehension
https://github.com/ymcui/mrc-model-analysis
공식 코드Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
https://github.com/yonatanbitton/AutoGenOfContrastSetsFromSceneGraphs
공식 코드https://github.com/yonatanbitton/wysiwyr
공식 코드What You See is What You Read? Improving Text-Image Alignment Evaluation
https://github.com/yonseivnl/vlm-rlaif
공식 코드Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
https://github.com/yottaxx/et5
공식 코드ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
https://github.com/youlandasu/act-aware-dst
공식 코드Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
https://github.com/youshanzhang/sparrowvqe
공식 코드SparrowVQE: Visual Question Explanation for Course Content Understanding
https://github.com/ys-zong/vl-icl
공식 코드VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
https://github.com/ytongxie/medical-vision-and-language-tasks-and-methodologies-a-survey
공식 코드A Survey of Medical Vision-and-Language Applications and Their Techniques
https://github.com/yu-fangxu/for
공식 코드Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples
https://github.com/yu-rp/visualperceptiontoken
공식 코드Introducing Visual Perception Token into Multimodal Large Language Model
https://github.com/yuchenliu98/comm
공식 코드From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
https://github.com/yuecao0119/MMFuser
공식 코드MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding
https://github.com/yuecao0119/mminstruct
공식 코드MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity
https://github.com/yueche77/spin
공식 코드Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
https://github.com/yueen-ma/awesome-vla
공식 코드https://github.com/yufang-liu/clip_hallucination
공식 코드Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models
https://github.com/yuhui-zh15/autoconverter
공식 코드Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
https://github.com/yujungheo/kbvqa-public
공식 코드https://github.com/yuleiniu/cfvqa
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.