https://github.com/google-research-datasets/screen_qa
공식 코드ScreenAI: A Vision-Language Model for UI and Infographics Understanding
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/google-research/big_vision
공식 코드https://github.com/google-research/google-research
공식 코드Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
https://github.com/google-research/language
공식 코드Fusion of Detected Objects in Text for Visual Question Answering
https://github.com/google-research/long-range-arena
공식 코드https://github.com/google-research/pix2struct
공식 코드Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
https://github.com/google-research/scenic
공식 코드Location-Aware Self-Supervised Transformers for Semantic Segmentation
https://github.com/google-research/scenic/tree/main/scenic/projects/knowledge_visual_language
공식 코드https://github.com/google/cog
공식 코드A Dataset and Architecture for Visual Reasoning with a Working Memory
https://github.com/google/haloquest
공식 코드HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning
https://github.com/google/mcafp
공식 코드Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors
https://github.com/google/spiqa
공식 코드SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
https://github.com/gorjanradevski/revisiting-spatial-temporal-layouts
공식 코드Revisiting spatio-temporal layouts for compositional action recognition
https://github.com/gpantaz/probing-resamplers
공식 코드Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers
https://github.com/groundlight/vlm-visual-demonstrations
공식 코드Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?
https://github.com/gtziafas/hots
공식 코드Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach
https://github.com/guangyans/sys2-llava
공식 코드https://github.com/guanjinquan/cxrtrek
공식 코드Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoning
https://github.com/guilk/kat
공식 코드KAT: A Knowledge Augmented Transformer for Vision-and-Language
https://github.com/guoyang9/AdaVQA
공식 코드AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss
https://github.com/guoyang9/class-imbalance-VQA
공식 코드Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View
https://github.com/guoyang9/elip
공식 코드ELIP: Efficient Language-Image Pre-training with Fewer Vision Tokens
https://github.com/guoyang9/unifer
공식 코드A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
https://github.com/guoyang9/unk-vqa
공식 코드UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models
https://github.com/guoyang9/vqa-prior
공식 코드Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
https://github.com/gzhu-dvl/attackvqa
공식 코드Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks
https://github.com/gzhu-dvl/starvqaplus
공식 코드StarVQA+: Co-training Space-Time Attention for Video Quality Assessment
https://github.com/hackerchenzhuo/LaKo
공식 코드LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection
https://github.com/hamzeiehsan/questions-to-geosparql
공식 코드https://github.com/hanxiao/daanet
공식 코드https://github.com/hao840/adem-vl
공식 코드ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
https://github.com/haochen-wang409/droppos
공식 코드DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
https://github.com/haochenz11/iref-vla
공식 코드IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes
https://github.com/haodongze/self-ksel-qans
공식 코드Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering
https://github.com/haonan-li/lamb
공식 코드Location Aware Modular Biencoder for Tourism Question Answering
https://github.com/haoningwu3639/SpatialScore
공식 코드SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.