https://github.com/ddw2aigroup2cqupt/pa-llava
공식 코드PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image 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/debymf/ipa_probing
공식 코드Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?
https://github.com/declare-lab/emma-x
공식 코드https://github.com/declare-lab/lg-vqa
공식 코드https://github.com/declare-lab/llm-puzzletest
공식 코드https://github.com/declare-lab/puzzle-reasoning
공식 코드https://github.com/declare-lab/sas-vqa
공식 코드Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
https://github.com/declare-lab/sealing
공식 코드Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models
https://github.com/deep-spin/TVmax
공식 코드https://github.com/deep-spin/mcan-vqa-continuous-attention
공식 코드https://github.com/deep-spin/sparse_continuous_distributions
공식 코드https://github.com/deepcs233/visual-cot
공식 코드https://github.com/deepglint/unicom
공식 코드Multi-label Cluster Discrimination for Visual Representation Learning
https://github.com/deepmind/slim-dataset
공식 코드https://github.com/deepmind/svo_probes
공식 코드https://github.com/deepseek-ai/deepseek-vl
공식 코드DeepSeek-VL: Towards Real-World Vision-Language Understanding
https://github.com/deepseek-ai/deepseek-vl2
공식 코드DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
https://github.com/deepseek-ai/janus
공식 코드Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
https://github.com/digitalphonetics/intrinsic-subgraph-generation-for-vqa
공식 코드Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering
https://github.com/divamgupta/sbevnet-stereo-layout-estimation
공식 코드https://github.com/divelab/vqa-text
공식 코드Learning Convolutional Text Representations for Visual Question Answering
https://github.com/djl11/ESM
공식 코드https://github.com/dkalpakchi/embrace
공식 코드https://github.com/dlcv-buaa/tinyllavabench
공식 코드TinyLLaVA: A Framework of Small-scale Large Multimodal Models
https://github.com/dlyuangod/tinygpt-v
공식 코드TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
https://github.com/doc-doc/NExT-QA
공식 코드NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions
https://github.com/doc-doc/hqga
공식 코드Video as Conditional Graph Hierarchy for Multi-Granular Question Answering
https://github.com/doc-doc/next-gqa
공식 코드Can I Trust Your Answer? Visually Grounded Video Question Answering
https://github.com/dongyh20/chain-of-spot
공식 코드Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
https://github.com/double125/Graph-Matching-Attention
공식 코드Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
https://github.com/dpappas/Data-Augmentation-for-Biomedical-Factoid-Question-Answering
공식 코드https://github.com/dpclip/dpclip
공식 코드Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
https://github.com/dragonlzm/pave
공식 코드https://github.com/dreichCSL/GQA_generalization_splits
공식 코드https://github.com/dreichcsl/fpvg
공식 코드https://github.com/dreichcsl/truevg
공식 코드Uncovering the Full Potential of Visual Grounding Methods in VQA
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.