https://github.com/khanhnguyen21006/mia_docvqa
공식 코드DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
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/khuangaf/awesome-chart-understanding
공식 코드https://github.com/kkahatapitiya/langrepo
공식 코드https://github.com/knowlab/halt-medvqa
공식 코드Hallucination Benchmark in Medical Visual Question Answering
https://github.com/knowledgetechnologyuhh/grid-3d
공식 코드https://github.com/koen-47/columbus
공식 코드COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes
https://github.com/kovvalsky/spacenli
공식 코드SpaceNLI: Evaluating the Consistency of Predicting Inferences in Space
https://github.com/kraina-ai/geospatial-code-llms-dataset
공식 코드https://github.com/kshitij98/cvil
공식 코드cViL: Cross-Lingual Training of Vision-Language Models using Knowledge Distillation
https://github.com/kuan2jiu99/audio-hallucination
공식 코드https://github.com/kugwzk/dide
공식 코드Distilled Dual-Encoder Model for Vision-Language Understanding
https://github.com/kugwzk/distilled-dualencoder
공식 코드Distilled Dual-Encoder Model for Vision-Language Understanding
https://github.com/kushalkafle/DVQA_dataset
공식 코드DVQA: Understanding Data Visualizations via Question Answering
https://github.com/kushalkafle/PREFIL
공식 코드Answering Questions about Data Visualizations using Efficient Bimodal Fusion
https://github.com/kvt0012/viclevr
공식 코드https://github.com/kyleseelman/vqa_accessibility
공식 코드https://github.com/kyrochi/qlip
공식 코드QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining
https://github.com/kzampog/cilantro
공식 코드cilantro: A Lean, Versatile, and Efficient Library for Point Cloud Data Processing
https://github.com/lab-rasool/awesome-medical-vlms-and-datasets
공식 코드Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review
https://github.com/lackel/dka
공식 코드https://github.com/laichengen/mcle
공식 코드Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA
https://github.com/lalithjets/surgical_vqa
공식 코드Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer
https://github.com/lalithjets/surgicalgpt
공식 코드SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery
https://github.com/lamalab-org/mac-bench
공식 코드Probing the limitations of multimodal language models for chemistry and materials research
https://github.com/lavi-lab/navillm
공식 코드https://github.com/lavi-lab/visual-table
공식 코드Beyond Embeddings: The Promise of Visual Table in Visual Reasoning
https://github.com/laytextllm/laytextllm
공식 코드https://github.com/leeyn-43/clover
공식 코드Clover: Towards A Unified Video-Language Alignment and Fusion Model
https://github.com/leitro/selfattnscoring-mpdocvqa
공식 코드Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism
https://github.com/leoleoasd/mlp-based-weighting
공식 코드Contextual embedding and model weighting by fusing domain knowledge on Biomedical Question Answering
https://github.com/letian2003/c-vqa
공식 코드What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models
https://github.com/letitiabanana/pnp-ovss
공식 코드Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models
https://github.com/levymsn/cqa-crct
공식 코드https://github.com/lgw863/LogiQA-dataset
공식 코드LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
https://github.com/li-qingyun/mllm-mmrotate
공식 코드A Simple Aerial Detection Baseline of Multimodal Language Models
https://github.com/libeineu/mmt-vqa
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.