Papers with Code 아카이브

Visual Question Answering (VQA)

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/microsoft/unilm

공식 코드

LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding

https://github.com/microsoft/unilm/tree/master/beit

공식 코드

Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

https://github.com/microsoft/unilm/tree/master/kosmos-2

공식 코드

Kosmos-2: Grounding Multimodal Large Language Models to the World

https://github.com/microsoft/unilm/tree/master/layoutlmv3

공식 코드

LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking

https://github.com/microsoft/unilm/tree/master/vlmo

공식 코드

VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts

https://github.com/mightyzau/infmllm

공식 코드

InfMLLM: A Unified Framework for Visual-Language Tasks

https://github.com/mihirp1998/Disentangling-3D-Prototypical-Nets

공식 코드

Disentangling 3D Prototypical Networks For Few-Shot Concept Learning

https://github.com/milomilo0320/a-semi-automatic-annotation-software-for-scene-graph

공식 코드

GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph

https://github.com/milvlg/bst

공식 코드

Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering

https://github.com/milvlg/imp

공식 코드

Imp: Highly Capable Large Multimodal Models for Mobile Devices

https://github.com/milvlg/prophet

공식 코드

Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering

https://github.com/mineanybuild/mineanybuild

공식 코드

MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents

https://github.com/ming-zch/let-androids-dream-of-electric-sheep

공식 코드

Let Androids Dream of Electric Sheep: A Human-like Image Implication Understanding and Reasoning Framework

https://github.com/minhquan6203/vitextvqa-dataset

공식 코드

ViTextVQA: A Large-Scale Visual Question Answering Dataset for Evaluating Vietnamese Text Comprehension in Images

https://github.com/mintelligence-group/cmfeed

공식 코드

Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image Data

https://github.com/mirthai/med3dvlm

공식 코드

Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis

https://github.com/mit-han-lab/llm-awq

공식 코드

VILA: On Pre-training for Visual Language Models

https://github.com/mitmedialab/mdagents

공식 코드

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making

https://github.com/mizuumi/JDocQA

공식 코드

JDocQA: Japanese Document Question Answering Dataset for Generative Language Models

https://github.com/ml-research/ILLUME

공식 코드

ILLUME: Rationalizing Vision-Language Models through Human Interactions

https://github.com/ml-research/slash

공식 코드

Scalable Neural-Probabilistic Answer Set Programming

https://github.com/mlfoundations/open_flamingo

공식 코드

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

https://github.com/mlpc-ucsd/bliva

공식 코드

BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions

https://github.com/mlvlab/Flipped-VQA

공식 코드

Large Language Models are Temporal and Causal Reasoners for Video Question Answering

https://github.com/mlvlab/MELTR

공식 코드

MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models

https://github.com/mlvlab/ovqa

공식 코드

Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models

https://github.com/mlvlab/vid-tldr

공식 코드

vid-TLDR: Training Free Token merging for Light-weight Video Transformer

https://github.com/mmahbub/bioadapt-mrc

공식 코드

BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task

https://github.com/mmdocrag/mmdocrag

공식 코드

Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering

https://github.com/mneuronico/griw-world-spatial-orientation-task

공식 코드

From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task

https://github.com/mobarakol/Surgical_SceneGraph_Generation

공식 코드

Learning and Reasoning with the Graph Structure Representation in Robotic Surgery

https://github.com/mobarakol/pitvqa

공식 코드

PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery

https://github.com/modelscope/data-juicer

공식 코드

DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?

https://github.com/modelscope/ms-swift

공식 코드

SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

https://github.com/modelscope/swift

공식 코드

SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

https://github.com/mohamedaghzal/llms-as-path-planners

공식 코드

Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.