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/marcwannerchalmers/vqa_continuous_bandits

공식 코드

Variational Quantum Optimization with Continuous Bandits

https://github.com/marrlab/shapr_torch

공식 코드

Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction

https://github.com/marslanm/multimodality-representation-learning

공식 코드

Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications

https://github.com/masoud-monajati/BERTHop

공식 코드

BERTHop: An Effective Vision-and-Language Model for Chest X-ray Disease Diagnosis

https://github.com/mateuszmalinowski/visual_turing_test-tutorial

공식 코드

Ask Your Neurons: A Deep Learning Approach to Visual Question Answering

https://github.com/matnlp/cmedmrc

공식 코드

Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources

https://github.com/matthewdm0816/bridgeqa

공식 코드

Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA

https://github.com/maum-ai/koffvqa

공식 코드

KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language

https://github.com/mayhugotong/videoinsta

공식 코드

VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs

https://github.com/mbzuai-nlp/multichoice2extractiveqa

공식 코드

From Multiple-Choice to Extractive QA: A Case Study for English and Arabic

https://github.com/mbzuai-oryx/bimedix2

공식 코드

BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities

https://github.com/mbzuai-oryx/geochat

공식 코드

GeoChat: Grounded Large Vision-Language Model for Remote Sensing

https://github.com/mbzuai-oryx/thinkgeo

공식 코드

ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks

https://github.com/mbzuai-oryx/video-chatgpt

공식 코드

Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

https://github.com/mbzuai-oryx/videogpt-plus

공식 코드

VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

https://github.com/mcogswell/dialog_without_dialog

공식 코드

Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data

https://github.com/mdca-loss/mdca-calibration

공식 코드

A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration

https://github.com/merlresearch/SMART

공식 코드

Are Deep Neural Networks SMARTer than Second Graders?

https://github.com/metabrainagi/awaker

공식 코드

Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts

https://github.com/metalbubble/VQAbaseline

공식 코드

Simple Baseline for Visual Question Answering

https://github.com/mi92/reverse-image-rag

공식 코드

Reverse Image Retrieval Cues Parametric Memory in Multimodal LLMs

https://github.com/michi-3000/eyeclip

공식 코드

EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis

https://github.com/microsoft/GLIP

공식 코드

GLIPv2: Unifying Localization and Vision-Language Understanding

https://github.com/microsoft/GenerativeImage2Text

공식 코드

GIT: A Generative Image-to-text Transformer for Vision and Language

https://github.com/microsoft/MM-REACT

공식 코드

MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

https://github.com/microsoft/Oscar

공식 코드

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

https://github.com/microsoft/PICa

공식 코드

An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA

https://github.com/microsoft/TAP

공식 코드

TAP: Text-Aware Pre-training for Text-VQA and Text-Caption

https://github.com/microsoft/UniTAB

공식 코드

UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling

https://github.com/microsoft/cream

공식 코드

Searching the Search Space of Vision Transformer

https://github.com/microsoft/fiber

공식 코드

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

https://github.com/microsoft/i-code

공식 코드

Unifying Vision, Text, and Layout for Universal Document Processing

https://github.com/microsoft/llm-data-creation

공식 코드

Making Large Language Models Better Data Creators

https://github.com/microsoft/scglab

공식 코드

GENIUS: Sketch-based Language Model Pre-training via Extreme and Selective Masking for Text Generation and Augmentation

https://github.com/microsoft/smartplay

공식 코드

SmartPlay: A Benchmark for LLMs as Intelligent Agents

https://github.com/microsoft/udop

공식 코드

Unifying Vision, Text, and Layout for Universal Document Processing

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