Papers with Code 아카이브

Visual Question Answering

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

5

평가표

30

보존된 평가 기록

334

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/DriveVLA/OpenDriveVLA

공식 코드

OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model

https://github.com/Earth-Intelligence-Lab/vleo-bench

공식 코드

Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data

https://github.com/Fangjun-Li/SpatialLM-StepGame

공식 코드

Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark

https://github.com/FightingFighting/cross-modal-information-flow-in-MLLM

공식 코드

Cross-modal Information Flow in Multimodal Large Language Models

https://github.com/FlamingHorizon/CMM-VR

공식 코드

Cascaded Mutual Modulation for Visual Reasoning

https://github.com/Flitternie/FMProgramming

공식 코드

Resource-efficient Inference with Foundation Model Programs

https://github.com/FrankZxShen/ATS

공식 코드

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering

https://github.com/FuxiaoLiu/LRV-Instruction

공식 코드

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

https://github.com/GanjinZero/RAMM

공식 코드

RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training

https://github.com/GeWu-Lab/MUSIC-AVQA

공식 코드

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

https://github.com/GeondoPark/MHSAN

공식 코드

MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding

https://github.com/GeraldHan/GGD

공식 코드

General Greedy De-bias Learning

https://github.com/GeraldHan/GGE

공식 코드

Greedy Gradient Ensemble for Robust Visual Question Answering

https://github.com/GuessWhatGame/referit

공식 코드

Visual Reasoning with Multi-hop Feature Modulation

https://github.com/HLR/Cross_Modality_Relevance

공식 코드

Cross-Modality Relevance for Reasoning on Language and Vision

https://github.com/HLR/Dual-Action-VLN-CE

공식 코드

Narrowing the Gap between Vision and Action in Navigation

https://github.com/HLR/FoREST

공식 코드

FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks

https://github.com/HLR/SpartQA_generation

공식 코드

SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning

https://github.com/HongyangLL/M3-JEPA

공식 코드

M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework

https://github.com/Hritikbansal/medmax

공식 코드

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants

https://github.com/HyeonwooNoh/vqa_task_discovery

공식 코드

Transfer Learning via Unsupervised Task Discovery for Visual Question Answering

https://github.com/Hyu-Zhang/ISR

공식 코드

Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog

https://github.com/IGLU-CHISTERA/CLEAR-dataset-generation

공식 코드

CLEAR: A Dataset for Compositional Language and Elementary Acoustic Reasoning

https://github.com/IemProg/QUAD

공식 코드

No Images, No Problem: Retaining Knowledge in Continual VQA with Questions-Only Memory

https://github.com/IllusoryVQA/IllusoryVQA

공식 코드

Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions

https://github.com/IntelliSensing/UniRS

공식 코드

UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models

https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V

공식 코드

ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

https://github.com/InternLM/opencompass

공식 코드

MMBench: Is Your Multi-modal Model an All-around Player?

https://github.com/JXZe/DualVD

공식 코드

DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue

https://github.com/JackHopkins/factorio-learning-environment

공식 코드

Factorio Learning Environment

https://github.com/JannerM/spatial-reasoning

공식 코드

Representation Learning for Grounded Spatial Reasoning

https://github.com/Jiaxuan-Li/MGU-Net

공식 코드

Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and disc in peripapillary OCT images

https://github.com/JingruG/GATHER

공식 코드

Open-Set Knowledge-Based Visual Question Answering with Inference Paths

https://github.com/Jirl-upenn/VLMnav

공식 코드

End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering

https://github.com/Junjue-Wang/EarthVQA

공식 코드

EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering

https://github.com/JunweiLiang/FVTA_MemexQA

공식 코드

Focal Visual-Text Attention for Visual Question Answering

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