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/yuleiniu/introd

공식 코드

Introspective Distillation for Robust Question Answering

https://github.com/yuleiniu/rva

공식 코드

Recursive Visual Attention in Visual Dialog

https://github.com/yuliang-liu/monkey

공식 코드

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models

https://github.com/yuliang-liu/multimodalocr

공식 코드

OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

https://github.com/yuliangcai2022/clumo

공식 코드

CluMo: Cluster-based Modality Fusion Prompt for Continual Learning in Visual Question Answering

https://github.com/yuweihao/mm-vet

공식 코드

MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities

https://github.com/yuweihao/reclor

공식 코드

ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

https://github.com/yuyangdu01/llm-cl-vqa

공식 코드

LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery

https://github.com/yuzcccc/mfb

공식 코드

Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering

https://github.com/yuzcccc/vqa-mfb

공식 코드

Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering

https://github.com/yzhjessica/cdvqa

공식 코드

Change Detection Meets Visual Question Answering

https://github.com/yzleroy/revive

공식 코드

REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering

https://github.com/z1zs/mmneuron

공식 코드

MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model

https://github.com/z1zs/mmunlearner

공식 코드

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

https://github.com/zaynmi/seada-vqa

공식 코드

Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering

https://github.com/zd11024/NaviLLM

공식 코드

Towards Learning a Generalist Model for Embodied Navigation

https://github.com/zdou0830/meter

공식 코드

An Empirical Study of Training End-to-End Vision-and-Language Transformers

https://github.com/zechenli03/qlevr

공식 코드

QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning

https://github.com/zengxingchen/chartqa-mllm

공식 코드

Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning

https://github.com/zengyan-97/x-vlm

공식 코드

Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts

https://github.com/zengyan-97/x2-vlm

공식 코드

X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks

https://github.com/zeqing-wang/timecausality

공식 코드

TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models

https://github.com/zfying/visfis

공식 코드

VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives

https://github.com/zh460045050/v2l-tokenizer

공식 코드

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

https://github.com/zhangbaijin/From-Redundancy-to-Relevance

공식 코드

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks

https://github.com/zhangbin-ai/apl

공식 코드

Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering

https://github.com/zhangxinsong-nlp/XFM

공식 코드

Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks

https://github.com/zhangyan-ucas/TEA

공식 코드

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues

https://github.com/zhangzjn/gpt-4v-ad

공식 코드

GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection

https://github.com/zhanyang-nwpu/rsvg-pytorch

공식 코드

RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data

https://github.com/zhaohengyuan1/genixer

공식 코드

Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator

https://github.com/zhaoshitian/Likelihood-Composition-Toolkit

공식 코드

Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models

https://github.com/zhaowc-ustc/tabpedia

공식 코드

TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy

https://github.com/zhegan27/LXMERT-AdvTrain

공식 코드

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

https://github.com/zhegan27/VILLA

공식 코드

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

https://github.com/zhengchen1999/grounding-iqa

공식 코드

Grounding-IQA: Multimodal Language Grounding Model for Image Quality Assessment

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