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/jinhaoduan/truthprint

공식 코드

TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention

https://github.com/jinlhe/pefomed

공식 코드

PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging

https://github.com/jisuk1/pllay

공식 코드

PLLay: Efficient Topological Layer based on Persistence Landscapes

https://github.com/jiuhaichen/florence-vl

공식 코드

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

https://github.com/jiwanchung/vlis

공식 코드

VLIS: Unimodal Language Models Guide Multimodal Language Generation

https://github.com/jmerullo/limber

공식 코드

Linearly Mapping from Image to Text Space

https://github.com/jmhb0/microvqa

공식 코드

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

https://github.com/jnhwkim/MulLowBiVQA

공식 코드

Hadamard Product for Low-rank Bilinear Pooling

https://github.com/jnhwkim/ban-vqa

공식 코드

Bilinear Attention Networks

https://github.com/jnhwkim/nips-mrn-vqa

공식 코드

Multimodal Residual Learning for Visual QA

https://github.com/jo-pan/flowlearn

공식 코드

FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding

https://github.com/joey1993/ad-themes

공식 코드

Recommending Themes for Ad Creative Design via Visual-Linguistic Representations

https://github.com/johncaged/OPT_Questioner

공식 코드

Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner

https://github.com/jokieleung/LPF-VQA

공식 코드

LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering

https://github.com/joshuaebenezer/lbmfr-public

공식 코드

Subjective and Objective Quality Assessment of High-Motion Sports Videos at Low-Bitrates

https://github.com/joshuafeinglass/vl-detector-eval

공식 코드

Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding

https://github.com/journeybench/journeybench

공식 코드

JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images

https://github.com/jpthu17/HBI

공식 코드

Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

https://github.com/jpthu17/emcl

공식 코드

Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

https://github.com/jshilong/gpt4roi

공식 코드

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

https://github.com/jsuarez5341/Efficient-Dynamic-Batching

공식 코드

Effective Approaches to Batch Parallelization for Dynamic Neural Network Architectures

https://github.com/justairr/satori-r1

공식 코드

SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable Rewards

https://github.com/jxliu-ai/medcot

공식 코드

MedCoT: Medical Chain of Thought via Hierarchical Expert

https://github.com/jzy-123/biod2c

공식 코드

BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQA

https://github.com/k-zha14/zoom-vqa

공식 코드

Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment

https://github.com/kaavyarekanar/towards-a-performance-analysis-on-pre-trained-vqa-models-for-autonomous-driving

공식 코드

Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving

https://github.com/kai-wen-yang/qvix

공식 코드

Good Questions Help Zero-Shot Image Reasoning

https://github.com/kaist-cvml/3d-vlm-gd

공식 코드

3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation

https://github.com/kaistai/volcano

공식 코드

Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision

https://github.com/kamichanw/mimic

공식 코드

Mimic In-Context Learning for Multimodal Tasks

https://github.com/kangreen0210/lime

공식 코드

LIME: Less Is More for MLLM Evaluation

https://github.com/kangreen0210/lime-m

공식 코드

LIME: Less Is More for MLLM Evaluation

https://github.com/kasuba-badri-vishal/dhrishtikon

공식 코드

DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images

https://github.com/katiefraser/pairs

공식 코드

Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images

https://github.com/kesenzhao/uv-cot

공식 코드

Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization

https://github.com/kevinduh/san_mrc

공식 코드

Stochastic Answer Networks for SQuAD 2.0

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