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/thunlp-mt/dbkd-plm

공식 코드

Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models

https://github.com/thunlp-mt/fiig

공식 코드

Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions

https://github.com/thunlp/ChartCoder

공식 코드

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

https://github.com/thunlp/moefication

공식 코드

MoEfication: Transformer Feed-forward Layers are Mixtures of Experts

https://github.com/thunlp/pevl

공식 코드

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models

https://github.com/tianyi-lab/hallusionbench

공식 코드

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

https://github.com/tianyu-z/vcr

공식 코드

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

https://github.com/tibhannover/patent-figure-classification

공식 코드

Patent Figure Classification using Large Vision-language Models

https://github.com/tiktok/fast_prompt_alignment

공식 코드

Fast Prompt Alignment for Text-to-Image Generation

https://github.com/timmy-chan/miss

공식 코드

MISS: A Generative Pretraining and Finetuning Approach for Med-VQA

https://github.com/tingyu215/ts-llava

공식 코드

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

https://github.com/tjvsonsbeek/open-ended-medical-vqa

공식 코드

Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models

https://github.com/togethercomputer/dragonfly

공식 코드

Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models

https://github.com/toloka/wsdmcup2023

공식 코드

Toloka Visual Question Answering Benchmark

https://github.com/tomohiro-sawada/cs7643-final-project

공식 코드

Towards a Unified Multimodal Reasoning Framework

https://github.com/tong-zeng/dvbench

공식 코드

Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding

https://github.com/tossowski/multimodalpromptretrieval

공식 코드

Multimodal Prompt Retrieval for Generative Visual Question Answering

https://github.com/tree985/treble-counterfactual-vlms

공식 코드

Treble Counterfactual VLMs: A Causal Approach to Hallucination

https://github.com/tri-ml/prismatic-vlms

공식 코드

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

https://github.com/tri-ml/vlm-evaluation

공식 코드

Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models

https://github.com/triumph123aaa/grid-augmented-vision

공식 코드

Grid-augmented vision: A simple yet effective approach for enhanced spatial understanding in multi-modal agents

https://github.com/tsinghua-fib-lab/CityEQA

공식 코드

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space

https://github.com/tsinghua-fib-lab/citygpt

공식 코드

CityGPT: Empowering Urban Spatial Cognition of Large Language Models

https://github.com/tsinghua-msiip/uni-med

공식 코드

Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE

https://github.com/tsujuifu/pytorch_empirical-mvm

공식 코드

An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling

https://github.com/tttamaki/vqd

공식 코드

An Entropy Clustering Approach for Assessing Visual Question Difficulty

https://github.com/tttyuntian/vlm_lexical_grounding

공식 코드

Does Vision-and-Language Pretraining Improve Lexical Grounding?

https://github.com/ttumyche/cxreasonbench

공식 코드

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

https://github.com/tu184044109/VIDEVAL_release

공식 코드

UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content

https://github.com/tuhinjubcse/faithfuledits_emnlp2023

공식 코드

Learning to Follow Object-Centric Image Editing Instructions Faithfully

https://github.com/tulerfeng/video-r1

공식 코드

Video-R1: Reinforcing Video Reasoning in MLLMs

https://github.com/turingmotors/nuscenes-mqa

공식 코드

NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations

https://github.com/tutujingyugang1/ChatVLA_public

공식 코드

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

https://github.com/txh-mercury/cosa

공식 코드

COSA: Concatenated Sample Pretrained Vision-Language Foundation Model

https://github.com/txh-mercury/vast

공식 코드

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

https://github.com/txhaug/optimal-quantum-learning

공식 코드

Optimal training of variational quantum algorithms without barren plateaus

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