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/lijiannuist/efficient-multimodal-llms-survey

공식 코드

Efficient Multimodal Large Language Models: A Survey

https://github.com/lik1996/crvqa2024

공식 코드

Convincing Rationales for Visual Question Answering Reasoning

https://github.com/like413/vista

공식 코드

Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection

https://github.com/lil-lab/knotgym

공식 코드

Knot So Simple: A Minimalistic Environment for Spatial Reasoning

https://github.com/lil-lab/touchdown

공식 코드

Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

https://github.com/lilidamowang/iiu

공식 코드

IIU: Independent Inference Units for Knowledge-based Visual Question Answering

https://github.com/limiaoyu/dietcoke

공식 코드

Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA

https://github.com/lin-tianwei/teamlora

공식 코드

TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition

https://github.com/lingyongyan/docds

공식 코드

From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension

https://github.com/linjieli222/VQA_ReGAT

공식 코드

Relation-Aware Graph Attention Network for Visual Question Answering

https://github.com/linjiemu/mmxu

공식 코드

MMXU: A Multi-Modal and Multi-X-ray Understanding Dataset for Disease Progression

https://github.com/lins-lab/dynmoe

공식 코드

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

https://github.com/linweizhedragon/retrieval-augmented-visual-question-answering

공식 코드

Retrieval Augmented Visual Question Answering with Outside Knowledge

https://github.com/linzhiqiu/t2i_metrics

공식 코드

Evaluating Text-to-Visual Generation with Image-to-Text Generation

https://github.com/linzhiqiu/t2v_metrics

공식 코드

Evaluating Text-to-Visual Generation with Image-to-Text Generation

https://github.com/linzhiqiu/visual_gpt_score

공식 코드

Revisiting the Role of Language Priors in Vision-Language Models

https://github.com/linziyang1999/vga-visual-gui-assistant

공식 코드

VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-Tuning

https://github.com/liqing-ustc/NGS

공식 코드

Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning

https://github.com/littlespray/crave

공식 코드

Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency

https://github.com/littlespray/e-bench

공식 코드

VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment

https://github.com/littlespray/ve-bench

공식 코드

VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment

https://github.com/liuhc0428/med-pmc

공식 코드

Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm

https://github.com/liuting20/dara

공식 코드

DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding

https://github.com/liuziyu77/mmdu

공식 코드

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

https://github.com/liwb1219/hrmf

공식 코드

Exploiting Word Semantics to Enrich Character Representations of Chinese Pre-trained Models

https://github.com/liweim/TextLayoutLLM

공식 코드

Large Language Models Understand Layout

https://github.com/lixinustc/kvq-challenge-cvpr-ntire2024

공식 코드

NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results

https://github.com/lixinustc/kvqe-challenge-cvpr-ntire2025

공식 코드

NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results

https://github.com/lizw14/calico

공식 코드

Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images

https://github.com/lizw14/super-clevr

공식 코드

Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning

https://github.com/ljh0v0/fmd-frechet-motion-distance

공식 코드

Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos

https://github.com/lkaesberg/sparc

공식 코드

SPaRC: A Spatial Pathfinding Reasoning Challenge

https://github.com/llamatouch/vlm-reasoning-traces

공식 코드

Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study

https://github.com/lmb-freiburg/ovqa

공식 코드

Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy

https://github.com/longbai1006/cat-vil

공식 코드

CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery

https://github.com/longbai1006/surgical-vqla

공식 코드

Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery

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