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/opengvlab/all-seeing

공식 코드

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World

https://github.com/opengvlab/internvl

공식 코드

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

https://github.com/opengvlab/multi-modality-arena

공식 코드

LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models

https://github.com/opengvlab/multitask-model-selector

공식 코드

Foundation Model is Efficient Multimodal Multitask Model Selector

https://github.com/opengvlab/piip

공식 코드

Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding

https://github.com/opengvlab/visionllm

공식 코드

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks

https://github.com/optimization-for-data-driven-science/dair

공식 코드

Robustness through Data Augmentation Loss Consistency

https://github.com/osilly/dynamic_llava

공식 코드

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

https://github.com/osu-nlp-group/seeact

공식 코드

GPT-4V(ision) is a Generalist Web Agent, if Grounded

https://github.com/osu-slatelab/mapqa

공식 코드

MapQA: A Dataset for Question Answering on Choropleth Maps

https://github.com/ouyangkun10/spacer

공식 코드

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

https://github.com/ouyangkun10/spatial-r1

공식 코드

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

https://github.com/overloadedhenry/clinkd

공식 코드

ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images

https://github.com/ovguyo/captions-in-vqa

공식 코드

Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts

https://github.com/ovshake/cobra

공식 코드

COBRA: Contrastive Bi-Modal Representation Algorithm

https://github.com/pairlab/slotformer

공식 코드

SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models

https://github.com/palaashagrawal/stupd

공식 코드

STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning

https://github.com/para-lost/rvp

공식 코드

Recursive Visual Programming

https://github.com/park-jungin/vlap

공식 코드

Bridging Vision and Language Spaces with Assignment Prediction

https://github.com/patilli/vqa_benchmarking

공식 코드

Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking

https://github.com/pauamargant/hsr-graspsynth

공식 코드

Sim2Real Transfer for Vision-Based Grasp Verification

https://github.com/paulgavrikov/vlm_shapebias

공식 코드

Can We Talk Models Into Seeing the World Differently?

https://github.com/paullerner/viquae

공식 코드

Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering

https://github.com/paulsubarna/core-tokenset

공식 코드

Core Tokensets for Data-efficient Sequential Training of Transformers

https://github.com/pds-dpo/pds-dpo

공식 코드

Multimodal Preference Data Synthetic Alignment with Reward Model

https://github.com/peijin360/vsre

공식 코드

Expand VSR Benchmark for VLLM to Expertize in Spatial Rules

https://github.com/pengfeiliheu/m2i2

공식 코드

Self-supervised vision-language pretraining for Medical visual question answering

https://github.com/penghao-wu/vstar

공식 코드

V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

https://github.com/pengts/vw-lmm

공식 코드

Multi-modal Auto-regressive Modeling via Visual Words

https://github.com/peteanderson80/Matterport3DSimulator

공식 코드

Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments

https://github.com/peteanderson80/bottom-up-attention

공식 코드

Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

https://github.com/philippds/sphyr

공식 코드

SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution

https://github.com/phoebussi/compress-robust-vqa

공식 코드

Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering

https://github.com/phoebussi/mmbs

공식 코드

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning

https://github.com/phoebussi/thinking-while-observing

공식 코드

Combo of Thinking and Observing for Outside-Knowledge VQA

https://github.com/phoebussi/vqa-vs

공식 코드

Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA

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