Papers with Code 아카이브
Visual Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 5
- 평가표
- 30
- 보존된 평가 기록
- 334
MLLM Leaderboard
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/LaVi-Lab/Video-3D-LLM
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
https://github.com/LisaAnne/Hallucination
https://github.com/LivXue/FS-MEVQA
https://github.com/LivXue/VCIN
https://github.com/LuanAdemi/VisualGo
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/Lucas2012/ProbabilisticNeuralProgrammedNetwork
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
https://github.com/LucasElbert/GradCam
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/MS-P3/code3/tree/main/instructblip
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
https://github.com/MS-P3/code3/tree/main/layoutlmv2
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
https://github.com/MS-P3/code5/tree/main/cogvlm
https://github.com/MS-P3/code7/tree/main/van
VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs
https://github.com/MarSaKi/NvEM
https://github.com/MarcBS/keras
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
https://github.com/MaxHolmberg96/GradCAM
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
https://github.com/Mehrab-Tanjim/enforce-reasoning
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/Mehrab-Tanjim/vilbert-rationalization
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/Mind23-2/MindCode-140
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
https://github.com/Mind23-2/MindCode-156
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
https://github.com/MindCode-4/code-1/tree/main/tvlt
https://github.com/MindCode-4/code-1/tree/main/vilt
https://github.com/MindCode-4/code-1/tree/main/vision_text_dual_encoder
Distilled Dual-Encoder Model for Vision-Language Understanding
https://github.com/MindCode-4/code-14/tree/main/CAJ
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
https://github.com/MindCode-4/code-3/tree/main/florence2
https://github.com/MindCode-4/code-4/tree/main/qwen2_moe
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
https://github.com/MindCode-4/code-4/tree/main/qwen2_vl
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
https://github.com/MindCode-4/code-5/tree/main/tvlt
https://github.com/MindCode-4/code-5/tree/main/vision_text_dual_encoder
Distilled Dual-Encoder Model for Vision-Language Understanding
https://github.com/MindCode-4/code-5/tree/main/xmod
Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model
https://github.com/MindCode-4/code-8/tree/main/perceptual-score
Perceptual Score: What Data Modalities Does Your Model Perceive?
https://github.com/MindSpore-scientific-2/code-10/tree/main/PR_Product
https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv2
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
https://github.com/MindSpore-scientific-2/code-14/tree/main/layoutlmv3
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
https://github.com/MindSpore-scientific-2/code-14/tree/main/llava
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
https://github.com/MindSpore-scientific-2/code-14/tree/main/llava_next
https://github.com/MindSpore-scientific-2/code-14/tree/main/lxmert
X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.