https://github.com/GeondoPark/MHSAN
공식 코드MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding
Papers with Code 아카이브
Visual Question Answering (VQA)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/GeraldHan/GGD
공식 코드https://github.com/GeraldHan/GGE
공식 코드Greedy Gradient Ensemble for Robust Visual Question Answering
https://github.com/GuessWhatGame/referit
공식 코드https://github.com/HIT-SCIR/Molweni
공식 코드https://github.com/HLR/Cross_Modality_Relevance
공식 코드Cross-Modality Relevance for Reasoning on Language and Vision
https://github.com/HLR/Dual-Action-VLN-CE
공식 코드https://github.com/HLR/FoREST
공식 코드FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks
https://github.com/HLR/SpartQA_generation
공식 코드SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning
https://github.com/HenryJunW/TAG
공식 코드TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
https://github.com/HongyangLL/M3-JEPA
공식 코드M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework
https://github.com/HongyuGong/RCM-Question-Answering
공식 코드Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension
https://github.com/Hoyyyaard/LSceneLLM
공식 코드LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences
https://github.com/Hritikbansal/medmax
공식 코드MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
https://github.com/HyeonwooNoh/vqa_task_discovery
공식 코드Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
https://github.com/Hyu-Zhang/ISR
공식 코드Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
https://github.com/Hzfinfdu/MPMP
공식 코드Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning
https://github.com/IBM/multidoc2dial
공식 코드MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents
https://github.com/IGLU-CHISTERA/CLEAR-dataset-generation
공식 코드CLEAR: A Dataset for Compositional Language and Elementary Acoustic Reasoning
https://github.com/INK-USC/mrc-explanation
공식 코드Teaching Machine Comprehension with Compositional Explanations
https://github.com/INK-USC/nl-explanation
공식 코드Teaching Machine Comprehension with Compositional Explanations
https://github.com/IemProg/QUAD
공식 코드No Images, No Problem: Retaining Knowledge in Continual VQA with Questions-Only Memory
https://github.com/IllusoryVQA/IllusoryVQA
공식 코드Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions
https://github.com/IntelliSensing/UniRS
공식 코드UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models
https://github.com/InterDigitalInc/DialogSummary-VideoQA
공식 코드On the hidden treasure of dialog in video question answering
https://github.com/InternLM/InternLM-XComposer/tree/main/projects/ShareGPT4V
공식 코드ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
https://github.com/InternLM/opencompass
공식 코드https://github.com/IrohXu/VCog-Bench
공식 코드What is the Visual Cognition Gap between Humans and Multimodal LLMs?
https://github.com/JXZe/DualVD
공식 코드DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue
https://github.com/JackHopkins/factorio-learning-environment
공식 코드https://github.com/JannerM/spatial-reasoning
공식 코드https://github.com/Jiaxuan-Li/MGU-Net
공식 코드https://github.com/JingruG/GATHER
공식 코드Open-Set Knowledge-Based Visual Question Answering with Inference Paths
https://github.com/Jirl-upenn/VLMnav
공식 코드https://github.com/JoshuaEbenezer/ChipQA
공식 코드ChipQA: No-Reference Video Quality Prediction via Space-Time Chips
https://github.com/JoshuaEbenezer/ChipQA-0
공식 코드No-Reference Video Quality Assessment Using Space-Time Chips
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.