https://github.com/forjadeforest/live-learnable-in-context-vector
공식 코드LIVE: Learnable In-Context Vector for Visual Question Answering
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/foundation-multimodal-models/world2code
공식 코드https://github.com/freedomintelligence/allava
공식 코드ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
https://github.com/freedomintelligence/huatuogpt-vision
공식 코드HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale
https://github.com/freedomintelligence/trim
공식 코드Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
https://github.com/freesunshine0316/nary-grn
공식 코드Tackling Graphical NLP problems with Graph Recurrent Networks
https://github.com/fualsan/datwep
공식 코드Dynamic Task and Weight Prioritization Curriculum Learning for Multimodal Imagery
https://github.com/fudannlplab/mousi
공식 코드https://github.com/fujitsuresearch/transformer_module_networks
공식 코드Transformer Module Networks for Systematic Generalization in Visual Question Answering
https://github.com/function2-llx/mmmm
공식 코드VividMed: Vision Language Model with Versatile Visual Grounding for Medicine
https://github.com/furkanbiten/object-bias
공식 코드Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning
https://github.com/fuxiaoliu/mmc
공식 코드MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
https://github.com/gabegrand/adversarial-vqa
공식 코드Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects
https://github.com/garygutc/lapa_model
공식 코드LaPA: Latent Prompt Assist Model For Medical Visual Question Answering
https://github.com/garyjiajia/ofv2_icl_vqa
공식 코드How to Configure Good In-Context Sequence for Visual Question Answering
https://github.com/gautierdag/cast
공식 코드CAST: Cross-modal Alignment Similarity Test for Vision Language Models
https://github.com/gazkune/spatiallm
공식 코드https://github.com/gcyzsl/cvlmn
공식 코드Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning
https://github.com/geekjuruo/beer2
공식 코드Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
https://github.com/georgegotin/ic2vqa
공식 코드Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics
https://github.com/gewu-lab/mwafm
공식 코드https://github.com/gewu-lab/pstp-net
공식 코드Progressive Spatio-temporal Perception for Audio-Visual Question Answering
https://github.com/gewu-lab/tspm
공식 코드Boosting Audio Visual Question Answering via Key Semantic-Aware Cues
https://github.com/ghazaleh-mahmoodi/lxmert_compression
공식 코드https://github.com/gicheonkang/DAN-VisDial
공식 코드Dual Attention Networks for Visual Reference Resolution in Visual Dialog
https://github.com/gingasan/adversarialsa
공식 코드https://github.com/glamor-usc/climb
공식 코드https://github.com/gls0425/linvt
공식 코드LinVT: Empower Your Image-level Large Language Model to Understand Videos
https://github.com/gmparg/ICLP2018
공식 코드A Trajectory Calculus for Qualitative Spatial Reasoning Using Answer Set Programming
https://github.com/gmum/3d-point-clouds-autocomplete
공식 코드https://github.com/gogoduan/got-r1
공식 코드GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
https://github.com/google-research-datasets/T2-Guiding
공식 코드Understanding Guided Image Captioning Performance across Domains
https://github.com/google-research-datasets/conceptual-12m
공식 코드Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
https://github.com/google-research-datasets/maverics
공식 코드https://github.com/google-research-datasets/maxm
공식 코드https://github.com/google-research-datasets/screen_annotation
공식 코드ScreenAI: A Vision-Language Model for UI and Infographics Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.