https://github.com/wenkehuang/awesome-mllm-tuning
공식 코드Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model
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/wenliangdai/vlp-object-hallucination
공식 코드Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
https://github.com/wentaoyuan/sornet
공식 코드SORNet: Spatial Object-Centric Representations for Sequential Manipulation
https://github.com/wenzhouyidu/light-vqa
공식 코드Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement
https://github.com/westlake-baichuan-mllm/bc-omni
공식 코드https://github.com/westlake-baichuan-mllm/ocean-omni
공식 코드https://github.com/whb139426/qa-prompts-eccv-24
공식 코드https://github.com/windweller/Pragmatic-ISIC
공식 코드https://github.com/winogavil/winogavil-experiments
공식 코드WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models
https://github.com/witcherleo/knowing-how-knowing-that
공식 코드Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manuals
https://github.com/wjnwjn59/CLAugViVQA
공식 코드Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations
https://github.com/woojeongjin/fewvlm
공식 코드https://github.com/worldcuisines/worldcuisines
공식 코드https://github.com/wsj-sjtu/fvq
공식 코드FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment
https://github.com/wskbest/mfc-bench
공식 코드MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models
https://github.com/wuhy68/p-adapter
공식 코드p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models
https://github.com/wujunjie1998/tri-he
공식 코드Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
https://github.com/wulinjuan/ssdm_mrc
공식 코드https://github.com/wutaiqiang/moslora
공식 코드https://github.com/wuxiyang1996/AutoHallusion
공식 코드AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models
https://github.com/wyk-nku/distinguishing-vqa
공식 코드https://github.com/wzhouad/context-faithful-llm
공식 코드https://github.com/wzzheng/doe
공식 코드Doe-1: Closed-Loop Autonomous Driving with Large World Model
https://github.com/x-plug/mplug-docowl
공식 코드TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
https://github.com/x-plug/mplug-halowl
공식 코드Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
https://github.com/x-plug/mplug-owl
공식 코드mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
https://github.com/x2fd/lvis-instruct4v
공식 코드To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning
https://github.com/xandery-geek/badcm
공식 코드BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
https://github.com/xdao85/vnhsge
공식 코드VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models
https://github.com/xiandaguo/drive-mllm
공식 코드https://github.com/xiangyue9607/CliniRC
공식 코드Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset
https://github.com/xiaoduoailab/xmodelvlm
공식 코드Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model
https://github.com/xiaohao-xu/ambiguity-in-space
공식 코드Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity
https://github.com/xiaojino/RUArt
공식 코드RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering
https://github.com/xiaoman-zhang/PMC-VQA
공식 코드PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
https://github.com/xiaowu0162/visualize-then-retrieve
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.