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/huangb23/vtimellm
공식 코드https://github.com/huangyangyi/tech
공식 코드https://github.com/hucvl/craft
공식 코드CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions
https://github.com/hughplay/TVR
공식 코드https://github.com/hugochan/GraphFlow
공식 코드https://github.com/hunto/reloss
공식 코드https://github.com/husseinmozannar/SOQAL
공식 코드https://github.com/hwanheelee1993/qace
공식 코드https://github.com/hxyz-123/reasoningocr
공식 코드Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
https://github.com/hyperwjf/logiccheckgpt
공식 코드Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
https://github.com/hyu-zhang/itr
공식 코드Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
https://github.com/iclr2019-anon123456/perm-optim
공식 코드Learning Representations of Sets through Optimized Permutations
https://github.com/icoz69/stablellava
공식 코드StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
https://github.com/ict-bigdatalab/vnel
공식 코드https://github.com/ictnlp/llava-mini
공식 코드LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
https://github.com/idansc/HighOrderAtten
공식 코드https://github.com/idansc/fga
공식 코드https://github.com/ids-cv/coling_iparaphrasing
공식 코드iParaphrasing: Extracting Visually Grounded Paraphrases via an Image
https://github.com/ieit-agi/mix-shannon
공식 코드https://github.com/iflytek/minirbt
공식 코드MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model
https://github.com/iigroup/map
공식 코드MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
https://github.com/iigroup/scl
공식 코드Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning
https://github.com/ikb-a/systematicity-gap-in-vqa
공식 코드https://github.com/ilija139/vqa-soft
공식 코드https://github.com/illusionhi/probingprivacy
공식 코드Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
https://github.com/imagegridworth/IG-VLM
공식 코드An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM
https://github.com/imatge-upc/vqa-2016-cvprw
공식 코드https://github.com/iml-dkfz/sure-vqa
공식 코드SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks
https://github.com/imran2205/logicrag
공식 코드https://github.com/infly-ai/inf-mllm
공식 코드https://github.com/ink-usc/entity-robustness
공식 코드On the Robustness of Reading Comprehension Models to Entity Renaming
https://github.com/inst-it/inst-it
공식 코드Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning
https://github.com/intell-sci-comput/slotpi
공식 코드https://github.com/intellabs/vl-interpret
공식 코드VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers
https://github.com/intellisensing/rs-agent
공식 코드RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.