https://github.com/artanic30/maccap
공식 코드Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training
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/asaakyan/V-FLUTE
공식 코드Understanding Figurative Meaning through Explainable Visual Entailment
https://github.com/asad14053/AdCare-VLM
공식 코드https://github.com/asgsaeid/cad_vqa
공식 코드How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?
https://github.com/ashkamath/mdetr
공식 코드MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
https://github.com/asu-apg/vli_sdro
공식 코드Semantically Distributed Robust Optimization for Vision-and-Language Inference
https://github.com/atelili/2bivqa
공식 코드2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos
https://github.com/atr-dbi/scanqa
공식 코드ScanQA: 3D Question Answering for Spatial Scene Understanding
https://github.com/atsumiyai/upd
공식 코드Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models
https://github.com/aurooj/MMFT-BERT
공식 코드MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering
https://github.com/aurooj/WeakGroundedVQA_Capsules
공식 코드Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules
https://github.com/aurooj/shg-vqa
공식 코드Learning Situation Hyper-Graphs for Video Question Answering
https://github.com/aurooj/wsg-vqa-vltransformers
공식 코드Weakly Supervised Grounding for VQA in Vision-Language Transformers
https://github.com/avikalp7/VQAtoCQA
공식 코드Adapting Visual Question Answering Models for Enhancing Multimodal Community Q&A Platforms
https://github.com/avinabsaha/hidro-vqa
공식 코드HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment
https://github.com/avinashsai/mml
공식 코드https://github.com/ayesha-ishaq/drivelmm-o1
공식 코드https://github.com/baai-dcai/m3d
공식 코드M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models
https://github.com/baai-dcai/spatialbot
공식 코드SpatialBot: Precise Spatial Understanding with Vision Language Models
https://github.com/baaivision/densefusion
공식 코드DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
https://github.com/baaivision/emu
공식 코드https://github.com/baeseongsu/ehrxqa
공식 코드https://github.com/baeseongsu/mimic-cxr-vqa
공식 코드https://github.com/baidu/DuReader/tree/master/DuReader-Robust
공식 코드https://github.com/bangliu/ACS-QG
공식 코드Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
https://github.com/beacon-3d/beacon-3d
공식 코드https://github.com/beckschen/llavolta
공식 코드Efficient Large Multi-modal Models via Visual Context Compression
https://github.com/believewhat/SemiHVision
공식 코드https://github.com/benyv/uncord
공식 코드https://github.com/benywon/ChiQA
공식 코드ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding
https://github.com/benywon/ComQA
공식 코드ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks
https://github.com/benywon/ReCO
공식 코드ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion
https://github.com/beyondguo/genius
공식 코드https://github.com/bflameswift/uni-mumer
공식 코드https://github.com/bfshi/AbSViT
공식 코드https://github.com/bhanukamanesha/ramen
공식 코드Improved RAMEN: Towards Domain Generalization for Visual Question Answering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.