https://github.com/xijun-cs/vila
공식 코드ViLA: Efficient Video-Language Alignment for Video 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/xikai97/med-mim
공식 코드Medical Large Vision Language Models with Multi-Image Visual Ability
https://github.com/xing0047/cca-llava
공식 코드Mitigating Object Hallucination via Concentric Causal Attention
https://github.com/xingdi-eric-yuan/imrc_graph_public
공식 코드Interactive Machine Comprehension with Dynamic Knowledge Graphs
https://github.com/xingdi-eric-yuan/imrc_public
공식 코드Interactive Machine Comprehension with Information Seeking Agents
https://github.com/xingdi-eric-yuan/qait_public
공식 코드https://github.com/xingruiwang/3d-aware-vqa
공식 코드3D-Aware Visual Question Answering about Parts, Poses and Occlusions
https://github.com/xingruiwang/spatial457
공식 코드Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models
https://github.com/xinliyue/vqa-generalization
공식 코드Revisiting Video Quality Assessment from the Perspective of Generalization
https://github.com/xinyiW915/SPIE-2023-Supplementary
공식 코드UGC Quality Assessment: Exploring the Impact of Saliency in Deep Feature-Based Quality Assessment
https://github.com/xinyiw915/relax-vqa
공식 코드ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment
https://github.com/xiye17/EvalQAExpl
공식 코드Connecting Attributions and QA Model Behavior on Realistic Counterfactuals
https://github.com/xli04/cvqa
공식 코드MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
https://github.com/xufangzhi/logiformer
공식 코드Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
https://github.com/xuliu-cyber/rsunivlm
공식 코드https://github.com/xxlllz/chartedit
공식 코드https://github.com/xycforgithub/MultiTask-MRC
공식 코드Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
https://github.com/y-d-wang/rsadapter
공식 코드RSAdapter: Adapting Multimodal Models for Remote Sensing Visual Question Answering
https://github.com/yangliu9208/cmcir
공식 코드Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
https://github.com/yanglixiaoshen/provqa
공식 코드Blind VQA on 360° Video via Progressively Learning from Pixels, Frames and Video
https://github.com/yangyue5114/DME
공식 코드Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
https://github.com/yanx27/clevr3d
공식 코드Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation
https://github.com/yanxinzju/CSS-VQA
공식 코드Counterfactual Samples Synthesizing for Robust Visual Question Answering
https://github.com/yaolinli/deco
공식 코드DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
https://github.com/yashkant/concat-vqa
공식 코드https://github.com/yashkant/sam-textvqa
공식 코드https://github.com/yehli/xmodaler
공식 코드X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics
https://github.com/yellow-binary-tree/pfram
공식 코드Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
https://github.com/yfyuan01/ravenea
공식 코드RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
https://github.com/yhzhu99/medagentboard
공식 코드https://github.com/yibowang214/multiner
공식 코드Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach
https://github.com/yihedeng9/stic
공식 코드Enhancing Large Vision Language Models with Self-Training on Image Comprehension
https://github.com/yikai-wang/asuka-misato
공식 코드https://github.com/yilin1111/poi-net
공식 코드Lite Unified Modeling for Discriminative Reading Comprehension
https://github.com/yilin1111/reknet
공식 코드Reference Knowledgeable Network for Machine Reading Comprehension
https://github.com/yinzhangyue/c2fm
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.