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/haoyu-bu/CAFe
공식 코드CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning
https://github.com/harshraj22/vqa
공식 코드https://github.com/harvardnlp/var-attn
공식 코드https://github.com/hashmatshadab/robust-llava
공식 코드https://github.com/hazel-heejeong-nam/vague
공식 코드Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset
https://github.com/hchoi256/i-halla-v1.0
공식 코드Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering
https://github.com/hcplab-sysu/causal-vlreasoning
공식 코드CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
https://github.com/hcplab-sysu/causalvlr
공식 코드CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
https://github.com/hcplab-sysu/cmcir
공식 코드Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
https://github.com/heendung/ii-mmr
공식 코드II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering
https://github.com/heendung/simpleaug
공식 코드https://github.com/heliossun/sq-llava
공식 코드SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
https://github.com/heliossun/stllava-med
공식 코드STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering
https://github.com/hendryx-scale/mhal-detect
공식 코드Detecting and Preventing Hallucinations in Large Vision Language Models
https://github.com/henryhzy/vl-pet
공식 코드VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control
https://github.com/herobd/dessurt
공식 코드End-to-end Document Recognition and Understanding with Dessurt
https://github.com/hfmei/veattack-lvlm
공식 코드VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models
https://github.com/hfutml/calibration-mllm
공식 코드https://github.com/hiba-meiruan/urdu-vqa-dataset-
공식 코드https://github.com/hieunghia-pat/ViConsFormer
공식 코드https://github.com/hieunghia-pat/openvivqa-dataset
공식 코드OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese
https://github.com/hila-chefer/Transformer-MM-Explainability
공식 코드Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
https://github.com/him1411/edgar10q-dataset
공식 코드https://github.com/hitsz-tmg/cognitive-visual-language-mapper
공식 코드A Comprehensive Evaluation of GPT-4V on Knowledge-Intensive Visual Question Answering
https://github.com/hitsz-tmg/umoe-scaling-unified-multimodal-llms
공식 코드Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts
https://github.com/hiyouga/easyr1
공식 코드https://github.com/hkust-nlp/vision4chart
공식 코드On the Perception Bottleneck of VLMs for Chart Understanding
https://github.com/hlr/lovis
공식 코드LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation
https://github.com/hlr/nesycoco
공식 코드NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization
https://github.com/holipori/mimic-diff-vqa
공식 코드https://github.com/howardhsu/RCRC
공식 코드https://github.com/hrl-mike/pitvqa-plus
공식 코드https://github.com/hs-yn/daps
공식 코드Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation
https://github.com/hs-yn/panoavqa
공식 코드Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\circ$ Videos
https://github.com/hs-yn/paver
공식 코드Panoramic Vision Transformer for Saliency Detection in 360° Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.