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/evolvinglmms-lab/longva
공식 코드https://github.com/evolvinglmms-lab/multimodal-search-r1
공식 코드https://github.com/explainableml/clevr-x
공식 코드CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations
https://github.com/explainableml/zs-a2t
공식 코드Zero-shot Translation of Attention Patterns in VQA Models to Natural Language
https://github.com/facebookresearch/EmbodiedQA
공식 코드https://github.com/facebookresearch/belebele
공식 코드The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants
https://github.com/facebookresearch/causalvqa
공식 코드CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models
https://github.com/facebookresearch/clevr-iep
공식 코드https://github.com/facebookresearch/daqa
공식 코드https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan
공식 코드MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond
https://github.com/facebookresearch/multimodal_rewardbench
공식 코드Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models
https://github.com/facebookresearch/pythia
공식 코드https://github.com/facebookresearch/reliable_vqa
공식 코드Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
https://github.com/facebookresearch/selective-vqa_ood
공식 코드Improving Selective Visual Question Answering by Learning from Your Peers
https://github.com/facebookresearch/sonata
공식 코드Sonata: Self-Supervised Learning of Reliable Point Representations
https://github.com/facebookresearch/vilbert-multi-task
공식 코드12-in-1: Multi-Task Vision and Language Representation Learning
https://github.com/fanchenyou/HME-VideoQA
공식 코드Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
https://github.com/fangbufang/sal
공식 코드Separate and Locate: Rethink the Text in Text-based Visual Question Answering
https://github.com/fangjun-li/roomspace
공식 코드https://github.com/farewellthree/BT-Adapter
공식 코드BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning
https://github.com/farewellthree/ppllava
공식 코드PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
https://github.com/fatemehshiri/spatial-mm
공식 코드An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
https://github.com/fawazsammani/nlxgpt
공식 코드NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
https://github.com/fawazsammani/uni-nlx
공식 코드Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks
https://github.com/fcihraeipnusnacwh/mrc-ce
공식 코드Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension
https://github.com/feielysia/viecap
공식 코드Transferable Decoding with Visual Entities for Zero-Shot Image Captioning
https://github.com/fenglinliu98/MIA
공식 코드Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
https://github.com/ffd8ffe/babelbench
공식 코드BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data
https://github.com/findalexli/SciGraphQA
공식 코드SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs
https://github.com/findalexli/mllm-dpo
공식 코드https://github.com/findalexli/mllm-dpo/blob/main/README.MD
공식 코드https://github.com/flageval-baai/flagevalmm
공식 코드FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation
https://github.com/flair-thu/creamfl
공식 코드Multimodal Federated Learning via Contrastive Representation Ensemble
https://github.com/forjadeforest/icd-lm
공식 코드Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
https://github.com/forjadeforest/lever-lm
공식 코드Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.