https://github.com/nkkbr/vica
공식 코드Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts
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/nlp-anonymous-happy/anonymous-kg-guided-nlp
공식 코드https://github.com/nlp-waseda/traveling-across-languages
공식 코드Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs
https://github.com/nlpcode/tubench
공식 코드TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions
https://github.com/nlpdata/evidence
공식 코드Evidence Sentence Extraction for Machine Reading Comprehension
https://github.com/nlpdata/strategy
공식 코드Improving Machine Reading Comprehension with General Reading Strategies
https://github.com/nnaik39/commvqa
공식 코드CommVQA: Situating Visual Question Answering in Communicative Contexts
https://github.com/nnaik39/context-vqa
공식 코드Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering
https://github.com/noagarcia/ArtVQA
공식 코드A Dataset and Baselines for Visual Question Answering on Art
https://github.com/noagarcia/ROLL-VideoQA
공식 코드Knowledge-Based Video Question Answering with Unsupervised Scene Descriptions
https://github.com/nooralahzadeh/clg-vqa
공식 코드Improving the Cross-Lingual Generalisation in Visual Question Answering
https://github.com/northsummer/proximityqa
공식 코드https://github.com/nttmdlab-nlp/VisualMRC
공식 코드https://github.com/nttmdlab-nlp/slidevqa
공식 코드SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images
https://github.com/nuochenpku/orca
공식 코드Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension
https://github.com/nuochenpku/penguin
공식 코드Natural Response Generation for Chinese Reading Comprehension
https://github.com/nvlabs/lita
공식 코드https://github.com/nvlabs/omnidrive
공식 코드OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning
https://github.com/nvlabs/prismer
공식 코드https://github.com/nvlabs/vila
공식 코드https://github.com/nzantout/sort3d
공식 코드https://github.com/oceanhao/CoNav
공식 코드CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
https://github.com/ofa-sys/ofa
공식 코드https://github.com/ofa-x/ofa-x
공식 코드Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations
https://github.com/om-ai-lab/ZoomEye
공식 코드https://github.com/omron-sinicx/sbsfigures
공식 코드SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images
https://github.com/open-compass/vlmevalkit
공식 코드https://github.com/open-dataflow/vts-v
공식 코드Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification
https://github.com/openai/evals
공식 코드https://github.com/openbmb/omnilmm
공식 코드RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
https://github.com/opencausalab/more
공식 코드Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
https://github.com/opendatalab/h2rsvlm
공식 코드VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
https://github.com/opendatalab/vhm
공식 코드VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
https://github.com/opendrivelab/drivelm
공식 코드https://github.com/opengvlab/all-seeing
공식 코드The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
https://github.com/opengvlab/ask-anything
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.