https://github.com/bhi-research/ava_mdetr
공식 코드Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos
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/bibisbar/LLaVA-Steering
공식 코드https://github.com/billchan226/halc
공식 코드HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
https://github.com/biluyong/cityeqa
공식 코드CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
https://github.com/biomedia-mbzuai/medpromptx
공식 코드MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis
https://github.com/boheumd/MA-LMM
공식 코드MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
https://github.com/bowen-upenn/Multi-Agent-VQA
공식 코드Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering
https://github.com/boyuanzheng010/SemEval2021-Reading-Comprehension-of-Abstract-Meaning
공식 코드SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning
https://github.com/bradyfu/awesome-multimodal-large-language-models
공식 코드Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
https://github.com/brandonman123/videocad
공식 코드https://github.com/bright2013/CorefAwareMRC
공식 코드Tracing Origins: Coreference-aware Machine Reading Comprehension
https://github.com/bronyayang/HallE_Switch
공식 코드HallE-Control: Controlling Object Hallucination in Large Multimodal Models
https://github.com/bronyayang/halle_control
공식 코드HallE-Control: Controlling Object Hallucination in Large Multimodal Models
https://github.com/brown-palm/visual-question-decomposition
공식 코드Analyzing Modular Approaches for Visual Question Decomposition
https://github.com/bscho333/ReVisiT
공식 코드https://github.com/btzyd/qava
공식 코드QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
https://github.com/bytedance/MTVQA
공식 코드MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
https://github.com/bytedance/lvlm_interpretation
공식 코드Where do Large Vision-Language Models Look at when Answering Questions?
https://github.com/bytedance/tarsier
공식 코드https://github.com/bytetriper/lm4lv
공식 코드LM4LV: A Frozen Large Language Model for Low-level Vision Tasks
https://github.com/byungkwanlee/meteor
공식 코드Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
https://github.com/byungkwanlee/phantom
공식 코드https://github.com/byungkwanlee/trol
공식 코드TroL: Traversal of Layers for Large Language and Vision Models
https://github.com/bzluan/textcot
공식 코드TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding
https://github.com/c-patsch/okcv
공식 코드Outside Knowledge Conversational Video (OKCV) Dataset -- Dialoguing over Videos
https://github.com/cambridgeltl/topviewrs
공식 코드TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
https://github.com/cambridgeltl/visual-spatial-reasoning
공식 코드https://github.com/camma-public/ssg-qa
공식 코드https://github.com/camma-public/ssg-vqa
공식 코드https://github.com/castorini/unirag
공식 코드UniRAG: Universal Retrieval Augmentation for Large Vision Language Models
https://github.com/catalina17/VideoNavQA
공식 코드VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
https://github.com/cather-chen/logical-reasoning-graph
공식 코드https://github.com/cciiplab/dpt
공식 코드Declaration-based Prompt Tuning for Visual Question Answering
https://github.com/ccqym/osmlocator
공식 코드OsmLocator: locating overlapping scatter marks with a non-training generative perspective
https://github.com/ccychongyanchen/vizwizvqagroundingcrowdsourcing
공식 코드Grounding Answers for Visual Questions Asked by Visually Impaired People
https://github.com/ccychongyanchen/vqatherapycrowdsourcing
공식 코드VQA Therapy: Exploring Answer Differences by Visually Grounding Answers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.