https://github.com/qizekun/ReCon
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
Papers with Code 아카이브
Visual Grounding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 4
- 보존된 평가 기록
- 20
Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence, or even a multi-round dialogue. There are three main challenges in VG:
- What is the main focus in a query?
- How to understand an image?
- How to locate an object?
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/rabiulcste/vqazero
Kosmos-2: Grounding Multimodal Large Language Models to the World
https://github.com/ruipingl/opensu
Collaborative Transformers for Grounded Situation Recognition
https://github.com/runpeidong/act
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/satwikkottur/VisualWord2Vec
Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
https://github.com/seanzhuh/seqtr
https://github.com/shekharRavi/Beyond-Task-Success-NAACL2019
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
https://github.com/styfeng/tinydialogues
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes
https://github.com/thunlp/pevl
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
https://github.com/towhee-io/towhee/tree/main/towhee/models/coformer
Collaborative Transformers for Grounded Situation Recognition
https://github.com/unclemedm/instpifu
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
https://github.com/ux-decoder/segment-everything-everywhere-all-at-once
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
https://github.com/vision-cair/minigpt-4
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
https://github.com/vmurahari3/visdial-bert
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/vuhoangminh/vqa_medical
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
https://github.com/wusize/harmon
https://github.com/x-plug/mplug
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
https://github.com/x-plug/mplug-owl
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
https://github.com/xiaofeng94/gen-enhanced-negs
LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
https://github.com/xubuvd/guesswhat
https://github.com/yikang-li/iqan
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
https://github.com/yunzeman/lexicon3d
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
https://github.com/yunzhuli/vgpl-dynamics-prior
https://github.com/zebangcheng/emotion-llama
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
https://github.com/zhanghanbo/invig-dataset
InViG: Benchmarking Interactive Visual Grounding with 500K Human-Robot Interactions
https://github.com/zhaoziheng/sat
One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts
https://github.com/zhihaozhang97/ru-ai
Text-Free Image-to-Speech Synthesis Using Learned Segmental Units
https://github.com/zihaow123/unimm
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/zixuwang1996/VQA-reading-list
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.