https://github.com/weitaikang/segvg
공식 코드SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
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/willemsenbram/a-game-of-sorts
공식 코드https://github.com/wusize/f-lmm
공식 코드https://github.com/xiangchenchao/ddpn
공식 코드Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding
https://github.com/xuyang-liu16/vgdiffzero
공식 코드VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
https://github.com/yan98/gta1
공식 코드https://github.com/yangli18/vltvg
공식 코드Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
https://github.com/yanmin-wu/eda
공식 코드EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
https://github.com/yashkant/sam-textvqa
공식 코드https://github.com/yayafengzi/LMM-HiMTok
공식 코드HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model
https://github.com/yifeisu/avdn-challenge
공식 코드Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog Navigation
https://github.com/yifeisu/tg-gat
공식 코드Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog Navigation
https://github.com/youngfly11/LCMCG-PyTorch
공식 코드https://github.com/youngfly11/ReIR-WeaklyGrounding.pytorch
공식 코드Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
https://github.com/yuchenliu98/comm
공식 코드From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
https://github.com/yuqi-zhou/gui-g1
공식 코드GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
https://github.com/yxb-nku/se-gui
공식 코드Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
https://github.com/yxchng/mask-grounding
공식 코드https://github.com/yyjmjc/loupe
공식 코드Fine-Grained Semantically Aligned Vision-Language Pre-Training
https://github.com/zanyarz/NeuralTwinsTalk
공식 코드https://github.com/zc-zhao/drivemonkey
공식 코드Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving
https://github.com/zengyan-97/x-vlm
공식 코드Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
https://github.com/zengyan-97/x2-vlm
공식 코드X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
https://github.com/zhangxinsong-nlp/XFM
공식 코드https://github.com/zhangzjn/gpt-4v-ad
공식 코드GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection
https://github.com/zhanyang-nwpu/mono3dvg
공식 코드https://github.com/zhanyang-nwpu/rsvg-pytorch
공식 코드RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data
https://github.com/zhanyang-nwpu/skyeyegpt
공식 코드https://github.com/zhaoziheng/sat-ds
공식 코드One Model to Rule them All: Towards Universal Segmentation for Medical Images with Text Prompts
https://github.com/zhjohnchan/sk-vg
공식 코드Advancing Visual Grounding with Scene Knowledge: Benchmark and Method
https://github.com/zinengtang/VidLanKD
공식 코드VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
https://github.com/ziyuguo99/viewrefer3d
공식 코드ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
https://github.com/zyang-ur/ReSC
공식 코드Improving One-stage Visual Grounding by Recursive Sub-query Construction
https://github.com/zyang-ur/SAT
공식 코드https://github.com/zyang-ur/onestage_grounding
공식 코드https://github.com/zytx121/awesome-vlgfm
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.