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/ddupont808/gpt-4v-act
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
https://github.com/divelab/vqa-text
https://github.com/earth-insights/ClassTrans
Aligning and Prompting Everything All at Once for Universal Visual Perception
https://github.com/even-jk/peft-3d
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
https://github.com/facebookresearch/corefnmn
Visual Coreference Resolution in Visual Dialog using Neural Module Networks
https://github.com/facebookresearch/multimodal
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
https://github.com/facebookresearch/vilbert-multi-task
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/fuqianya/ViLBERT-Paddle
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/gabegrand/adversarial-vqa
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
https://github.com/google-research/trecs_image_generation
Text-to-Image Generation Grounded by Fine-Grained User Attention
https://github.com/hwanheelee1993/vilbertscore
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/iqua/m-dgt
https://github.com/ivan-tang-3d/any2point
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
https://github.com/ivan-tang-3d/peft-3d
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
https://github.com/ivan-tang-3d/point-peft
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
https://github.com/jialinwu17/tmpimgs
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/jiasenlu/vilbert_beta
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/jnhwkim/cbp
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
https://github.com/johntiger1/multitask_multimodal
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/kamperh/flickr_semantic_qbe_eval
Semantic query-by-example speech search using visual grounding
https://github.com/lavender105/rsgpt
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
https://github.com/likaixin2000/screenspot-pro-gui-grounding
Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
https://github.com/linhuixiao/awesome-visual-grounding
https://github.com/linhuixiao/oneref
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
https://github.com/ltzheng/agent-studio
https://github.com/lunaproject22/rpa
CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models
https://github.com/luogen1996/simrec
https://github.com/lx709/reobench
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
https://github.com/magic-research/bubogpt
https://github.com/mees/AIS-Alexa-Robot
https://github.com/mees/pickAndPlace-PR2
https://github.com/mmazuecos/reinact2021-impact-of-answers
Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
https://github.com/modelscope/modelscope
https://github.com/nku-shengzheliu/Pytorch-TransVG
https://github.com/phellonchen/DMRM
Dual Attention Networks for Visual Reference Resolution in Visual Dialog
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.