https://github.com/alibaba/AliceMind
공식 코드mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
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/alibaba/AliceMind/tree/main/mPLUG
공식 코드mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
https://github.com/allenai/x-lxmert
공식 코드X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
https://github.com/altsoph/modality_shifts
공식 코드Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations
https://github.com/amazon-research/mix-generation
공식 코드https://github.com/amazon-research/read-up
공식 코드Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation
https://github.com/amazon-science/vigor
공식 코드ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling
https://github.com/ankitapasad/layerwise-analysis
공식 코드https://github.com/antoyang/TubeDETR
공식 코드https://github.com/archiki/repare
공식 코드Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
https://github.com/ashkamath/mdetr
공식 코드MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
https://github.com/atharvmane/ges3vig
공식 코드https://github.com/atr-dbi/cityrefer
공식 코드CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
https://github.com/atr-dbi/cross3dvg
공식 코드Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans
https://github.com/bcv-uniandes/png
공식 코드https://github.com/beacon-3d/beacon-3d
공식 코드https://github.com/biomedia-mbzuai/medpromptx
공식 코드MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis
https://github.com/bscho333/ReVisiT
공식 코드https://github.com/cambrian-mllm/cambrian
공식 코드Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
https://github.com/cheliu-computation/g2d-neurips24
공식 코드G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
https://github.com/chenwei746/eevg
공식 코드An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding
https://github.com/chihhuiho/yoro
공식 코드https://github.com/clairecyq/whos-waldo
공식 코드https://github.com/clarence-lee-sheng/determinet
공식 코드https://github.com/computer-vision-in-the-wild/cvinw_readings
공식 코드Vision-Language Pre-training: Basics, Recent Advances, and Future Trends
https://github.com/controlnet/naver
공식 코드NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning
https://github.com/cv516buaa/ir-vg
공식 코드Iterative Robust Visual Grounding with Masked Reference based Centerpoint Supervision
https://github.com/cv516buaa/ov-vg
공식 코드https://github.com/czczup/vit-adapter
공식 코드https://github.com/d-ailin/clip-guided-decoding
공식 코드https://github.com/dahyun-kang/lazygrounding
공식 코드In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation
https://github.com/dcdcvgroup/vglaw-mindspore
공식 코드Language Adaptive Weight Generation for Multi-task Visual Grounding
https://github.com/deepseek-ai/deepseek-vl2
공식 코드DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
https://github.com/dfki-av/mikasa-3dvg
공식 코드MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
https://github.com/djiajunustc/TransVG
공식 코드https://github.com/dmmm1997/c3vg
공식 코드Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.