https://github.com/dmmm1997/simvg
공식 코드SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
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/doc-doc/vRGV
공식 코드https://github.com/dreichCSL/GQA_generalization_splits
공식 코드https://github.com/dreichcsl/fpvg
공식 코드https://github.com/dreichcsl/truevg
공식 코드Uncovering the Full Potential of Visual Grounding Methods in VQA
https://github.com/drigoni/Loss_VT_Grounding
공식 코드https://github.com/dzcgaara/HuBo-VLM
공식 코드HuBo-VLM: Unified Vision-Language Model designed for HUman roBOt interaction tasks
https://github.com/erobic/negative_analysis_of_grounding
공식 코드Visual Grounding Methods for VQA are Working for the Wrong Reasons!
https://github.com/eslambakr/CoT3D_VG
공식 코드CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
https://github.com/eslambakr/LAR-Look-Around-and-Refer
공식 코드Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding
https://github.com/evolvinglmms-lab/mgpo
공식 코드High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
https://github.com/facebookresearch/connect-caption-and-trace
공식 코드Connecting What to Say With Where to Look by Modeling Human Attention Traces
https://github.com/fjhzhixi/3d-sps
공식 코드3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
https://github.com/foundation-multimodal-models/world2code
공식 코드https://github.com/fpsluozi/tofindwaldo
공식 코드To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo
https://github.com/function2-llx/mmmm
공식 코드VividMed: Vision Language Model with Versatile Visual Grounding for Medicine
https://github.com/gavin001201/cof
공식 코드CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models
https://github.com/gicheonkang/DAN-VisDial
공식 코드Dual Attention Networks for Visual Reference Resolution in Visual Dialog
https://github.com/gicheonkang/prograsp
공식 코드PROGrasp: Pragmatic Human-Robot Communication for Object Grasping
https://github.com/google/localized-narratives
공식 코드https://github.com/gpantaz/vl_mamba
공식 코드https://github.com/gsig/visual-grounding
공식 코드https://github.com/gtziafas/hots
공식 코드Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach
https://github.com/gtziafas/ocid-vlg
공식 코드Language-guided Robot Grasping: CLIP-based Referring Grasp Synthesis in Clutter
https://github.com/guanrunwei/talk2radar
공식 코드Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension
https://github.com/gwxuan/tsp3d
공식 코드Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding
https://github.com/hasanar1f/llava-hallunication-fix
공식 코드PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
https://github.com/hasanar1f/paint
공식 코드PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
https://github.com/hazel-heejeong-nam/vague
공식 코드Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset
https://github.com/hazel1994/visually_grounded_word_embeddings_2
공식 코드Language with Vision: a Study on Grounded Word and Sentence Embeddings
https://github.com/heendung/simpleaug
공식 코드https://github.com/heshuting555/refmask3d
공식 코드RefMask3D: Language-Guided Transformer for 3D Referring Segmentation
https://github.com/hobbitqia/unimoco
공식 코드UniMoCo: Unified Modality Completion for Robust Multi-Modal Embeddings
https://github.com/i-m-vivek/AttnGrounder
공식 코드https://github.com/idea-research/dq-detr
공식 코드DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding
https://github.com/idejie/3DSyn
공식 코드3D Vision and Language Pretraining with Large-Scale Synthetic Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.