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/iqua/vggbase
공식 코드https://github.com/ivan-tang-3d/viewrefer3d
공식 코드ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
https://github.com/jacobswan1/MTG-pytorch
공식 코드https://github.com/jasonppy/fast-vgs-family
공식 코드https://github.com/jasonppy/syllable-discovery
공식 코드https://github.com/jasonppy/word-discovery
공식 코드Word Discovery in Visually Grounded, Self-Supervised Speech Models
https://github.com/jefferyzhan/griffon
공식 코드Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models
https://github.com/jhcho99/coformer
공식 코드Collaborative Transformers for Grounded Situation Recognition
https://github.com/jhcho99/gsrtr
공식 코드https://github.com/jhuang81/weak-sup-visual-grounding
공식 코드Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
https://github.com/jinyuanli0012/pgim
공식 코드LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition
https://github.com/jizhizili/rim
공식 코드https://github.com/kamperh/vqwordseg
공식 코드Word Discovery in Visually Grounded, Self-Supervised Speech Models
https://github.com/kasuba-badri-vishal/dhrishtikon
공식 코드DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images
https://github.com/lackel/agla
공식 코드https://github.com/leaplabthu/pseudo-q
공식 코드Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
https://github.com/leon1207/3dgctr
공식 코드https://github.com/leon1207/3dreftr
공식 코드https://github.com/leonnnop/locater
공식 코드Local-Global Context Aware Transformer for Language-Guided Video Segmentation
https://github.com/lhao499/instructrl
공식 코드https://github.com/li-qingyun/mllm-mmrotate
공식 코드A Simple Aerial Detection Baseline of Multimodal Language Models
https://github.com/linhuixiao/clip-vg
공식 코드CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual Grounding
https://github.com/linhuixiao/hivg
공식 코드HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding
https://github.com/liudaizong/awesome-3d-visual-grounding
공식 코드A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions
https://github.com/liuting20/dara
공식 코드DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding
https://github.com/liuting20/swimvg
공식 코드SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding
https://github.com/lizhou-cs/jointnlt
공식 코드Joint Visual Grounding and Tracking with Natural Language Specification
https://github.com/lluma/OCID-Ref
공식 코드OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
https://github.com/lqh52/promvil
공식 코드Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models
https://github.com/ltl3a87/compa
공식 코드Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
https://github.com/lukeforeveryoung/qrnet
공식 코드https://github.com/lx709/vrsbench
공식 코드VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
https://github.com/lxtgh/denseworld-1m
공식 코드DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
https://github.com/mhamilton723/DenseAV
공식 코드Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language
https://github.com/microsoft/SoM
공식 코드Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.