Papers with Code 아카이브
Referring Expression Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 22
- 보존된 평가 기록
- 317
The task aims at labeling the pixels of an image or video that represent an object instance referred by a linguistic expression. In particular, the referring expression (RE) must allow the identification of an individual object in a discourse or scene (the referent). REs unambiguously identify the target instance.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/80chen86/ipdn
공식 코드IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation
https://github.com/ChenyunWu/PhraseCutDataset
공식 코드https://github.com/DerrickWang005/CRIS.pytorch
공식 코드https://github.com/Dmmm1997/DeRIS
공식 코드https://github.com/FoundationVision/GLEE
공식 코드General Object Foundation Model for Images and Videos at Scale
https://github.com/MasterBin-IIAU/UNINEXT
공식 코드Universal Instance Perception as Object Discovery and Retrieval
https://github.com/RobertLuo1/HDC
공식 코드https://github.com/RobertLuo1/NeurIPS2023_SOC
공식 코드SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
https://github.com/ai-application-and-integration-lab/sam4mllm
공식 코드SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation
https://github.com/aim-uofa/SegAgent
공식 코드https://github.com/amazon-science/polygon-transformer
공식 코드PolyFormer: Referring Image Segmentation as Sequential Polygon Generation
https://github.com/ashkamath/mdetr
공식 코드MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
https://github.com/berkeley-hipie/hipie
공식 코드https://github.com/bhi-research/ava_mdetr
공식 코드Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos
https://github.com/bo-miao/HTR
공식 코드Temporally Consistent Referring Video Object Segmentation with Hybrid Memory
https://github.com/bo-miao/sgmg
공식 코드Spectrum-guided Multi-granularity Referring Video Object Segmentation
https://github.com/buptlwz/mabp
공식 코드Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation
https://github.com/congvvc/HyperSeg
공식 코드HyperSeg: Towards Universal Visual Segmentation with Large Language Model
https://github.com/deepglint/unicom
공식 코드Multi-label Cluster Discrimination for Visual Representation Learning
https://github.com/dexianghong/manet
공식 코드Multi-Attention Network for Compressed Video Referring Object Segmentation
https://github.com/dmmm1997/c3vg
공식 코드Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
https://github.com/dvlab-research/Seg-Zero
공식 코드Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
https://github.com/dvlab-research/VisionReasoner
공식 코드VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
https://github.com/fawnliu/tris
공식 코드https://github.com/foundationvision/uniref
공식 코드UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
https://github.com/henghuiding/ReLA
공식 코드https://github.com/henghuiding/Vision-Language-Transformer
공식 코드Vision-Language Transformer and Query Generation for Referring Segmentation
https://github.com/heshuting555/dshmp
공식 코드Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
https://github.com/hiyouga/easyr1
공식 코드VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
https://github.com/hkchengrex/Tracking-Anything-with-DEVA
공식 코드https://github.com/hustvl/evf-sam
공식 코드EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
https://github.com/hustvl/groundingsuite
공식 코드GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
https://github.com/ilkerkesen/bvpr
공식 코드Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters
https://github.com/imatge-upc/synthref
공식 코드SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation
https://github.com/jiaqihuang01/detris
공식 코드Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.