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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation
Harnessing Vision-Language Pretrained Models with Temporal-Aware Adaptation for Referring Video Object Segmentation
Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding
Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
Temporally Consistent Referring Video Object Segmentation with Hybrid Memory
PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
UniVS: Unified and Universal Video Segmentation with Prompts as Queries
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation
RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner
Generalizable Entity Grounding via Assistance of Large Language Model
UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
Mask Grounding for Referring Image Segmentation
GSVA: Generalized Segmentation via Multimodal Large Language Models
General Object Foundation Model for Images and Videos at Scale
Unveiling Parts Beyond Objects:Towards Finer-Granularity Referring Expression Segmentation
EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment
Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects
Universal Segmentation at Arbitrary Granularity with Language Instruction
InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation
NExT-Chat: An LMM for Chat, Detection and Segmentation
GLaMM: Pixel Grounding Large Multimodal Model
Towards Omni-supervised Referring Expression Segmentation
CLIPUNetr: Assisting Human-robot Interface for Uncalibrated Visual Servoing Control with CLIP-driven Referring Expression Segmentation
Tracking Anything with Decoupled Video Segmentation
3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation
Referring Image Segmentation Using Text Supervision
Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
EAVL: Explicitly Align Vision and Language for Referring Image Segmentation
Expression Prompt Collaboration Transformer for Universal Referring Video Object Segmentation
Spectrum-guided Multi-granularity Referring Video Object Segmentation
Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
Hierarchical Open-vocabulary Universal Image Segmentation
Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
WiCo: Win-win Cooperation of Bottom-up and Top-down Referring Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.