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.
MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding
Comprehensive Multi-Modal Interactions for Referring Image Segmentation
Locate then Segment: A Strong Pipeline for Referring Image Segmentation
ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
Actor and Action Modular Network for Text-based Video Segmentation
RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation
Referring Image Segmentation via Cross-Modal Progressive Comprehension
PhraseCut: Language-based Image Segmentation in the Wild
Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters
Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
Recurrent Instance Segmentation using Sequences of Referring Expressions
Referring Expression Object Segmentation with Caption-Aware Consistency
Cross-Modal Self-Attention Network for Referring Image Segmentation
CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions
Video Object Segmentation with Language Referring Expressions
Actor and Action Video Segmentation from a Sentence
MAttNet: Modular Attention Network for Referring Expression Comprehension
Segmentation from Natural Language Expressions
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.