Papers with Code 아카이브
Referring Expression
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 1
Referring expressions places a bounding box around the instance corresponding to the provided description and image.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
Referring Expression Instance Retrieval and A Strong End-to-End Baseline
Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation
Synthetic Visual Genome
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes
Refer to Anything with Vision-Language Prompts
Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning
RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
Improving Contrastive Learning for Referring Expression Counting
Deformable Attentive Visual Enhancement for Referring Segmentation Using Vision-Language Model
WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation
RemoteSAM: Towards Segment Anything for Earth Observation
Learning to Reason and Navigate: Parameter Efficient Action Planning with Large Language Models
RESAnything: Attribute Prompting for Arbitrary Referring Segmentation
Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation
LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation
3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation
Towards Unified Referring Expression Segmentation Across Omni-Level Visual Target Granularities
4th PVUW MeViS 3rd Place Report: Sa2VA
MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing
Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding
Exploring Contextual Attribute Density in Referring Expression Counting
GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing
Cognitive Disentanglement for Referring Multi-Object Tracking
GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis
New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration
PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?
Exploring Spatial Language Grounding Through Referring Expressions
NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning
RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes
Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities
FLORA: Formal Language Model Enables Robust Training-free Zero-shot Object Referring Analysis
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.