Papers with Code 아카이브
Dense Captioning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 4
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs
TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action
3D Spatial Understanding in MLLMs: Disambiguation and Evaluation
PerLA: Perceptive 3D Language Assistant
3D Scene Graph Guided Vision-Language Pre-training
ComiCap: A VLMs pipeline for dense captioning of Comic Panels
Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving
xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
See It All: Contextualized Late Aggregation for 3D Dense Captioning
Bi-directional Contextual Attention for 3D Dense Captioning
PaveCap: The First Multimodal Framework for Comprehensive Pavement Condition Assessment with Dense Captioning and PCI Estimation
Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions
3D Vision and Language Pretraining with Large-Scale Synthetic Data
Live Video Captioning
Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning
Grounded 3D-LLM with Referent Tokens
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization
DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection
Streaming Dense Video Captioning
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
Entity6K: A Large Open-Domain Evaluation Dataset for Real-World Entity Recognition
Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning
FlexCap: Describe Anything in Images in Controllable Detail
A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes
ControlCap: Controllable Region-level Captioning
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment
3D-LLM: Injecting the 3D World into Large Language Models
Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner
IIITD-20K: Dense captioning for Text-Image ReID
CapDet: Unifying Dense Captioning and Open-World Detection Pretraining
End-to-End 3D Dense Captioning with Vote2Cap-DETR
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.