No article text was recorded for this version.
caption sparsity
Version 1 of 1189 papers193 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
- Blog: Learning to Relate from Captions and Bounding Boxes
- Blog: Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
- Blog: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
- Blog: Automatic Radiology Reports Generation via Memory Alignment Network
- Blog: AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization
- Blog: CapDet: Unifying Dense Captioning and Open-World Detection Pretraining
- Blog: Reconstruction Alignment Improves Unified Multimodal Models
- Blog: CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
- Blog: SemanticAC: Semantics-Assisted Framework for Audio Classification
- Blog: De-Diffusion Makes Text a Strong Cross-Modal Interface
- Blog: Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
- Blog: Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models
- Blog: Benchmarking and Improving Fine-Grained Text-to-Image Alignment via Paired Reinforcement Learning
- Blog: Self-Supervised Visual Representations for Cross-Modal Retrieval
- Blog: COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation
- Blog: BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
- Blog: VS-Boost: Boosting Visual-Semantic Association for Generalized Zero-Shot Learning
- Blog: How far can we go with ImageNet for Text-to-Image generation?
- Blog: Comprehensive Multi-Modal Prototypes Are Simple and Effective Classifiers for Vast-Vocabulary Object Detection
- Blog: Dimba: Transformer-Mamba Diffusion Models
- Blog: Enriching Texture Analysis with Semantic Data
- Blog: ShareGPT4V: Improving Large Multi-modal Models with Better Captions
- Blog: Parrot Captions Teach CLIP to Spot Text
- Blog: AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
- Blog: FLAIR: VLM with Fine-grained Language-informed Image Representations
- Blog: Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection
- Blog: Harmonizing Visual Text Comprehension and Generation
- Blog: A Framework For Image Synthesis Using Supervised Contrastive Learning
- Blog: Associating Spatially-Consistent Grouping with Text-supervised Semantic Segmentation
- Blog: HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding
- Blog: Fine-grained Audible Video Description
- Blog: Dialogue Director: Bridging the Gap in Dialogue Visualization for Multimodal Storytelling
- Blog: Text Embedding Bank for Detailed Image Paragraph Captioning
- Blog: MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY
- Blog: Connecting Vision and Language with Localized Narratives
- Blog: VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
- Blog: Diffusion Feedback Helps CLIP See Better
- Blog: Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision
- Blog: Improving Multi-modal Large Language Model through Boosting Vision Capabilities
- Blog: SEPS: Semantic-Enhanced Patch Slimming Framework for Fine-Grained Cross-Modal Alignment
- Blog: Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
- Blog: Retrieval-Augmented Open-Vocabulary Object Detection
- Blog: OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning
- Blog: ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
- Blog: MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
- Blog: Visual Instruction Tuning with Polite Flamingo
- Blog: Neural Machine Translation with Phrase-Level Universal Visual Representations
- Blog: Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content
- Blog: Scene Parsing through ADE20K Dataset
- Blog: Quality and Quantity: Unveiling a Million High-Quality Images for Text-to-Image Synthesis in Fashion Design
- Blog: X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
- Blog: Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
- Blog: DreamLIP: Language-Image Pre-training with Long Captions
- Blog: Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- Blog: GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task
- Blog: SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
- Blog: PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks
- Blog: FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification
- Blog: ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Showing 60 of 189 papers.
History & citation
Current · Permanent link
- Dense Vision Language Learning from Sparse Supervision merged into this direction (73% overlap)
- Dense Recaptioning for Fine-Grained Vision-Language Alignment merged into this direction (51% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_caption_sparsity_4b6f72f5,
title = {caption sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/caption-sparsity/rdr_4b6f72f5e22a4135a9beb80e88e7cb00},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_caption_sparsity_4b6f72f5_v1,
title = {caption sparsity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/caption-sparsity/rdr_4b6f72f5e22a4135a9beb80e88e7cb00/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}