Search Results for author:
Found 8 papers, 6 papers with code
Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints
Furthermore, to address the challenge of insufficient multimodal understanding, we leverage pre-trained models based on visual-linguistic fusion representations.
ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming
In this paper, we conduct a comprehensive investigation of MLLM attention mechanisms with LLaVA.
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image.
Descriptive
Generalized Referring Expression Comprehension
+2
A Survey on Benchmarks of Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) are gaining increasing popularity in both academia and industry due to their remarkable performance in various applications such as visual question answering, visual perception, understanding, and reasoning.
OS-FPI: A Coarse-to-Fine One-Stream Network for UAV Geo-Localization
Furthermore, its performance in meter-level localization accuracy is impressive, with 182. 62% improvement in 3-meter accuracy, 164. 17% improvement in 5-meter accuracy, and 137. 43% improvement in 10-meter accuracy.
Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization
However, IR-based methods face several challenges: 1) Pre- and post-processing incur significant computational and storage overhead; 2) The lack of interaction between dual-source features impairs precise spatial perception.
A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
However it still has some limitations, e. g., it can only extract part of the information in the neighborhood and some scale reduction operations will make some fine-grained information lost.
Ranked #1 on
Drone navigation
on University-1652
Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments
Last, we enhance the Recall@K metric and introduce a new measurement, SDM@K, to evaluate the performance of a trained model from both the retrieval and localization perspectives simultaneously.
