Search Results for author:
Found 31 papers, 15 papers with code
Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
Abundant recent methods aim to solve this problem with token pruning, which first defines an importance criterion for tokens and then prunes the unimportant vision tokens during inference.
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs.
Where am I? Cross-View Geo-localization with Natural Language Descriptions
In this work, we introduce a novel task for cross-view geo-localization with natural language descriptions, which aims to retrieve corresponding satellite images or OSM database based on scene text.
Beyond Static Assumptions: the Predictive Justified Perspective Model for Epistemic Planning
We then implemented the PJP model in several well-known domains and compared it with the JP model in the experiments.
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data increasingly challenging.
UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios
Moreover, existing urban benchmarks have been limited to evaluating LMMs with basic region-level urban tasks under singular views, leading to incomplete evaluations of LMMs' abilities in urban environments.
CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis
In this work, we propose CrossViewDiff, a cross-view diffusion model for satellite-to-street view synthesis.
Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning, broadening its applicability to various building function categorization systems.
Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network
In the existing retrieval of street view panorama images and satellite images, we introduce BEV and satellite image retrieval branches for collaborative retrieval.
SkyDiffusion: Ground-to-Aerial Image Synthesis with Diffusion Models and BEV Paradigm
In this paper, we introduce SkyDiffusion, a novel cross-view generation method for synthesizing aerial images from street view images, utilizing a diffusion model and the Bird's-Eye View (BEV) paradigm.
Haze-Aware Attention Network for Single-Image Dehazing
Our work not only advances the field of image dehazing but also offers insights into the design of attention mechanisms for broader applications in computer vision.
Vision Transformer with Key-select Routing Attention for Single Image Dehazing
We present Ksformer, utilizing Multi-scale Key-select Routing Attention (MKRA) for intelligent selection of key areas through multi-channel, multi-scale windows with a top-k operator, and Lightweight Frequency Processing Module (LFPM) to enhance high-frequency features, outperforming other dehazing methods in tests.
Exploring Test-Time Adaptation for Object Detection in Continually Changing Environments
We demonstrate the effectiveness of AMROD on four CTTA object detection tasks, where AMROD outperforms existing methods, especially achieving a 3. 2 mAP improvement and a 20% increase in efficiency on the Cityscapes-to-Cityscapes-C CTTA task.
A$^{2}$-MAE: A spatial-temporal-spectral unified remote sensing pre-training method based on anchor-aware masked autoencoder
A$^{2}$-MAE integrates an anchor-aware masking strategy and a geographic encoding module to comprehensively exploit the properties of RS images.
Parallel Cross Strip Attention Network for Single Image Dehazing
The objective of single image dehazing is to restore hazy images and produce clear, high-quality visuals.
3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions
3D building reconstruction from monocular remote sensing images is an important and challenging research problem that has received increasing attention in recent years, owing to its low cost of data acquisition and availability for large-scale applications.
SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation
This paper aims at achieving fine-grained building attribute segmentation in a cross-view scenario, i. e., using satellite and street-view image pairs.
VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD).
Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model
Specifically, we inject the priors into the denoising model to improve the utilization of reference information in unchanged areas and regulate the reconstruction of semantically relevant content in changed areas.
Parrot Captions Teach CLIP to Spot Text
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias.
A review of individual tree crown detection and delineation from optical remote sensing images
); (2) traditional machine learning methods (such as random forest, decision tree, etc.
VIGC: Visual Instruction Generation and Correction
A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks.
An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions
For the cloth-changing problem, video-based ReID is rarely studied due to the lack of a suitable cloth-changing benchmark, and gait recognition is often researched under controlled conditions.
Large-Scale Land Cover Mapping with Fine-Grained Classes via Class-Aware Semi-Supervised Semantic Segmentation
Moreover, we propose the Class Center Contrast method to jointly utilize the labeled and unlabeled data.
SEPT: Towards Scalable and Efficient Visual Pre-Training
To address these issues, we build a task-specific self-supervised pre-training framework from a data selection perspective based on a simple hypothesis that pre-training on the unlabeled samples with similar distribution to the target task can bring substantial performance gains.
OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
More precisely, the OmniCity contains multi-view satellite images as well as street-level panorama and mono-view images, constituting over 100K pixel-wise annotated images that are well-aligned and collected from 25K geo-locations in New York City.
Exploring the Interactive Guidance for Unified and Effective Image Matting
Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two limitations: (1) For the single image with multiple objects, it is essential to provide extra interaction information to help determining the matting target; (2) For transparent objects, the accurate regression of alpha matte from RGB image is much more difficult compared with the opaque ones.
Learning to Extract Building Footprints from Off-Nadir Aerial Images
In this paper, we propose an offset vector learning scheme, which turns the building footprint extraction problem in off-nadir images into an instance-level joint prediction problem of the building roof and its corresponding "roof to footprint" offset vector.
Influence Selection for Active Learning
To obtain the Influence of the unlabeled sample in the active learning scenario, we design the Untrained Unlabeled sample Influence Calculation(UUIC) to estimate the unlabeled sample's expected gradient with which we calculate its Influence.
3D Building Reconstruction From Monocular Remote Sensing Images
3D building reconstruction from monocular remote sensing imagery is an important research problem and an economic solution to large-scale city modeling, compared with reconstruction from LiDAR data and multi-view imagery.
Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
In this paper, we propose a novel domain adaptive oil palm tree detection method, i. e., a Multi-level Attention Domain Adaptation Network (MADAN) to reap cross-regional oil palm tree counting and detection.
