Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models.

A Multimodal Benchmark and Improved Architecture for Zero Shot Learning.

Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models.

Dynamic Inference with Grounding Based Vision and Language Models.

GOHSP: A Unified Framework of Graph and Optimization-Based Heterogeneous Structured Pruning for Vision Transformer.

Lite-MDETR: A Lightweight Multi-Modal Detector.

Efficient Conditional Pre-training for Transfer Learning.

Negative Data Augmentation.

Geography-Aware Self-Supervised Learning.

Predicting Livelihood Indicators from Community-Generated Street-Level Imagery.

Efficient Poverty Mapping from High Resolution Remote Sensing Images.

Efficient Object Detection in Large Images Using Deep Reinforcement Learning.

Cloud Removal in Satellite Images Using Spatiotemporal Generative Networks.

Generating Interpretable Poverty Maps using Object Detection in Satellite Images.

Learning When and Where to Zoom With Deep Reinforcement Learning.

Farm Parcel Delineation Using Spatio-temporal Convolutional Networks.

Predicting Economic Development using Geolocated Wikipedia Articles.

Learning to Interpret Satellite Images using Wikipedia.

EnKCF: Ensemble of Kernelized Correlation Filters for High-Speed Object Tracking.

Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Maps.

Real-Time Vehicle Tracking in Aerial Video Using Hyperspectral Features.

Spectral Validation of Measurements in a Vehicle Tracking DDDAS.

Efficient integration of spectral features for vehicle tracking utilizing an adaptive sensor.

Feature Matching and Adaptive Prediction Models in an Object Tracking DDDAS.

Pitch-Range Based Feature Extraction for Audio Surveillance Systems.