Search Results for author:
Found 18 papers, 7 papers with code
Learning Adaptive and View-Invariant Vision Transformer with Multi-Teacher Knowledge Distillation for Real-Time UAV Tracking
Specifically, we maximize the MI between the softened feature representations from the multi-teacher models and the student model, leading to improved generalization and performance of the student model, particularly in noisy conditions.
MambaNUT: Nighttime UAV Tracking via Mamba and Adaptive Curriculum Learning
Our ACL is composed of two levels of curriculum schedulers: (1) sampling scheduler that transforms the data distribution from imbalanced to balanced, as well as from easier (daytime) to harder (nighttime) samples; (2) loss scheduler that dynamically assigns weights based on data frequency and the IOU.
Camouflaged Object Tracking: A Benchmark
Visual tracking has seen remarkable advancements, largely driven by the availability of large-scale training datasets that have enabled the development of highly accurate and robust algorithms.
Low-Light Object Tracking: A Benchmark
We hope that our benchmark and H-DCPT will stimulate the development of novel and accurate methods for tracking objects in low-light conditions.
Towards Reflected Object Detection: A Benchmark
Our Reflected Object Detection Dataset (RODD) features a diverse collection of images showcasing reflected objects in various contexts, providing standard annotations for both real and reflected objects.
Tracking Reflected Objects: A Benchmark
To address this gap, we introduce TRO, a benchmark specifically for Tracking Reflected Objects.
Learning Motion Blur Robust Vision Transformers with Dynamic Early Exit for Real-Time UAV Tracking
Another significant enhancement introduced in this paper is the improved effectiveness of ViTs in handling motion blur, a common issue in UAV tracking caused by the fast movements of either the UAV, the tracked objects, or both.
Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Tracking
Empowered by transformer-based models, visual tracking has advanced significantly.
Tracking Transforming Objects: A Benchmark
We provide carefully hand-annotated bounding boxes for each frame within these sequences, making DTTO the pioneering benchmark dedicated to tracking transforming objects.
Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking
Lightweight Deep learning (DL)-based trackers can achieve a good balance between efficiency and precision but performance gains are limited by the compression rate.
Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking
Efficiency has been a critical problem in UAV tracking due to limitations in computation resources, battery capacity, and unmanned aerial vehicle maximum load.
Adaptive and Background-Aware Vision Transformer for Real-Time UAV Tracking
In this paper, we propose an efficient ViT-based tracking framework, Aba-ViTrack, for UAV tracking.
Tracking Small and Fast Moving Objects: A Benchmark
The evaluation results exhibit that more effort are required to improve tracking small and fast moving objects.
Rank-Based Filter Pruning for Real-Time UAV Tracking
Model compression is a promising way to narrow the gap (i. e., effciency, precision) between DCF- and deep learning- based trackers, which has not caught much attention in UAV tracking.
SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images
With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects.
Equivalence of Correlation Filter and Convolution Filter in Visual Tracking
On the surface, correlation filter and convolution filter are usually used for different purposes.
Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking
Unmanned aerial vehicle (UAV)-based tracking is attracting increasing attention and developing rapidly in applications such as agriculture, aviation, navigation, transportation and public security.
The 1st Tiny Object Detection Challenge:Methods and Results
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
