arXiv Machine Learning June 5, 2026 By Phillip Jiang

HDST-GNN: Heterogeneous Dynamic Spatiotemporal Graph Neural Networks for Multi-Object Tracking in UAV Aerial Imagery

Read the original on arXiv Machine Learning →

arXiv:2606. 05587v1 Announce Type: cross Abstract: Multi-object tracking (MOT) from UAV imagery presents unique challenges: altitude varies across sequences, objects are small and densely packed, and frequent occlusion causes identity switches.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 3

COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm

arXiv:2603. 24016v2 Announce Type: replace-cross Abstract: Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects.

By Zekun Qian, Wei Feng, Ruize Han, Junhui Hou

benchmarks

arXiv AI

1d ago

Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

arXiv:2608. 16142v1 Announce Type: cross Abstract: UAV on-board vision systems are widely used for different activities, including monitoring in no-fly zones.

By Alam Noor, Luis Almeida, Kai Li, Jiyan Wu, Miguel Guti\'errez Gait\'an, Eduardo Tovar

reinforcement-learning benchmarks

Hugging Face Trending Papers

2d ago

Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

UAV on-board vision systems are widely used for different activities, including monitoring in no-fly zones. In this case, the vision-equipped UAV streams a video to a ground server where an operator assists its activities.

reinforcement-learning benchmarks

arXiv AI

Jul 14

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

arXiv:2410. 19553v2 Announce Type: replace-cross Abstract: This paper explores the impact of occlusions in video action detection.

By Rajat Modi, Vibhav Vineet, Yogesh Singh Rawat

llms efficiency benchmarks

arXiv AI

Jun 9

SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

arXiv:2511. 18493v4 Announce Type: replace-cross Abstract: The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity.

By Gia Huy Thai, Hoang-Nguyen Vu, Anh-Minh Phan, Quang-Thinh Ly, Thi-Ngoc-Truc Nguyen, Nhat Ho

llms computer-vision robotics

arXiv AI

Jun 26

Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking

arXiv:2606. 26455v1 Announce Type: cross Abstract: RGB-Event tracking improves localization robustness by fusing RGB appearance textures and dense temporal motion cues from event sensors.

By Xiao Wang, Xufeng Lou, Zikang Yan, Lan Chen, Sibao Chen, Yaowei Wang, Yonghong Tian, Jin Tang

multimodal safety

Related stories

COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm

Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking