5 papers
Beyond Appearance: A Multi-cue Framework and Large-scale Benchmark for Pedestrian Association and Tracking on Mobile Aerial-Ground Platforms
Ruiqi Wu, Bingliang Jiao, Ruize Han +6
Multi-view Multi-object Association and Tracking (MvMoAT) associates objects across camera views and tracks them over time, supporting identity persistence and forensic trajectory…
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk…
Sustainable Self-evolution Adversarial Training
Wenxuan Wang, Chenglei Wang, Huihui Qi +4
With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deepl…
SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks
Shining Wang, Yunlong Wang, Ruiqi Wu +3
When discussing the Aerial-Ground Person Re-identification (AGPReID) task, we face the main challenge of the significant appearance variations caused by different viewpoints, makin…
Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification
Hongyu Chen, Bingliang Jiao, Wenxuan Wang +1
Lifelong person re-identification attempts to recognize people across cameras and integrate new knowledge from continuous data streams. Key challenges involve addressing catastroph…