5 papers
Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation
Zhaoyu Liu, Kan Jiang, Murong Ma +3
Precise event spotting (PES) aims to recognize fine-grained events at exact moments and has become a key component of sports analytics. This task is particularly challenging due to…
Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
Qi Zhou, Tianlin Li, Qing Guo +4
Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mis…
LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging
Yunrui Pei, Hongshu Wang, Wenjie Zhang +3
Determining the dynamic data dependency of a step that reads a variable is challenging. It typically requires either exhaustive instrumentation, which becomes prohibitively exp…
FSet: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos
Zhaoyu Liu, Kan Jiang, Murong Ma +3
Analyzing Fast, Frequent, and Fine-grained (F) events presents a significant challenge in video analytics and multi-modal LLMs. Current methods struggle to identify events that…
Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation
Qi Guo, Zhen Tian, Minghao Yao +4
Federated Unlearning (FU) enables clients to selectively remove the influence of specific data from a trained federated learning model, addressing privacy concerns and regulatory r…