5 papers
Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges
Senyao Li, Haozhao Wang, Wenchao Xu +6
As large language models (LLMs) evolve, deploying them solely in the cloud or compressing them for edge devices has become inadequate due to concerns about latency, privacy, cost,…
Expanding Zero-Shot Object Counting with Rich Prompts
Huilin Zhu, Senyao Li, Jingling Yuan +5
Expanding pre-trained zero-shot counting models to handle unseen categories requires more than simply adding new prompts, as this approach does not achieve the necessary alignment…
FocalCount: Towards Class-Count Imbalance in Class-Agnostic Counting
Huilin Zhu, Jingling Yuan, Zhengwei Yang +3
In class-agnostic object counting, the goal is to estimate the total number of object instances in an image without distinguishing between specific categories. Existing methods oft…
DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy
Yi Lei, Huilin Zhu, Jingling Yuan +3
Drone-based crowd tracking faces difficulties in accurately identifying and monitoring objects from an aerial perspective, largely due to their small size and close proximity to ea…
Zero-shot Object Counting with Good Exemplars
Huilin Zhu, Jingling Yuan, Zhengwei Yang +4
Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a criti…