A well-built dataset is a necessary starting point for advanced computer vision research. It plays a crucial role in evaluation and provides a continuous challenge to stateof-the-...
We propose a visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new...
We propose a novel framework for constrained spectral
clustering with pairwise constraints which specify whether
two objects belong to the same cluster or not. Unlike previous
m...
Zhenguo Li (The Chinese University of Hong Kong), ...
Common objects such as people and cars comprise many visual parts and attributes, yet image-based tracking algorithms are often keyed to only one of a target's identifying ch...
We present an improved, prescient, scheme to deliver pre-encoded video streams at very low latency. We dynamically manage the prediction dependency for a group of packets using a ...