4 accepted papers
Long-form video understanding with Large Vision Language Models is challenged by the need to analyze temporally dispersed yet spatially concentrated key moments within limited context windows. In this work, we introduce VideoMindPalace, a new framework inspired by the "Mind Palace", which organizes…
The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels which real-world vision datasets rarely satisfy. While current synthetic data generators offer a promising alternative particularly fo…
In this paper, we study an intermediate form of supervision, i.e., single-frame supervision, for temporal action localization (TAL). To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action. This can significantly reduce…
We propose a family of cutset sampling schemes and a generalized k-level image reconstruction approach formulated under a minimum mean squared error (MMSE) framework. The k-level reconstruction approach is a direct generalization of the recently proposed pattern-based approach, and can be applied to…