Aligning Videos in Space and Time
This addresses a fine-grained video alignment challenge for computer vision applications, but it is incremental as it builds on existing cycle-consistency ideas.
The paper tackles the problem of aligning semantically similar patches across videos in both space and time, proposing a cross video cycle-consistency method that learns correspondences without requiring extensive labeled training data, achieving successful results on the Penn Action and Pouring datasets.
In this paper, we focus on the task of extracting visual correspondences across videos. Given a query video clip from an action class, we aim to align it with training videos in space and time. Obtaining training data for such a fine-grained alignment task is challenging and often ambiguous. Hence, we propose a novel alignment procedure that learns such correspondence in space and time via cross video cycle-consistency. During training, given a pair of videos, we compute cycles that connect patches in a given frame in the first video by matching through frames in the second video. Cycles that connect overlapping patches together are encouraged to score higher than cycles that connect non-overlapping patches. Our experiments on the Penn Action and Pouring datasets demonstrate that the proposed method can successfully learn to correspond semantically similar patches across videos, and learns representations that are sensitive to object and action states.