This report presents an efficient method for semi-supervised video object segmentation – the problem of identifying foreground pixels occupied by a target object. The target is specified by the ground-truth mask in the first video frame. While the state of the art achieves a segmentation accuracy greater than 80%, it...
This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
This dissertation addresses few-shot object segmentation in images. The goal of segmentation is to label every image pixel with a class of the object occupying that pixel, where the class may represent a semantic object category or instance. In few-shot segmentation, training and test datasets have different classes. Every new...
This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...
This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
In this dissertation, we address action segmentation in videos under limited supervision. The goal of action segmentation is to predict an action class for each frame of a video. The limited supervision means ground truth labels of video frames are not available in training. We focus on three types of...
Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...