Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video
Manual annotations of temporal bounds for object interactions (i.e. start and end times) are typical training input to recognition, localization and detection algorithms. For three publicly available egocentric datasets, we uncover inconsistencies in ground truth temporal bounds within and across annotators and datasets. We systematically assess the robustness of state-of-the-art approaches to changes in labeled temporal bounds, for object interaction recognition. As boundaries are trespassed, a drop of up to 10% is observed for both Improved Dense Trajectories and Two-Stream Convolutional Neural Network. We demonstrate that such disagreement stems from a limited understanding of the distinct phases of an action, and propose annotating based on the Rubicon Boundaries, inspired by a similarly named cognitive model, for consistent temporal bounds of object interactions. Evaluated on a public dataset, we report a 4% increase in overall accuracy, and an increase in accuracy for 55% of classes when Rubicon Boundaries are used for temporal annotations.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSimilar Papers 제목 키워드 기반
The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness
Computer scientists are trained to create abstractions that simplify and generalize. However, a premature abstraction that omits crucial contextual details creates the risk of epistemic trespassing, by falsely asserting …
EthicsFairnessCoherent Parametric Contours for Interactive Video Object Segmentation
Interactive video segmentation systems aim at producing sub-pixel-level object boundaries for visual effect applications. Recent approaches mainly focus on using sparse user input (i.e. scribbles) for efficient segmentat…
Interactive Video Object SegmentationObjectSegmentationSemantic Segmentation+3Learning Objective Boundaries for Constraint Optimization Problems
Constraint Optimization Problems (COP) are often considered without sufficient knowledge on the boundaries of the objective variable to optimize. When available, tight boundaries are helpful to prune the search space or …
Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels
Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective …
Pseudo LabelSegmentationOn the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams
Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos. Typically, although their intrinsic subjectiveness, temporal bounds are prov…
Action RecognitionActivity RecognitionEgocentric Activity RecognitionTemporal Action Localization