paper-with-me

Papers

Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video

2017-03-27 · ICCV 2017 10 · Davide Moltisanti, Michael Wray, Walterio Mayol-Cuevas, Dima Damen

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.

📄 PDF Abstract BibTeX arXiv:1703.09026

Code (0)

등록된 구현이 없습니다.

Tasks

Object

Similar Papers 제목 키워드 기반

The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness

2022-02-19 · Elizabeth Anne Watkins, Michael McKenna, Jiahao Chen

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 …

EthicsFairness

Coherent Parametric Contours for Interactive Video Object Segmentation

2016-06-01 · CVPR 2016 6 · Yao Lu, Xue Bai, Linda Shapiro, Jue Wang

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+3

Learning Objective Boundaries for Constraint Optimization Problems

2020-06-20 · Helge Spieker, Arnaud Gotlieb

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

2023-03-30 · Tzeviya Sylvia Fuchs, Yedid Hoshen

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 LabelSegmentation

On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams

2018-09-02 · Alejandro Cartas, Estefania Talavera, Petia Radeva, Mariella Dimiccoli

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