Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 18 of 18 for “"Action segmentation"”.
-
Multi-Modal Models for Fine-grained Action Segmentation in Situated Environments
… enabling new applications in human-robot interaction, surgical data modeling, video summarization, and beyond. Despite decades of research in the fields of robotics and computer vision, current approaches are inadequate for modeling complex activities outside of constrained environments or …
-
Assembly Video Understanding for Human-Robot Collaboration: Methods and Applications
… into a series of primitive tasks and atomic actions. By rigorously and objectively defining these tasks and actions, the assembly process is uniformly and unambiguously represented, meeting both human intuitive understanding and robotic programming requirements. This work focuses on …
-
Foundations of Vocabulary: Does Statistical Segmentation of Events Contribute to Word Learning?
… predicted that 3-year-old children’s statistical action segmentation abilities would relate to their verb comprehension and to their overall vocabulary knowledge (Research Question 1). We also hypothesized that statistical action segmentation would facilitate children’s learning of novel verbs …
-
CHALLENGES AND APPLICATIONS OF FINE-GRAINED TEMPORAL ACTION UNDERSTANDING: MODELING TEMPORAL GRANULARITY AND DATA EFFICIENCY
Fine-grained Temporal Action Segmentation (TAS) has become a cornerstone of video understanding, offering dense frame-level predictions essential for clinical assessment, surgical skill evaluation, and human-computer interaction. While TAS methods have delivered strong results on coarse-grained …
-
TEMPORAL MODELING FOR PROCEDURAL VIDEO UNDERSTANDING
… analyzing long, untrimmed videos with multiple actions, where modeling temporal dependencies is essential for accurate interpretation. This is hindered by action imbalance and missing context in online setting. Such challenges weaken temporal models, reducing the reliability and generalization …
-
Action in Mind : A Neural Network Approach to Action Recognition and Segmentation
Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry.This thesis presents a novel computational approach for human action …
-
Bridging distributional discrepancy with temporal dynamics for video understanding
… temporal dynamics from unlabeled videos for action segmentation, I proposed Self-Supervised Temporal Domain Adaptation (SSTDA) to jointly align cross-domain feature spaces embedded with local and global temporal dynamics by two self-supervised auxiliary tasks, binary and sequential domain …
-
A Unified Multiscale Encoder-Decoder Transformer for Video Segmentation
… for dense video estimation, with a focus on segmentation. We investigate this direction by exploring unified multiscale processing throughout the processing pipeline of feature encoding, context encoding and object decoding in an encoder-decoder model. Correspondingly, we present a Multiscale …
-
Action Recognition, Temporal Localization and Detection in Trimmed and Untrimmed Video
… in video surveillance, human computer interaction, video sports analysis, virtual and augmented reality, video retrieval etc. In this dissertation, we address four important tasks in video understanding, namely action recognition, temporal action localization, spatial-temporal action …
-
SCENE AND ACTION UNDERSTANDING USING CONTEXT AND KNOWLEDGE SHARING
… objects, human pose, scene information etc. for action segmentation. For certain functions like zero shot and few shot action recognition, we learn a classifier for unseen test classes through comparison with similar training classes. We provide information about similarity between two classes …
-
Learning Discriminative Feature Representations for Action Recognition and Segmentation
The recognition of actions and activities has a long history in the computer vision community. State-of-the-art approaches are based on analysis of the distribution of low-level feature descriptors such as space-time interest points and dense trajectories. These feature descriptors are typically …
-
Robust and Generalizable Temporal Video Understanding
… these issues becomes crucial for accurate action recognition, real-time processing, and discovery of novel behaviors in open-world scenarios. This thesis tackles three major challenges in robust temporal video understanding. First, we propose a video pre-training framework for Video …
-
Online Spatiotemporal Action Detection and Prediction via Causal Representations
In this thesis, we focus on video action understanding problems from an online and real-time processing point of view. We start with the conversion of the traditional oine spatiotemporal action detection pipeline into an online spatiotemporal action tube detection system. An action tube is a set of …
-
HUMAN ACTION TEMPORAL DETECTION AND PROBABILISTIC PREDICTION UNDER ABRUPT CHANGING SCENARIOS
… detecting and predicting sudden human action changes remains a formidable challenge due to the erratic and stochastic nature of human behaviors. This dissertation presents the development of efficient and accurate algorithms for understanding human sudden change behaviors and predicting …
-
On the formulation and uses of SVD-based generalized curvatures
… Kinect 2 sensor. To address the topic of action segmentation and recognition, a popular topic within the field of computer vision, we created a new dataset from this sensor showcasing a pose space skeletonized representation of individuals performing continuous human actions as defined by …
-
Pupillometry as a Window on the Role of Motionese in Infants’ Processing of Dynamic Activity
… and learn from a variety of everyday human actions. Finding segmental structure within unfolding activity – in particular, boundaries at which units of action begin and end – seems key to the acquisition of such action-processing fluency, and has important downstream implications for …
-
Unsupervised co-segmentation of actions in motion capture data and videos
We focus on the problem of temporal co-segmentation of actions in sequences of 3D motion capture data and in image sequences (videos). Given two data sequences representing action relevant information, the goal is to detect and temporally co-segment all pairs of matching sub-sequences (segments), …