Search Results for author:
Found 13 papers, 1 papers with code
Action Segmentation Using 2D Skeleton Heatmaps
This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition.
Learning by Aligning 2D Skeleton Sequences in Time
This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications.
Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment
The frame-level prediction module is trained in an unsupervised manner via temporal optimal transport.
Timestamp-Supervised Action Segmentation with Graph Convolutional Networks
We introduce a novel approach for temporal activity segmentation with timestamp supervision.
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering
The temporal optimal transport module enables our approach to learn effective representations for unsupervised activity segmentation.
Towards Anomaly Detection in Dashcam Videos
We apply: (i) one-class classification loss and (ii) reconstruction-based loss, for anomaly detection on RetroTrucks as well as on existing static-camera datasets.
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Further, we propose to use activation maps at different layers of a CNN, as an effective and principled replacement for the multi-resolution image pyramids often used for matching tasks.
Deep Supervision with Intermediate Concepts
In this work, we explore an approach for injecting prior domain structure into neural network training by supervising hidden layers of a CNN with intermediate concepts that normally are not observed in practice.
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation.
Comparative Design Space Exploration of Dense and Semi-Dense SLAM
SLAM has matured significantly over the past few years, and is beginning to appear in serious commercial products.
Towards Scene Understanding with Detailed 3D Object Representations
An object class - in our case cars - is modeled as a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices and faces.
Introducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM
Real-time dense computer vision and SLAM offer great potential for a new level of scene modelling, tracking and real environmental interaction for many types of robot, but their high computational requirements mean that use on mass market embedded platforms is challenging.
Explicit Occlusion Modeling for 3D Object Class Representations
In this paper, we tackle the challenge of modeling occlusion in the context of a 3D geometric object class model that is capable of fine-grained, part-level 3D object reconstruction.
