88 citations · 112 across the 12 of their papers we have counts for
14 papers
Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization
Usman Nizamani, M. Shaheer Luqman, Fawad Javed Fateh +4
Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit be…
A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics
Fawad Javed Fateh, Ali Shah Ali, Murad Popattia +4
We present a novel hierarchical spatiotemporal action tokenizer for in-context imitation learning. We first propose a hierarchical approach, which consists of two successive levels…
Action Segmentation Using 2D Skeleton Heatmaps and Multi-Modality Fusion
Syed Waleed Hyder, Muhammad Usama, Anas Zafar +5
This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition. In contrast with state-of-the-art methods which dir…
Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion
Quoc-Huy Tran, Muhammad Ahmed, Murad Popattia +3
This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the st…
Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment
Quoc-Huy Tran, Ahmed Mehmood, Muhammad Ahmed +4
This paper presents an unsupervised transformer-based framework for temporal activity segmentation which leverages not only frame-level cues but also segment-level cues. This is in…
Timestamp-Supervised Action Segmentation with Graph Convolutional Networks
Hamza Khan, Sanjay Haresh, Awais Ahmed +4
We introduce a novel approach for temporal activity segmentation with timestamp supervision. Our main contribution is a graph convolutional network, which is learned in an end-to-e…
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering
Sateesh Kumar, Sanjay Haresh, Awais Ahmed +3
We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and onlin…
Learning by Aligning Videos in Time
Sanjay Haresh, Sateesh Kumar, Huseyin Coskun +4
We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level informa…
Towards Anomaly Detection in Dashcam Videos
Sanjay Haresh, Sateesh Kumar, M. Zeeshan Zia +1
Inexpensive sensing and computation, as well as insurance innovations, have made smart dashboard cameras ubiquitous. Increasingly, simple model-driven computer vision algorithms fo…
Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
Huseyin Coskun, Zeeshan Zia, Bugra Tekin +4
The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot tran…
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Mohammed E. Fathy, Quoc-Huy Tran, M. Zeeshan Zia +2
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors t…
Deep Supervision with Intermediate Concepts
Chi Li, M. Zeeshan Zia, Quoc-Huy Tran +3
Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). H…
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
Chi Li, M. Zeeshan Zia, Quoc-Huy Tran +3
Monocular 3D object parsing is highly desirable in various scenarios including occlusion reasoning and holistic scene interpretation. We present a deep convolutional neural network…
Towards Scene Understanding with Detailed 3D Object Representations
M. Zeeshan Zia, Michael Stark, Konrad Schindler
Current approaches to semantic image and scene understanding typically employ rather simple object representations such as 2D or 3D bounding boxes. While such coarse models are rob…