19 citations · 63 across the 17 of their papers we have counts for
23 papers
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…
Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization
Umer Ahmed, Syed Ahmed Mahmood, Fawad Javed Fateh +3
We propose a novel hierarchical spatiotemporal vector quantization framework for unsupervised skeleton-based temporal action segmentation. We first introduce a hierarchical approac…
Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport
Syed Ahmed Mahmood, Ali Shah Ali, Umer Ahmed +3
We study self-supervised procedure learning, which discovers key steps and their order from a set of unlabeled videos. Previous methods typically learn frame-to-frame correspondenc…
Joint Self-Supervised Video Alignment and Action Segmentation
Ali Shah Ali, Syed Ahmed Mahmood, Mubin Saeed +3
We introduce a novel approach for simultaneous self-supervised video alignment and action segmentation based on a unified optimal transport framework. In particular, we first tackl…
TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos
Fawad Javed Fateh, Umer Ahmed, Hamza Khan +2
We introduce TemporalVLM, a video large language model (video LLM) for temporal reasoning and fine-grained understanding in long videos. Our approach includes a visual encoder for…
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…
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
Khoi D. Nguyen, Quoc-Huy Tran, Khoi Nguyen +2
We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct…
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples
Duong H. Le, Khoi D. Nguyen, Khoi Nguyen +3
In this work, we propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. Specifically, we exploit…
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…
Image Stitching and Rectification for Hand-Held Cameras
Bingbing Zhuang, Quoc-Huy Tran
In this paper, we derive a new differential homography that can account for the scanline-varying camera poses in Rolling Shutter (RS) cameras, and demonstrate its application to ca…
Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling
Yuliang Zou, Pan Ji, Quoc-Huy Tran +2
Monocular visual odometry (VO) suffers severely from error accumulation during frame-to-frame pose estimation. In this paper, we present a self-supervised learning method for VO wi…
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…
Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction
Lokender Tiwari, Pan Ji, Quoc-Huy Tran +3
Classical monocular Simultaneous Localization And Mapping (SLAM) and the recently emerging convolutional neural networks (CNNs) for monocular depth prediction represent two largely…
Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM
Bingbing Zhuang, Quoc-Huy Tran, Pan Ji +3
Self-calibration of camera intrinsics and radial distortion has a long history of research in the computer vision community. However, it remains rare to see real applications of su…
Sales Demand Forecast in E-commerce using a Long Short-Term Memory Neural Network Methodology
Kasun Bandara, Peibei Shi, Christoph Bergmeir +3
Generating accurate and reliable sales forecasts is crucial in the E-commerce business. The current state-of-the-art techniques are typically univariate methods, which produce fore…
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…
Thompson Sampling for Dynamic Pricing
Ravi Ganti, Matyas Sustik, Quoc Tran +1
In this paper we apply active learning algorithms for dynamic pricing in a prominent e-commerce website. Dynamic pricing involves changing the price of items on a regular basis, an…
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…