Related papers: Learning Human Motion with Temporally Conditional …
Transformer-based methods for 3D human pose estimation face significant computational challenges due to the quadratic growth of self-attention mechanism complexity with sequence length. Recently, the Mamba model has substantially reduced…
Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which…
Although learned video compression methods have exhibited outstanding performance, most of them typically follow a hybrid coding paradigm that requires explicit motion estimation and compensation, resulting in a complex solution for video…
The goal of this work is the development of a motion model for sequentially timed movement actions in robotic systems under specific consideration of temporal stabilization, that is maintaining an approximately constant overall movement…
Vehicle trajectories provide crucial movement information for various real-world applications. To better utilize vehicle trajectories, it is essential to develop a trajectory learning approach that can effectively and efficiently extract…
Human motion prediction is essential for the safe and smooth operation of mobile service robots and intelligent vehicles around people. Commonly used neural network-based approaches often require large amounts of complete trajectories to…
Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning…
Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…
Inductive biases influence the behavior and performance of sequential models. In this work, we study an underexplored inductive bias in sequential modeling: continuity in time. We ask a simple question: do models motivated by…
In the field of autonomous systems, accurately predicting the trajectories of nearby vehicles and pedestrians is crucial for ensuring both safety and operational efficiency. This paper introduces a novel methodology for trajectory…
Human motion prediction is a necessary component for many applications in robotics and autonomous driving. Recent methods propose using sequence-to-sequence deep learning models to tackle this problem. However, they do not focus on…
Long-term time-series forecasting remains challenging due to the difficulty in capturing long-term dependencies, achieving linear scalability, and maintaining computational efficiency. We introduce TimeMachine, an innovative model that…
In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, {\Delta}t, and training over a diverse range of {\Delta}t values --…
Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like…
As a fundamental task in long-form video understanding, temporal action detection (TAD) aims to capture inherent temporal relations in untrimmed videos and identify candidate actions with precise boundaries. Over the years, various…
This paper studies the task of conditional Human Motion Animation (cHMA). Given a source image and a driving video, the model should animate the new frame sequence, in which the person in the source image should perform a similar motion as…
Training urban spatio-temporal foundation models that generalize well across diverse regions and cities is critical for deploying urban services in unseen or data-scarce regions. Recent studies have typically focused on fusing cross-domain…
The Mamba model has gained significant attention for its computational advantages over Transformer-based models, while achieving comparable performance across a wide range of language tasks. Like Transformers, Mamba exhibits in-context…
Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples. CL enables prediction on new tasks by incorporating sequential training samples. Building on this…
Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction-…