Related papers: Multi-Scale Control Signal-Aware Transformer for M…
Traffic signal control is a critical challenge in urban transportation, requiring coordination among multiple intersections to optimize network-wide traffic flow. While reinforcement learning has shown promise for adaptive signal control,…
The multi-modality and stochastic characteristics of human behavior make motion prediction a highly challenging task, which is critical for autonomous driving. While deep learning approaches have demonstrated their great potential in this…
Decision Transformers, in their vanilla form, struggle to perform on image-based environments with multi-discrete action spaces. Although enhanced Decision Transformer architectures have been developed to improve performance, these methods…
This paper presents a novel framework to build a voice conversion (VC) system by learning from a text-to-speech (TTS) synthesis system, that is called TTS-VC transfer learning. We first develop a multi-speaker speech synthesis system with…
We consider the problem of synthesizing multi-action human motion sequences of arbitrary lengths. Existing approaches have mastered motion sequence generation in single action scenarios, but fail to generalize to multi-action and…
Human motion synthesis is a fundamental task in computer animation. Despite recent progress in this field utilizing deep learning and motion capture data, existing methods are always limited to specific motion categories, environments, and…
Human motion synthesis is a long-standing problem with various applications in digital twins and the Metaverse. However, modern deep learning based motion synthesis approaches barely consider the physical plausibility of synthesized motions…
We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an…
Multi-Stage Classifier (MSC) - several classifiers working sequentially in an arranged order and classification decision is partially made at each step - is widely used in industrial applications for various resource limitation reasons. The…
The synthesis of human motion has traditionally been addressed through task-dependent models that focus on specific challenges, such as predicting future motions or filling in intermediate poses conditioned on known key-poses. In this…
This study proposes an unsupervised sequence-to-sequence learning approach that automatically assesses the motion-induced reliability degradation of the cardiac volume signal (CVS) in multi-channel electrical impedance-based hemodynamic…
We present a novel method for populating 3D indoor scenes with virtual humans that can navigate in the environment and interact with objects in a realistic manner. Existing approaches rely on training sequences that contain captured human…
Expressive synthetic speech is essential for many human-computer interaction and audio broadcast scenarios, and thus synthesizing expressive speech has attracted much attention in recent years. Previous methods performed the expressive…
Action recognition from multi-modal and multi-view observations holds significant potential for applications in surveillance, robotics, and smart environments. However, existing methods often fall short of addressing real-world challenges…
Standard decoding approaches rely on model-based channel estimation methods to compensate for varying channel effects, which degrade in performance whenever there is a model mismatch. Recently proposed Deep learning based neural decoders…
Multimodal sentiment analysis in videos is a key task in many real-world applications, which usually requires integrating multimodal streams including visual, verbal and acoustic behaviors. To improve the robustness of multimodal fusion,…
This paper develops a controller synthesis approach for a multi-agent system (MAS) with intermittent communication. We adopt a leader-follower scheme, where a mobile leader with absolute position sensors switches among a set of followers…
Machine learning techniques have been shown to be effective to recognize different phases of matter and produce phase diagrams in the parameter space interested, while they usually require prior labeled data to perform well. Here, we…
Controllable human motion synthesis is essential for applications in AR/VR, gaming and embodied AI. Existing methods often focus solely on either language or full trajectory control, lacking precision in synthesizing motions aligned with…
Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics. Challenges remain in these fields for generating diverse motions given past…