Related papers: SimVPv2: Towards Simple yet Powerful Spatiotempora…

In this paper, we provide a fine-grain machine learning-based method, PerfNetV2, which improves the accuracy of our previous work for modeling the neural network performance on a variety of GPU accelerators. Given an application, the…

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…

The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems.…

A clear understanding of where humans move in a scenario, their usual paths and speeds, and where they stop, is very important for different applications, such as mobility studies in urban areas or robot navigation tasks within…

Spiking neural networks (SNNs) have demonstrated significant potential in real-time multi-sensor perception tasks due to their event-driven and parameter-efficient characteristics. A key challenge is the timestep-wise iterative update of…

Accurate traffic state prediction is the foundation of transportation control and guidance. It is very challenging due to the complex spatiotemporal dependencies in traffic data. Existing works cannot perform well for multi-step traffic…

Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e.,…

We present a deep layered architecture that generalizes convolutional neural networks (ConvNets). The architecture, called SimNets, is driven by two operators: (i) a similarity function that generalizes inner-product, and (ii) a…

In visual planning (VP), an agent learns to plan goal-directed behavior from observations of a dynamical system obtained offline, e.g., images obtained from self-supervised robot interaction. Most previous works on VP approached the problem…

The efficiency of modern machine intelligence depends on high accuracy with minimal computational cost. In spiking neural networks (SNNs), synaptic delays are crucial for encoding temporal structure, yet existing models treat them as fully…

Spatio-temporal forecasting is essential for real-world applications such as traffic management and urban computing. Although recent methods have shown improved accuracy, they often fail to account for dynamic deviations between current…

Recent object tracking methods depend upon deep networks or convoluted architectures. Most of those trackers can hardly meet real-time processing requirements on mobile platforms with limited computing resources. In this work, we introduce…

Vectorized high-definition map online construction has garnered considerable attention in the field of autonomous driving research. Most existing approaches model changeable map elements using a fixed number of points, or predict local maps…

Large language models have achieved remarkable success in time series prediction tasks, but their substantial computational and memory requirements limit deployment on lightweight platforms. In this paper, we propose the Symbolic Transition…

Spiking neural networks (SNNs) are brain-inspired mathematical models with the ability to process information in the form of spikes. SNNs are expected to provide not only new machine-learning algorithms, but also energy-efficient…

There has been huge progress on video action recognition in recent years. However, many works focus on tweaking existing 2D backbones due to the reliance of ImageNet pretraining, which restrains the models from achieving higher efficiency…

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…

Visual Prompt Tuning (VPT) techniques have gained prominence for their capacity to adapt pre-trained Vision Transformers (ViTs) to downstream visual tasks using specialized learnable tokens termed as prompts. Contemporary VPT methodologies,…

Spatio-temporal forecasting is a critical component of various smart city applications, such as transportation optimization, energy management, and socio-economic analysis. Recently, several automated spatio-temporal forecasting methods…

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…