Related papers: Event Masked Autoencoder: Point-wise Action Recogn…
Event cameras are novel sensors that report brightness changes in the form of asynchronous "events" instead of intensity frames. They have significant advantages over conventional cameras: high temporal resolution, high dynamic range, and…
Current Facial Action Unit (FAU) detection methods generally encounter difficulties due to the scarcity of labeled video training data and the limited number of training face IDs, which renders the trained feature extractor insufficient…
Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent success in a variety of vision tasks. Despite the emergence of…
Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can…
Event camera is an emerging bio-inspired vision sensors that report per-pixel brightness changes asynchronously. It holds noticeable advantage of high dynamic range, high speed response, and low power budget that enable it to best capture…
With their motion-responsive nature, event-based cameras offer significant advantages over traditional cameras for optical flow estimation. While deep learning has improved upon traditional methods, current neural networks adopted for…
Neuromorphic vision-based sensors are gaining popularity in recent years with their ability to capture Spatio-temporal events with low power sensing. These sensors record events or spikes over traditional cameras which helps in preserving…
Event vision sensors (neuromorphic cameras) output sparse, asynchronous ON/OFF events triggered by log-intensity threshold crossings, enabling microsecond-scale sensing with high dynamic range and low data bandwidth. As a nonlinear system,…
In recent years, deep learning has achieved innovative advancements in various fields, including the analysis of human emotions and behaviors. Initiatives such as the Affective Behavior Analysis in-the-wild (ABAW) competition have been…
Anomaly detection without priors of the anomalies is challenging. In the field of unsupervised anomaly detection, traditional auto-encoder (AE) tends to fail based on the assumption that by training only on normal images, the model will not…
Utilization of event-based cameras is expected to improve the visual quality of video frame interpolation solutions. We introduce a learning-based method to exploit moving region boundaries in a video sequence to increase the overall…
Neuromorphic visual sensors are artificial retinas that output sequences of asynchronous events when brightness changes occur in the scene. These sensors offer many advantages including very high temporal resolution, no motion blur and…
Unsupervised visual anomaly detection conveys practical significance in many scenarios and is a challenging task due to the unbounded definition of anomalies. Moreover, most previous methods are application-specific, and establishing a…
The bio-inspired event cameras or dynamic vision sensors are capable of asynchronously capturing per-pixel brightness changes (called event-streams) in high temporal resolution and high dynamic range. However, the non-structural…
Event-based cameras are bio-inspired sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, offering the potential to handle state estimation tasks involving motion blur and high…
Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as they generally are…
In this paper, we present a new data-efficient voxel-based self-supervised learning method for event cameras. Our pre-training overcomes the limitations of previous methods, which either sacrifice temporal information by converting event…
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…
Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness…
This paper presents a neuromorphic, event-driven tactile sensing system for soft, large-area skin, based on the Dynamic Vision Sensors (DVS) integrated with a flexible silicone optical waveguide skin. Instead of repetitively scanning…