Related papers: Sparse Convolutional Recurrent Learning for Effici…

Event camera, a novel neuromorphic vision sensor, records data with high temporal resolution and wide dynamic range, offering new possibilities for accurate visual representation in challenging scenarios. However, event data is inherently…

Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for robust object detection. While Spiking Neural Networks (SNNs) on neuromorphic hardware are often considered for…

As a basic component of SE(3)-equivariant deep feature learning, steerable convolution has recently demonstrated its advantages for 3D semantic analysis. The advantages are, however, brought by expensive computations on dense, volumetric…

3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that…

Spatiotemporal prediction of event data is a challenging task with a long history of research. While recent work in spatiotemporal prediction has leveraged deep sequential models that substantially improve over classical approaches, these…

Neuromorphic event-based dynamic vision sensors (DVS) have much faster sampling rates and a higher dynamic range than frame-based imaging sensors. However, they are sensitive to background activity (BA) events that are unwanted. There are…

In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking. Our recurrent convolutional network exploits the history of locations as well as the distinctive visual…

Bird-eye-view (BEV) based methods have made great progress recently in multi-view 3D detection task. Comparing with BEV based methods, sparse based methods lag behind in performance, but still have lots of non-negligible merits. To push…

We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models,…

Event-based image representations are fundamentally different to traditional dense images. This poses a challenge to apply current state-of-the-art models for object detection as they are designed for dense images. In this work we evaluate…

In sparse coding, we attempt to extract features of input vectors, assuming that the data is inherently structured as a sparse superposition of basic building blocks. Similarly, neural networks perform a given task by learning features of…

Deep convolutional neural network significantly boosted the capability of salient object detection in handling large variations of scenes and object appearances. However, convolution operations seek to generate strong responses on…

Sparse algorithms offer great flexibility for multi-view temporal perception tasks. In this paper, we present an enhanced version of Sparse4D, in which we improve the temporal fusion module by implementing a recursive form of multi-frame…

Sparse reduced-rank regression is an important tool to uncover meaningful dependence structure between large numbers of predictors and responses in many big data applications such as genome-wide association studies and social media…

Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…

Although synthetic aperture imaging (SAI) can achieve the seeing-through effect by blurring out off-focus foreground occlusions while recovering in-focus occluded scenes from multi-view images, its performance is often deteriorated by dense…

Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs should be well-suited for processing them. However, when applying SNNs…

Event-based vision sensors, inspired by biological neural systems, asynchronously capture local pixel-level intensity changes as a sparse event stream containing position, polarity, and timestamp information. These neuromorphic sensors…

Event-based sensors are drawing increasing attention due to their high temporal resolution, low power consumption, and low bandwidth. To efficiently extract semantically meaningful information from sparse data streams produced by such…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…