EvSegSNN : Segmentation sémantique neuromorphique pour la vision événementielle
-
May 22, 2023 (v1)Conference paperUploaded on: October 11, 2023
-
July 5, 2022 (v1)Conference paper
This work was supported by the European Union's ERA-NET CHIST-ERA 2018 research and innovation programme under grant agreement ANR-19-CHR3-0008.
Uploaded on: February 22, 2023 -
June 28, 2021 (v1)Conference paper
Visual attention can be defined as the behavioral and cognitive process of selectively focusing on a discrete aspect of sensory cues while disregarding other perceivable information. This biological mechanism, more specifically saliency detection, has long been used in multimedia indexing to drive the analysis only on relevant parts of images...
Uploaded on: February 22, 2023 -
July 19, 2020 (v1)Conference paper
The bio-inspired concept of Spike-Timing-Dependent Plasticity (STDP) derived from neurobiology is increasingly used in Spiking Neural Networks (SNNs) nowadays. Mostly found in unsupervised learning, though recent work has shown its usefulness in supervised or reinforced paradigms too, STDP is a key element to understanding SNN architectures'...
Uploaded on: December 4, 2022 -
July 5, 2022 (v1)Conference paper
This work was supported by the European Union's ERA-NET CHIST-ERA 2018 research and innovation programme under grant agreement ANR-19-CHR3-0008.
Uploaded on: December 3, 2022 -
June 28, 2021 (v1)Conference paper
Visual attention can be defined as the behavioral and cognitive process of selectively focusing on a discrete aspect of sensory cues while disregarding other perceivable information. This biological mechanism, more specifically saliency detection, has long been used in multimedia indexing to drive the analysis only on relevant parts of images...
Uploaded on: December 4, 2022 -
February 27, 2020 (v1)Conference paper
Being able to estimate motion features is an essential step in dynamic scene analysis. Optical flow typically quantifies the apparent motion of objects. Motion features can benefit from bio-inspired models of mammalian retina, where ganglion cells show preferences to global patterns of direction, especially in the four cardinal translatory...
Uploaded on: December 4, 2022 -
July 5, 2022 (v1)Publication
This work was supported by the European Union's ERA-NET CHIST-ERA 2018 research and innovation programme under grant agreement ANR-19-CHR3-0008.
Uploaded on: December 3, 2022 -
March 22, 2021 (v1)Publication
Visual attention can be defined as the behavioral and cognitive process of selectively focusing on a discrete aspect of sensory cues while disregarding other perceivable information. This biological mechanism, more specifically saliency detection, has long been used in multimedia indexing to drive the analysis only on relevant parts of images...
Uploaded on: December 3, 2022 -
May 22, 2023 (v1)Conference paper
Sélection neuromorphique d'objets saillants pour la vision événementielle
Uploaded on: October 11, 2023 -
June 18, 2023 (v1)Conference paper
The combined use of spiking neural networks and event cameras is gaining momentum in the field of embedded computer vision as they promise to reduce latency and computational resource requests. However, state-of-the-art embedded neuromorphic models show little interest in modifying input data to optimise model performance, memory usage,...
Uploaded on: September 5, 2023 -
2020 (v1)Journal article
International audience
Uploaded on: December 4, 2022 -
September 8, 2021 (v1)Conference paper
Image classification is one of the most important topics in computer vision. It became crucial for large image datasets. In the literature, several image classification approaches are proposed. In this context, Bag-of-Visual Words (BoVW) model has been widely used. The BoVW model relies on building visual vocabulary and images are represented...
Uploaded on: December 3, 2022 -
2020 (v1)Journal article
International audience
Uploaded on: December 4, 2022 -
June 13, 2022 (v1)Conference paper
Contrary to RGB cameras, Dynamic Vision Sensor (DVS) output visual data in the form of an asynchronous events stream by recording pixel-wise luminance changes at microsecond resolution. While conventional computer vision approaches utilise frame-based input data, thus failing to take full advantage of the high temporal resolution, novel...
Uploaded on: December 4, 2022 -
June 13, 2022 (v1)Publication
Contrary to RGB cameras, Dynamic Vision Sensor (DVS) output visual data in the form of an asynchronous events stream by recording pixel-wise luminance changes at microsecond resolution. While conventional computer vision approaches utilise frame-based input data, thus failing to take full advantage of the high temporal resolution, novel...
Uploaded on: February 22, 2023 -
June 17, 2023 (v1)Conference paper
Human speech perception is intrinsically a multi-modal task since speech production requires the speaker to move the lips, producing visual cues in addition to auditory information. Lip reading consists in visually interpreting the movements of the lips to understand speech, without the use of sound. It is an important task since it can either...
Uploaded on: September 5, 2023 -
June 13, 2022 (v1)Publication
Contrary to RGB cameras, Dynamic Vision Sensor (DVS) output visual data in the form of an asynchronous events stream by recording pixel-wise luminance changes at microsecond resolution. While conventional computer vision approaches utilise frame-based input data, thus failing to take full advantage of the high temporal resolution, novel...
Uploaded on: December 3, 2022 -
December 2, 2024 (v1)Conference paper
Vision Transformers (ViTs) have shown promising results in computer vision tasks, challenging CNN architectures on image classification, segmentation and object detection. However, their quadratic complexity O(N 2 ), where N is the token sequence length, hinders their deployment on edge devices. To tackle this challenge, researchers have...
Uploaded on: January 13, 2025 -
December 29, 2022 (v1)Journal article
Why do neurons communicate through spikes? By definition, spikes are all-or-none neural events which occur at continuous times. In other words, spikes are on one side binary, existing or not without further details, and on the other, can occur at any asynchronous time, without the need for a centralized clock. This stands in stark contrast to...
Uploaded on: February 22, 2023