Search Results for author:
Found 26 papers, 11 papers with code
Sign Language Translation: Ongoing Development, Challenges and Innovations in the SignON Project
The SignON project (www. signon-project. eu) focuses on the research and development of a Sign Language (SL) translation mobile application and an open communications framework.
Learned Thresholds Token Merging and Pruning for Vision Transformers
Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
Towards the extraction of robust sign embeddings for low resource sign language recognition
However, due to a domain mismatch with their training sets and challenging poses in sign language, they lack robustness on sign language data and image-based models often still outperform keypoint-based models.
Hardware-aware mobile building block evaluation for computer vision
In this work we propose a methodology to accurately evaluate and compare the performance of efficient neural network building blocks for computer vision in a hardware-aware manner.
Machine Translation from Signed to Spoken Languages: State of the Art and Challenges
Automatic translation from signed to spoken languages is an interdisciplinary research domain, lying on the intersection of computer vision, machine translation and linguistics.
Frozen Pretrained Transformers for Neural Sign Language Translation
Our results show that pretrained language models can be used to improve sign language translation performance and that the self-attention patterns in BERT transfer in zero-shot to the encoder and decoder of sign language translation models.
Isolated Sign Recognition from RGB Video using Pose Flow and Self-Attention
However, due to the limited amount of labeled data that is commonly available for training automatic sign (language) recognition, the VTN cannot reach its full potential in this domain.
Ranked #6 on
Sign Language Recognition
on AUTSL
Anchor Pruning for Object Detection
In this work, we show that many anchors in the object detection head can be removed without any loss in accuracy.
PyTorch-Hebbian: facilitating local learning in a deep learning framework
Using this framework, the potential of Hebbian learned feature extractors for image classification is illustrated.
Exchangeable Models in Meta Reinforcement Learning
One recent approach to meta reinforcement learning (meta-RL) is to integrate models for task inference with models for control.
Sign Language Recognition with Transformer Networks
Sign language recognition can be used to speed up the annotation process of these corpora, in order to aid research into sign languages and sign language recognition.
Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped
Using the FORCE learning paradigm, we train a reservoir of spiking neuron populations to act as a central pattern generator.
Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping
Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths.
Addressing Limited Weight Resolution in a Fully Optical Neuromorphic Reservoir Computing Readout
Using optical hardware for neuromorphic computing has become more and more popular recently due to its efficient high-speed data processing capabilities and low power consumption.
Training Passive Photonic Reservoirs with Integrated Optical Readout
As Moore's law comes to an end, neuromorphic approaches to computing are on the rise.
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?
In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations.
BRUNO: A Deep Recurrent Model for Exchangeable Data
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.
Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks
A DReLU, which comes with an unbounded positive and negative image, can be used as a drop-in replacement for a tanh activation function in the recurrent step of Quasi-Recurrent Neural Networks (QRNNs) (Bradbury et al. (2017)).
Improving Language Modeling using Densely Connected Recurrent Neural Networks
In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks.
Fast Face-swap Using Convolutional Neural Networks
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting.
A Differentiable Physics Engine for Deep Learning in Robotics
Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent.
Beyond Temporal Pooling: Recurrence and Temporal Convolutions for Gesture Recognition in Video
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition.
Ranked #1 on
Gesture Recognition
on Montalbano
Rotation-invariant convolutional neural networks for galaxy morphology prediction
Unfortunately, even this approach does not scale well enough to keep up with the increasing availability of galaxy images.
Photonic Delay Systems as Machine Learning Implementations
We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach.
Trainable and Dynamic Computing: Error Backpropagation through Physical Media
Machine learning algorithms, and more in particular neural networks, arguably experience a revolution in terms of performance.
Memristor models for machine learning
In this work, we explore the use of memristor networks for analog approximate computation, based on a machine learning framework called reservoir computing.
