13 citations · 25 across the 9 of their papers we have counts for
10 papers
On Deep Neural Network Calibration by Regularization and its Impact on Refinement
Aditya Singh, Alessandro Bay, Biswa Sengupta +1
Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical syst…
Assessing The Importance Of Colours For CNNs In Object Recognition
Aditya Singh, Alessandro Bay, Andrea Mirabile
Humans rely heavily on shapes as a primary cue for object recognition. As secondary cues, colours and textures are also beneficial in this regard. Convolutional neural networks (CN…
Filtering Point Targets via Online Learning of Motion Models
Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez
Filtering point targets in highly cluttered and noisy data frames can be very challenging, especially for complex target motions. Fixed motion models can fail to provide accurate p…
Real-time tracker with fast recovery from target loss
Alessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez +1
In this paper, we introduce a variation of a state-of-the-art real-time tracker (CFNet), which adds to the original algorithm robustness to target loss without a significant comput…
Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking
Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez
Defining a multi-target motion model, which is an important step of tracking algorithms, can be very challenging. Using fixed models (as in several generative Bayesian algorithms,…
Hide and Seek tracker: Real-time recovery from target loss
Alessandro Bay, Panagiotis Sidiropoulos, Eduard Vazquez +1
In this paper, we examine the real-time recovery of a video tracker from a target loss, using information that is already available from the original tracker and without a signific…
Deep Recurrent Neural Network for Multi-target Filtering
Mehryar Emambakhsh, Alessandro Bay, Eduard Vazquez
This paper addresses the problem of fixed motion and measurement models for multi-target filtering using an adaptive learning framework. This is performed by defining target tuples…
GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
Alessandro Bay, Biswa Sengupta
The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent ne…
StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks
Alessandro Bay, Biswa Sengupta
A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as are…
Approximating meta-heuristics with homotopic recurrent neural networks
Alessandro Bay, Biswa Sengupta
Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding th…