Search Results for author: Akshay Asthana

Found 8 papers, 4 papers with code

Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks

no code implementations9 Nov 2023 Kartik Gupta, Akshay Asthana

While quantization-aware training QAT is the well-studied approach to quantize the networks at low precision, most research focuses on over-parameterized networks for classification with limited studies on popular and edge device friendly single-shot object detection and semantic segmentation methods like YOLO.

object-detection Object Detection +2

Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning

1 code implementation4 Aug 2023 Ravikiran Parameshwara, Ibrahim Radwan, Akshay Asthana, Iman Abbasnejad, Ramanathan Subramanian, Roland Goecke

Whilst deep learning techniques have achieved excellent emotion prediction, they still require large amounts of labelled training data, which are (a) onerous and tedious to compile, and (b) prone to errors and biases.

Contrastive Learning Multi-Task Learning

A Weakly Supervised Approach to Emotion-change Prediction and Improved Mood Inference

no code implementations12 Jun 2023 Soujanya Narayana, Ibrahim Radwan, Ravikiran Parameshwara, Iman Abbasnejad, Akshay Asthana, Ramanathan Subramanian, Roland Goecke

Whilst a majority of affective computing research focuses on inferring emotions, examining mood or understanding the \textit{mood-emotion interplay} has received significantly less attention.

Metric Learning

A Comprehensive Performance Evaluation of Deformable Face Tracking "In-the-Wild"

1 code implementation18 Mar 2016 Grigorios G. Chrysos, Epameinondas Antonakos, Patrick Snape, Akshay Asthana, Stefanos Zafeiriou

Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild").

Face Alignment Face Detection +1

Incremental Face Alignment in the Wild

no code implementations CVPR 2014 Akshay Asthana, Stefanos Zafeiriou, Shiyang Cheng, Maja Pantic

We propose very efficient strategies to update the model and we show that is possible to automatically construct robust discriminative person and imaging condition specific models 'in-the-wild' that outperform state-of-the-art generic face alignment strategies.

Face Alignment

Robust Discriminative Response Map Fitting with Constrained Local Models

no code implementations CVPR 2013 Akshay Asthana, Stefanos Zafeiriou, Shiyang Cheng, Maja Pantic

We present a novel discriminative regression based approach for the Constrained Local Models (CLMs) framework, referred to as the Discriminative Response Map Fitting (DRMF) method, which shows impressive performance in the generic face fitting scenario.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.