no code implementations • MADiMa Workshop in ACM Multimedia 2023 • Jesús M. Rodríguez-de-Vera, Pablo Villacorta, Imanol G. Estepa, Marc Bolaños, Ignacio Sarasúa, Bhalaji Nagarajan, Petia Radeva
Trained through an end-to-end multi-task learning process, this method enhances performance in the fine-grained food recognition task, showing exceptional prowess with highly similar classes.
Ranked #4 on Fine-Grained Image Classification on Food-101
Fine-Grained Image Classification Fine-Grained Image Recognition +2
2 code implementations • ICCV 2023 • Imanol G. Estepa, Ignacio Sarasúa, Bhalaji Nagarajan, Petia Radeva
Nearest neighbour based methods have proved to be one of the most successful self-supervised learning (SSL) approaches due to their high generalization capabilities.
no code implementations • 16 Mar 2023 • Pablo Villacorta, Jesús M. Rodríguez-de-Vera, Marc Bolaños, Ignacio Sarasúa, Bhalaji Nagarajan, Petia Radeva
Extensive experimentation shows improvements in the SoTA FGVR benchmarks of up to +1. 3% of accuracy using both CNNs and transformer-based networks.
Fine-Grained Image Recognition Fine-Grained Visual Recognition
1 code implementation • 30th ACM International Conference on Multimedia 2022 • Javier Ródenas, Bhalaji Nagarajan, Marc Bolaños, Petia Radeva
We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets.
Ranked #1 on Fine-Grained Image Classification on FoodX-251
no code implementations • 23 Mar 2022 • Guillem Martinez, Maya Aghaei, Martin Dijkstra, Bhalaji Nagarajan, Femke Jaarsma, Jaap van de Loosdrecht, Petia Radeva, Klaas Dijkstra
Given the hyper-spectral imaging unique potentials in grasping the polymer characteristics of different materials, it is commonly used in sorting procedures.
no code implementations • 31 Oct 2018 • Bhalaji Nagarajan, V Ramana Murthy Oruganti
This paper investigates the influence of different acoustic features, audio-events based features and automatic speech translation based lexical features in complex emotion recognition such as curiosity.
no code implementations • 30 Oct 2018 • Bhalaji Nagarajan, V Ramana Murthy Oruganti
Deep learning is popular as an end-to-end framework extracting the prominent features and performing the classification also.