Search Results for author: Shreyank N Gowda

Found 18 papers, 5 papers with code

Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques

no code implementations31 Jan 2024 Shreyank N Gowda, Yash Thakre, Shashank Narayana Gowda, Xiaobo Jin

This paper offers a comprehensive analysis of recent advancements in video inpainting techniques, a critical subset of computer vision and artificial intelligence.

Computational Efficiency Video Inpainting

Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts

no code implementations21 Jan 2024 Kiyoon Kim, Shreyank N Gowda, Panagiotis Eustratiadis, Antreas Antoniou, Robert B Fisher

More precisely, we created dataset splits of HMDB-51 or UCF-101 for training, and Kinetics-400 for testing, using the subset of the classes that are overlapping in both train and test datasets.

Action Recognition Scheduling +2

Watt For What: Rethinking Deep Learning's Energy-Performance Relationship

no code implementations10 Oct 2023 Shreyank N Gowda, Xinyue Hao, Gen Li, Laura Sevilla-Lara, Shashank Narayana Gowda

Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy.

Telling Stories for Common Sense Zero-Shot Action Recognition

1 code implementation29 Sep 2023 Shreyank N Gowda, Laura Sevilla-Lara

The textual narratives forge connections between seen and unseen classes, overcoming the bottleneck of labeled data that has long impeded advancements in this exciting domain.

Action Recognition Common Sense Reasoning +5

Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning

no code implementations4 Sep 2023 Chong Zhang, Mingyu Jin, Qinkai Yu, Haochen Xue, Shreyank N Gowda, Xiaobo Jin

Generalized zero-shot learning (GZSL) aims to recognize samples from both seen and unseen classes using only seen class samples for training.

Generalized Zero-Shot Learning Metric Learning

Optimizing ViViT Training: Time and Memory Reduction for Action Recognition

no code implementations7 Jun 2023 Shreyank N Gowda, Anurag Arnab, Jonathan Huang

In this paper, we address the challenges posed by the substantial training time and memory consumption associated with video transformers, focusing on the ViViT (Video Vision Transformer) model, in particular the Factorised Encoder version, as our baseline for action recognition tasks.

Action Recognition

Synthetic Sample Selection for Generalized Zero-Shot Learning

no code implementations6 Apr 2023 Shreyank N Gowda

Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training.

feature selection Generalized Zero-Shot Learning +1

Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition

1 code implementation25 Jan 2022 Kiyoon Kim, Shreyank N Gowda, Oisin Mac Aodha, Laura Sevilla-Lara

We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost.

Action Recognition Optical Flow Estimation +2

A New Split for Evaluating True Zero-Shot Action Recognition

1 code implementation27 Jul 2021 Shreyank N Gowda, Laura Sevilla-Lara, Kiyoon Kim, Frank Keller, Marcus Rohrbach

We benchmark several recent approaches on the proposed True Zero-Shot(TruZe) Split for UCF101 and HMDB51, with zero-shot and generalized zero-shot evaluation.

Few-Shot action recognition Few Shot Action Recognition +2

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition

no code implementations18 Jan 2021 Shreyank N Gowda, Laura Sevilla-Lara, Frank Keller, Marcus Rohrbach

Theproblem can be seen as learning a function which general-izes well to instances of unseen classes without losing dis-crimination between classes.

Action Recognition Clustering +4

SMART Frame Selection for Action Recognition

no code implementations19 Dec 2020 Shreyank N Gowda, Marcus Rohrbach, Laura Sevilla-Lara

In this work, however, we focus on the more standard short, trimmed action recognition problem.

Action Recognition

Using an ensemble color space model to tackle adversarial examples

no code implementations10 Mar 2020 Shreyank N Gowda, Chun Yuan

Minute pixel changes in an image drastically change the prediction that the deep learning model makes.

Adversarial Attack Autonomous Driving

ColorNet: Investigating the importance of color spaces for image classification

1 code implementation1 Feb 2019 Shreyank N Gowda, Chun Yuan

These color images are taken as input in the form of RGB images and classification is done without modifying them.

Classification General Classification +1

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