21 citations · 24 across the 5 of their papers we have counts for
5 papers · 1 filter
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
Kiyoon Kim, Shreyank N Gowda, Panagiotis Eustratiadis +2
Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shi…
An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
Kiyoon Kim, Davide Moltisanti, Oisin Mac Aodha +1
Precisely naming the action depicted in a video can be a challenging and oftentimes ambiguous task. In contrast to object instances represented as nouns (e.g. dog, cat, chair, etc.…
Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition
Kiyoon Kim, Shreyank N Gowda, Oisin Mac Aodha +1
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost. Existing approaches focus on modifyin…
A New Split for Evaluating True Zero-Shot Action Recognition
Shreyank N Gowda, Laura Sevilla-Lara, Kiyoon Kim +2
Zero-shot action recognition is the task of classifying action categories that are not available in the training set. In this setting, the standard evaluation protocol is to use ex…
Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
Michael S. Ryoo, Kiyoon Kim, Hyun Jong Yang
This paper presents an approach for recognizing human activities from extreme low resolution (e.g., 16x12) videos. Extreme low resolution recognition is not only necessary for anal…