Saved in:
Bibliographic Details
Main Authors: Dhar, Sauptik, Ramakrishnan, Naveen, Munson, Michelle
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.20287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911228123676672
author Dhar, Sauptik
Ramakrishnan, Naveen
Munson, Michelle
author_facet Dhar, Sauptik
Ramakrishnan, Naveen
Munson, Michelle
contents Large Vision Language models have seen huge application in several sports use-cases recently. Most of these works have been targeted towards a limited subset of popular sports like soccer, cricket, basketball etc; focusing on generative tasks like visual question answering, highlight generation. This work analyzes the applicability of the modern video foundation models (both encoder and decoder) for a very niche but hugely popular dance sports - breakdance. Our results show that Video Encoder models continue to outperform state-of-the-art Video Language Models for prediction tasks. We provide insights on how to choose the encoder model and provide a thorough analysis into the workings of a finetuned decoder model for breakdance video classification.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20287
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breakdance Video classification in the age of Generative AI
Dhar, Sauptik
Ramakrishnan, Naveen
Munson, Michelle
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Large Vision Language models have seen huge application in several sports use-cases recently. Most of these works have been targeted towards a limited subset of popular sports like soccer, cricket, basketball etc; focusing on generative tasks like visual question answering, highlight generation. This work analyzes the applicability of the modern video foundation models (both encoder and decoder) for a very niche but hugely popular dance sports - breakdance. Our results show that Video Encoder models continue to outperform state-of-the-art Video Language Models for prediction tasks. We provide insights on how to choose the encoder model and provide a thorough analysis into the workings of a finetuned decoder model for breakdance video classification.
title Breakdance Video classification in the age of Generative AI
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.20287