Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Nguyen, Thong Thanh
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.00683
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917381713952768
author Nguyen, Thong Thanh
author_facet Nguyen, Thong Thanh
contents This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an automatic annotation framework that utilizes large vision-language models and a noise-robust contrastive learning objective with a subtractive angular margin; (2) a parameter-efficient fine-tuning strategy using "recurrent adapters" to capture temporal dynamics in low-data regimes; (3) the integration of State Space Layers (SSL) for efficient long-form video modeling, supported by the introduction of two new long-term benchmarks for egocentric and feature-length content; (4) a novel contrastive learning framework designed to explicitly model fine-grained relations between motions and video moments; and (5) a comprehensive empirical study on Large Vision-Language Models (LVLMs) that identifies the visual-language interface as a bottleneck for temporal reasoning, leading to a new "temporal-oriented recipe" for upscaled video understanding. Collectively, these contributions demonstrate that explicit temporal modeling significantly enhances a model's ability to represent and reason about the fluid nature of video content.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00683
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Video Understanding: Through A Temporal Lens
Nguyen, Thong Thanh
Computer Vision and Pattern Recognition
This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an automatic annotation framework that utilizes large vision-language models and a noise-robust contrastive learning objective with a subtractive angular margin; (2) a parameter-efficient fine-tuning strategy using "recurrent adapters" to capture temporal dynamics in low-data regimes; (3) the integration of State Space Layers (SSL) for efficient long-form video modeling, supported by the introduction of two new long-term benchmarks for egocentric and feature-length content; (4) a novel contrastive learning framework designed to explicitly model fine-grained relations between motions and video moments; and (5) a comprehensive empirical study on Large Vision-Language Models (LVLMs) that identifies the visual-language interface as a bottleneck for temporal reasoning, leading to a new "temporal-oriented recipe" for upscaled video understanding. Collectively, these contributions demonstrate that explicit temporal modeling significantly enhances a model's ability to represent and reason about the fluid nature of video content.
title Video Understanding: Through A Temporal Lens
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.00683