Leveraging Local Temporal Information for Multimodal Scene Classification

by   Saurabh Sahu, et al.

Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video understanding is still relatively unexplored. Moreover, these models fail to exploit the strong temporal relationships between the neighboring video frames to get potent frame-level representations. In this paper, we propose a novel self-attention block that leverages both local and global temporal relationships between the video frames to obtain better contextualized representations for the individual frames. This enables the model to understand the video at various granularities. We illustrate the performance of our models on the large scale YoutTube-8M data set on the task of video categorization and further analyze the results to showcase improvement.



There are no comments yet.


page 2

page 4


Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training

The introduction of Transformer model has led to tremendous advancements...

ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis

Deep Convolutional Neural Networks (CNNs) are powerful models that have ...

Flow-Guided Sparse Transformer for Video Deblurring

Exploiting similar and sharper scene patches in spatio-temporal neighbor...

ViViT: A Video Vision Transformer

We present pure-transformer based models for video classification, drawi...

Exploiting Temporal Coherence for Multi-modal Video Categorization

Multimodal ML models can process data in multiple modalities (e.g., vide...

Video Question Generation via Cross-Modal Self-Attention Networks Learning

Video Question Answering (Video QA) is a critical and challenging task i...

VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning

Video understanding relies on perceiving the global content and modeling...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.