Search Results for author:
Found 9 papers, 0 papers with code
Leveraging Local Temporal Information for Multimodal Scene Classification
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.
Can't Fool Me: Adversarially Robust Transformer for Video Understanding
To address this, several techniques have been proposed to increase robustness of a model for image classification tasks.
Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training
GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts.
Cross-modal Learning for Multi-modal Video Categorization
Multi-modal machine learning (ML) models can process data in multiple modalities (e. g., video, audio, text) and are useful for video content analysis in a variety of problems (e. g., object detection, scene understanding, activity recognition).
Exploiting Temporal Coherence for Multi-modal Video Categorization
Multimodal ML models can process data in multiple modalities (e. g., video, images, audio, text) and are useful for video content analysis in a variety of problems (e. g., object detection, scene understanding).
Modeling Feature Representations for Affective Speech using Generative Adversarial Networks
In this work, we experiment with variants of GAN architectures to generate feature vectors corresponding to an emotion in two ways: (i) A generator is trained with samples from a mixture prior.
On Enhancing Speech Emotion Recognition using Generative Adversarial Networks
GANs consist of a discriminator and a generator working in tandem playing a min-max game to learn a target underlying data distribution; when fed with data-points sampled from a simpler distribution (like uniform or Gaussian distribution).
Semi-supervised and Transfer learning approaches for low resource sentiment classification
Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event.
Adversarial Auto-encoders for Speech Based Emotion Recognition
Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition.
