Related papers: Modality Distillation with Multiple Stream Network…

Person re-identification (ReID) is aimed at identifying the same person across videos captured from different cameras. In the view that networks extracting global features using ordinary network architectures are difficult to extract local…

Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve…

Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage and computational costs, related approaches offer a promising…

Understanding human actions in videos requires more than raw pixel analysis; it relies on high-level semantic reasoning and effective integration of multimodal features. We propose a deep translational action recognition framework that…

Action recognition is a key technology in building interactive metaverses. With the rapid development of deep learning, methods in action recognition have also achieved great advancement. Researchers design and implement the backbones…

Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each…

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is…

Dataset distillation has demonstrated remarkable effectiveness in high-compression scenarios for image datasets. While video datasets inherently contain greater redundancy, existing video dataset distillation methods primarily focus on…

Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering…

This paper presents an innovative approach to address the challenges of translating multi-modal emotion recognition models to a more practical and resource-efficient uni-modal counterpart, specifically focusing on speech-only emotion…

Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant…

The success of deep convolutional neural networks is partially attributed to the massive amount of annotated training data. However, in practice, medical data annotations are usually expensive and time-consuming to be obtained. Considering…

Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…

Egocentric action recognition enables robots to facilitate human-robot interactions and monitor task progress. Existing methods often rely solely on RGB videos, although additional modalities, such as audio, can improve accuracy under…

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing…

Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…

Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…

Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between…

Many recommender models have been proposed to investigate how to incorporate multimodal content information into traditional collaborative filtering framework effectively. The use of multimodal information is expected to provide more…

Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor…