Related papers: Cultivating DNN Diversity for Large Scale Video La…

The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has…

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by…

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves $2^L$ possible label sets especially when the…

Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of grounded relationships between visual content and automatic…

Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…

Accurate vehicle type recognition underpins intelligent transportation and logistics, but severe class imbalance in public datasets suppresses performance on rare categories. We curate a 16-class corpus (~47k images) by merging Kaggle,…

Graph Neural Networks (GNNs) are widely adopted in advanced AI systems due to their capability of representation learning on graph data. Even though GNN explanation is crucial to increase user trust in the systems, it is challenging due to…

Neural networks have recently been proposed for multi-label classification because they are able to capture and model label dependencies in the output layer. In this work, we investigate limitations of BP-MLL, a neural network (NN)…

Many machine learning problems require the prediction of multi-dimensional labels. Such structured prediction models can benefit from modeling dependencies between labels. Recently, several deep learning approaches to structured prediction…

Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this approach has a…

Deep neural networks (DNNs) have revolutionized artificial intelligence but often lack performance when faced with out-of-distribution (OOD) data, a common scenario due to the inevitable domain shifts in real-world applications. This…

Multi-class ensemble classification remains a popular focus of investigation within the research community. The popularization of cloud services has sped up their adoption due to the ease of deploying large-scale machine-learning models. It…

We consider the task of dimensional emotion recognition on video data using deep learning. While several previous methods have shown the benefits of training temporal neural network models such as recurrent neural networks (RNNs) on…

Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their great potential in general-purpose video understanding. To verify the significance of these models, a number of benchmarks have been proposed to diagnose…

We develop a new high-dimensional statistical learning model which can take advantage of structured correlation in data even in the presence of randomness. We completely characterize learnability in this model in terms of…

Human label variation (Plank 2022), or annotation disagreement, exists in many natural language processing (NLP) tasks. To be robust and trusted, NLP models need to identify such variation and be able to explain it. To this end, we created…

Understanding the semantic meaning of content on the web through the lens of entities and concepts has many practical advantages. However, when building large-scale entity extraction systems, practitioners are facing unique challenges…

This paper proposes a new prediction process to explain and predict popularity evolution of YouTube videos. We exploit our recent study on the classification of YouTube videos in order to predict the evolution of videos' view-count. This…

Multi-label classification consists in classifying an instance into two or more classes simultaneously. It is a very challenging task present in many real-world applications, such as classification of biology, image, video, audio, and text.…

We present an approach where two different models (Deep and Shallow) are trained separately on the data and a weighted average of the outputs is taken as the final result. For the Deep approach, we use different combinations of models like…