Related papers: Affordance-First Decomposition for Continual Learn…

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. Thanks to the increasing availability of pre-trained image and video…

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…

Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be…

Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…

Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal. To this end, we…

Federated Learning (FL) is a decentralized machine learning framework that enables collaborative model training while respecting data privacy. In various applications, non-uniform availability or participation of users is unavoidable due to…

Deep representation learning methods struggle with continual learning, suffering from both catastrophic forgetting of useful units and loss of plasticity, often due to rigid and unuseful units. While many methods address these two issues…

Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception through irreversible information disposal or inhibit long-range…

Reasoning Video Object Segmentation (ReasonVOS) is a challenging task that requires stable object segmentation across video sequences using implicit and complex textual inputs. Previous methods fine-tune Multimodal Large Language Models…

Federated Learning is a popular distributed learning paradigm in machine learning. Meanwhile, composition optimization is an effective hierarchical learning model, which appears in many machine learning applications such as meta learning…

We address the problem of affordance reasoning in diverse scenes that appear in the real world. Affordances relate the agent's actions to their effects when taken on the surrounding objects. In our work, we take the egocentric view of the…

Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…

Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…

Digital media is ubiquitous and produced in ever-growing quantities. This necessitates a constant evolution of compression techniques, especially for video, in order to maintain efficient storage and transmission. In this work, we aim at…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Exploiting both audio and visual modalities for video classification is a challenging task, as the existing methods require large model architectures, leading to high computational complexity and resource requirements. Smaller…

Pre-trained vision-language models (VLMs) have advanced out-of-distribution (OOD) detection recently. However, existing CLIP-based methods often focus on learning OOD-related knowledge to improve OOD detection, showing limited…

Video diffusion models have rapidly become the dominant paradigm for high-fidelity generative video synthesis, but their practical deployment remains constrained by severe inference costs. Compared with image generation, video synthesis…

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its scalability is limited by synchronization overhead. Asynchronous federated learning (AFL) alleviates this issue by…

Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks is hampered by two main challenges. First, fast adversarial…